ICLR 2025 Papers

Skip to yearly menu bar Skip to main content

Layout:

mini compact topic detail

Universal Image Restoration Pre-training via Degradation Classification

On the Benefits of Attribute-Driven Graph Domain Adaptation

Port-Hamiltonian Architectural Bias for Long-Range Propagation in Deep Graph Networks

SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Framer: Interactive Frame Interpolation

Beyond Next Token Prediction: Patch-Level Training for Large Language Models

CTSyn: A Foundation Model for Cross Tabular Data Generation

Aligned Better, Listen Better for Audio-Visual Large Language Models

MiniPLM: Knowledge Distillation for Pre-training Language Models

From an LLM Swarm to a PDDL-empowered Hive: Planning Self-executed Instructions in a Multi-modal Jungle

Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon

DelTA: An Online Document-Level Translation Agent Based on Multi-Level Memory

Discrete Codebook World Models for Continuous Control

The 3D-PC: a benchmark for visual perspective taking in humans and machines

Contextual Self-paced Learning for Weakly Supervised Spatio-Temporal Video Grounding

Faster Cascades via Speculative Decoding

miniCTX: Neural Theorem Proving with (Long-)Contexts

Directional Gradient Projection for Robust Fine-Tuning of Foundation Models

Towards a Unified and Verified Understanding of Group-Operation Networks

Scaling Diffusion Language Models via Adaptation from Autoregressive Models

Multi-domain Distribution Learning for De Novo Drug Design

NeSyC: A Neuro-symbolic Continual Learner For Complex Embodied Tasks in Open Domains

Toward Exploratory Inverse Constraint Inference with Generative Diffusion Verifiers

Federated Domain Generalization with Data-free On-server Matching Gradient

Context-Parametric Inversion: Why Instruction Finetuning May Not Actually Improve Context Reliance

Understanding Optimization in Deep Learning with Central Flows

Inference Optimal VLMs Need Fewer Visual Tokens and More Parameters

StochSync: Stochastic Diffusion Synchronization for Image Generation in Arbitrary Spaces

Data Unlearning in Diffusion Models

Repurposing in AI: A Distinct Approach or an Extension of Creative Problem Solving?

Consistency Models Made Easy

MAD-TD: Model-Augmented Data stabilizes High Update Ratio RL

Fast Uncovering of Protein Sequence Diversity from Structure

Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws

Compute-Optimal LLMs Provably Generalize Better with Scale

AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents

Large Language Models Meet Symbolic Provers for Logical Reasoning Evaluation

Learning mirror maps in policy mirror descent

DiTTo-TTS: Diffusion Transformers for Scalable Text-to-Speech without Domain-Specific Factors

CodeMMLU: A Multi-Task Benchmark for Assessing Code Understanding & Reasoning Capabilities of CodeLLMs

Bridging the Data Provenance Gap Across Text, Speech, and Video

Decoupled Subgraph Federated Learning

Improved Diffusion-based Generative Model with Better Adversarial Robustness

Manifold Learning by Mixture Models of VAEs for Inverse Problems

Generative Classifiers Avoid Shortcut Solutions

AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials

Everything, Everywhere, All at Once: Is Mechanistic Interpretability Identifiable?

Masked Diffusion Models are Secretly Time-Agnostic Masked Models and Exploit Inaccurate Categorical Sampling

Diffusion Bridge Implicit Models

LiFT: Learning to Fine-Tune via Bayesian Parameter Efficient Meta Fine-Tuning

Beyond Worst-Case Dimensionality Reduction for Sparse Vectors

Elucidating the Preconditioning in Consistency Distillation

Improving Data Efficiency via Curating LLM-Driven Rating Systems

Convergence of Score-Based Discrete Diffusion Models: A Discrete-Time Analysis

Retrieval Head Mechanistically Explains Long-Context Factuality

Do LLMs estimate uncertainty well in instruction-following?

Nonconvex Stochastic Optimization under Heavy-Tailed Noises: Optimal Convergence without Gradient Clipping

Large (Vision) Language Models are Unsupervised In-Context Learners

ThunderKittens: Simple, Fast, and $\textit{Adorable}$ Kernels

Achieving Dimension-Free Communication in Federated Learning via Zeroth-Order Optimization

Chain-of-Thought Provably Enables Learning the (Otherwise) Unlearnable

Towards Learning High-Precision Least Squares Algorithms with Sequence Models

Understanding Warmup-Stable-Decay Learning Rates: A River Valley Loss Landscape View

nGPT: Normalized Transformer with Representation Learning on the Hypersphere

A Coefficient Makes SVRG Effective

Homomorphism Counts as Structural Encodings for Graph Learning

Reasoning with Latent Thoughts: On the Power of Looped Transformers

PhysPDE: Rethinking PDE Discovery and a Physical HYpothesis Selection Benchmark

Adam Exploits $\ell_\infty$-geometry of Loss Landscape via Coordinate-wise Adaptivity

SINGER: Stochastic Network Graph Evolving Operator for High Dimensional PDEs

InstantPortrait: One-Step Portrait Editing via Diffusion Multi-Objective Distillation

SurFhead: Affine Rig Blending for Geometrically Accurate 2D Gaussian Surfel Head Avatars

MAP: Multi-Human-Value Alignment Palette

Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form

Diffusion Transformers for Tabular Data Time Series Generation

Optimality and Adaptivity of Deep Neural Features for Instrumental Variable Regression

Revisiting Large-Scale Non-convex Distributionally Robust Optimization

Mufu: Multilingual Fused Learning for Low-Resource Translation with LLM

ImageFolder: Autoregressive Image Generation with Folded Tokens

High-Dynamic Radar Sequence Prediction for Weather Nowcasting Using Spatiotemporal Coherent Gaussian Representation

Aligning Human Motion Generation with Human Perceptions

SEPARATE: A Simple Low-rank Projection for Gradient Compression in Modern Large-scale Model Training Process

Can a MISL Fly? Analysis and Ingredients for Mutual Information Skill Learning

Affine Steerable Equivariant Layer for Canonicalization of Neural Networks

Three Mechanisms of Feature Learning in a Linear Network

Number Cookbook: Number Understanding of Language Models and How to Improve It

MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine

TC-MoE: Augmenting Mixture of Experts with Ternary Expert Choice

Provably Accurate Shapley Value Estimation via Leverage Score Sampling

Remove Symmetries to Control Model Expressivity and Improve Optimization

Attention with Markov: A Curious Case of Single-layer Transformers

The AdEMAMix Optimizer: Better, Faster, Older

LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code

Pyramidal Flow Matching for Efficient Video Generative Modeling

DeLLMa: Decision Making Under Uncertainty with Large Language Models

JPEG Inspired Deep Learning

SpinQuant: LLM Quantization with Learned Rotations

R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference

Param$\Delta$ for Direct Mixing: Post-Train Large Language Model At Zero Cost

ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities

Image-level Memorization Detection via Inversion-based Inference Perturbation

gRNAde: Geometric Deep Learning for 3D RNA inverse design

A Policy-Gradient Approach to Solving Imperfect-Information Games with Best-Iterate Convergence

Boltzmann priors for Implicit Transfer Operators

Conformal Generative Modeling with Improved Sample Efficiency through Sequential Greedy Filtering

How Does Vision-Language Adaptation Impact the Safety of Vision Language Models?

Neuron-based Multifractal Analysis of Neuron Interaction Dynamics in Large Models

Pursuing Feature Separation based on Neural Collapse for Out-of-Distribution Detection

CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control

Hidden in the Noise: Two-Stage Robust Watermarking for Images

Biologically Constrained Barrel Cortex Model Integrates Whisker Inputs and Replicates Key Brain Network Dynamics

LoRA-Pro: Are Low-Rank Adapters Properly Optimized?

Proximal Mapping Loss: Understanding Loss Functions in Crowd Counting & Localization

Pairwise Elimination with Instance-Dependent Guarantees for Bandits with Cost Subsidy

MMKE-Bench: A Multimodal Editing Benchmark for Diverse Visual Knowledge

In-Context Editing: Learning Knowledge from Self-Induced Distributions

AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs

Towards Understanding the Universality of Transformers for Next-Token Prediction

Cocoon: Robust Multi-Modal Perception with Uncertainty-Aware Sensor Fusion

High-dimensional Analysis of Knowledge Distillation: Weak-to-Strong Generalization and Scaling Laws

Learning Task Belief Similarity with Latent Dynamics for Meta-Reinforcement Learning

LongPO: Long Context Self-Evolution of Large Language Models through Short-to-Long Preference Optimization

CryoGEN: Generative Energy-based Models for Cryogenic Electron Tomography Reconstruction

CLIBD: Bridging Vision and Genomics for Biodiversity Monitoring at Scale

MathCoder2: Better Math Reasoning from Continued Pretraining on Model-translated Mathematical Code

Where Am I and What Will I See: An Auto-Regressive Model for Spatial Localization and View Prediction

KAN: Kolmogorov–Arnold Networks

On the expressiveness and spectral bias of KANs

Online Clustering with Nearly Optimal Consistency

Simplifying, Stabilizing and Scaling Continuous-time Consistency Models

The Geometry of Categorical and Hierarchical Concepts in Large Language Models

Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks

Accelerating neural network training: An analysis of the AlgoPerf competition

An Auditing Test to Detect Behavioral Shift in Language Models

Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data

TRENDy: Temporal Regression of Effective Nonlinear Dynamics

HQGS: High-Quality Novel View Synthesis with Gaussian Splatting in Degraded Scenes

Dynamic Contrastive Skill Learning with State-Transition Based Skill Clustering and Dynamic Length Adjustment

Efficient Causal Decision Making with One-sided Feedback

Think Then React: Towards Unconstrained Action-to-Reaction Motion Generation

Ferret-UI 2: Mastering Universal User Interface Understanding Across Platforms

Regularized Proportional Fairness Mechanism for Resource Allocation Without Money

Dynamic Neural Fortresses: An Adaptive Shield for Model Extraction Defense

Agent S: An Open Agentic Framework that Uses Computers Like a Human

Simple ReFlow: Improved Techniques for Fast Flow Models

Protein Language Model Fitness is a Matter of Preference

Forte : Finding Outliers with Representation Typicality Estimation

Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models

MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses

Automated Design of Agentic Systems

Watch Less, Do More: Implicit Skill Discovery for Video-Conditioned Policy

Learning and aligning single-neuron invariance manifolds in visual cortex

Visual-O1: Understanding Ambiguous Instructions via Multi-modal Multi-turn Chain-of-thoughts Reasoning

Learning Video-Conditioned Policy on Unlabelled Data with Joint Embedding Predictive Transformer

Discrete Latent Plans via Semantic Skill Abstractions

Efficient Residual Learning with Mixture-of-Experts for Universal Dexterous Grasping

Adaptive Energy Alignment for Accelerating Test-Time Adaptation

MLLM as Retriever: Interactively Learning Multimodal Retrieval for Embodied Agents

Cross-Embodiment Dexterous Grasping with Reinforcement Learning

From Pixels to Tokens: Byte-Pair Encoding on Quantized Visual Modalities

Knowing Your Target: Target-Aware Transformer Makes Better Spatio-Temporal Video Grounding

Cross-Domain Offline Policy Adaptation with Optimal Transport and Dataset Constraint

Revisiting Source-Free Domain Adaptation: a New Perspective via Uncertainty Control

ESE: Espresso Sentence Embeddings

Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation

Beyond Autoregression: Fast LLMs via Self-Distillation Through Time

Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge

3DIS: Depth-Driven Decoupled Image Synthesis for Universal Multi-Instance Generation

ARLON: Boosting Diffusion Transformers with Autoregressive Models for Long Video Generation

Catastrophic Failure of LLM Unlearning via Quantization

Gaussian Head & Shoulders: High Fidelity Neural Upper Body Avatars with Anchor Gaussian Guided Texture Warping

Robustness Inspired Graph Backdoor Defense

Specialized Foundation Models Struggle to Beat Supervised Baselines

R2Det: Exploring Relaxed Rotation Equivariance in 2D Object Detection

Do You Keep an Eye on What I Ask? Mitigating Multimodal Hallucination via Attention-Guided Ensemble Decoding

LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations

NL-Eye: Abductive NLI For Images

Lost in Prediction: Why Social Media Narratives Don't Help Macroeconomic Forecasting?

Exploring the Camera Bias of Person Re-identification

Improving Probabilistic Diffusion Models With Optimal Diagonal Covariance Matching

Multimodal Large Language Models for Inverse Molecular Design with Retrosynthetic Planning

Towards Foundation Models for Mixed Integer Linear Programming

Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data

Second Order Bounds for Contextual Bandits with Function Approximation

A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image Generation

TetSphere Splatting: Representing High-Quality Geometry with Lagrangian Volumetric Meshes

Wavelet-based Positional Representation for Long Context

Inverse Scaling: When Bigger Isn't Better

Procedural Synthesis of Synthesizable Molecules

Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks

LOIRE: LifelOng learning on Incremental data via pre-trained language model gRowth Efficiently

Conditional Testing based on Localized Conformal $p$-values

Error-quantified Conformal Inference for Time Series

Occlusion-aware Non-Rigid Point Cloud Registration via Unsupervised Neural Deformation Correntropy

VLMaterial: Procedural Material Generation with Large Vision-Language Models

LoCA: Location-Aware Cosine Adaptation for Parameter-Efficient Fine-Tuning

Flow-based Variational Mutual Information: Fast and Flexible Approximations

SMI-Editor: Edit-based SMILES Language Model with Fragment-level Supervision

Beyond the convexity assumption: Realistic tabular data generation under quantifier-free real linear constraints

3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting

Risk-Sensitive Variational Actor-Critic: A Model-Based Approach

Faster Diffusion Sampling with Randomized Midpoints: Sequential and Parallel

Learning How Hard to Think: Input-Adaptive Allocation of LM Computation

On Disentangled Training for Nonlinear Transform in Learned Image Compression

GTR: Improving Large 3D Reconstruction Models through Geometry and Texture Refinement

VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control

Competition Dynamics Shape Algorithmic Phases of In-Context Learning

ADAM Optimization with Adaptive Batch Selection

Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence

Towards Realistic UAV Vision-Language Navigation: Platform, Benchmark, and Methodology

Unsupervised Model Tree Heritage Recovery

Optimality of Matrix Mechanism on $\ell_p^p$-metric

PINP: Physics-Informed Neural Predictor with latent estimation of fluid flows

Adversarial Mixup Unlearning

Pushing the Limits of All-Atom Geometric Graph Neural Networks: Pre-Training, Scaling, and Zero-Shot Transfer

Time-to-Event Pretraining for 3D Medical Imaging

Real-Time Video Generation with Pyramid Attention Broadcast

SBSC: Step-by-Step Coding for Improving Mathematical Olympiad Performance

Denoising Autoregressive Transformers for Scalable Text-to-Image Generation

Few-Class Arena: A Benchmark for Efficient Selection of Vision Models and Dataset Difficulty Measurement

GSBA$^K$: $top$-$K$ Geometric Score-based Black-box Attack

Logicbreaks: A Framework for Understanding Subversion of Rule-based Inference

Bad-PFL: Exploiting Backdoor Attacks against Personalized Federated Learning

Deep Linear Probe Generators for Weight Space Learning

UNSURE: self-supervised learning with Unknown Noise level and Stein's Unbiased Risk Estimate

Preserving Deep Representations in One-Shot Pruning: A Hessian-Free Second-Order Optimization Framework

Wicked Oddities: Selectively Poisoning for Effective Clean-Label Backdoor Attacks

Graph Neural Networks Are More Than Filters: Revisiting and Benchmarking from A Spectral Perspective

Scaling Transformers for Low-Bitrate High-Quality Speech Coding

Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge

DataGen: Unified Synthetic Dataset Generation via Large Language Models

GUI-World: A Video Benchmark and Dataset for Multimodal GUI-oriented Understanding

CR-CTC: Consistency regularization on CTC for improved speech recognition

DEEM: Diffusion models serve as the eyes of large language models for image perception

TS-LIF: A Temporal Segment Spiking Neuron Network for Time Series Forecasting

FLOPS: Forward Learning with OPtimal Sampling

AdvPaint: Protecting Images from Inpainting Manipulation via Adversarial Attention Disruption

An Illustrated Guide to Automatic Sparse Differentiation

RGB-Event ISP: The Dataset and Benchmark

Animate-X: Universal Character Image Animation with Enhanced Motion Representation

SimPER: A Minimalist Approach to Preference Alignment without Hyperparameters

Dataset Distillation via Knowledge Distillation: Towards Efficient Self-Supervised Pre-training of Deep Networks

OmniKV: Dynamic Context Selection for Efficient Long-Context LLMs

Inverse Constitutional AI: Compressing Preferences into Principles

Neural Functions for Learning Periodic Signal

MACPO: Weak-to-Strong Alignment via Multi-Agent Contrastive Preference Optimization

Infilling Score: A Pretraining Data Detection Algorithm for Large Language Models

Measuring And Improving Persuasiveness Of Large Language Models

Teaching Human Behavior Improves Content Understanding Abilities Of VLMs

Diff-Prompt: Diffusion-driven Prompt Generator with Mask Supervision

Competing Large Language Models in Multi-Agent Gaming Environments

Zeroth-Order Fine-Tuning of LLMs with Transferable Static Sparsity

From Commands to Prompts: LLM-based Semantic File System for AIOS

AutoCGP: Closed-Loop Concept-Guided Policies from Unlabeled Demonstrations

Robust System Identification: Finite-sample Guarantees and Connection to Regularization

Accelerating 3D Molecule Generation via Jointly Geometric Optimal Transport

Spurious Forgetting in Continual Learning of Language Models

Training Large Language Models for Retrieval-Augmented Question Answering through Backtracking Correction

Transition Path Sampling with Improved Off-Policy Training of Diffusion Path Samplers

Tight Lower Bounds under Asymmetric High-Order Hölder Smoothness and Uniform Convexity

Generalization Bounds and Model Complexity for Kolmogorov–Arnold Networks

Discrete Diffusion Schrödinger Bridge Matching for Graph Transformation

CyberHost: A One-stage Diffusion Framework for Audio-driven Talking Body Generation

A Statistical Framework for Ranking LLM-based Chatbots

KooNPro: A Variance-Aware Koopman Probabilistic Model Enhanced by Neural Process for Time Series Forecasting

Lie Algebra Canonicalization: Equivariant Neural Operators under arbitrary Lie Groups

Block Verification Accelerates Speculative Decoding

Continuous Diffusion for Mixed-Type Tabular Data

Intricacies of Feature Geometry in Large Language Models

What to align in multimodal contrastive learning?

MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Masked Image Modeling Representations

Shape as Line Segments: Accurate and Flexible Implicit Surface Representation

Generative Flows on Synthetic Pathway for Drug Design

DartControl: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion Control

NExUME: Adaptive Training and Inference for DNNs under Intermittent Power Environments

PEARL: Parallel Speculative Decoding with Adaptive Draft Length

Weakly Supervised Video Scene Graph Generation via Natural Language Supervision

Mixture of Attentions For Speculative Decoding

Data Shapley in One Training Run

PALMBENCH: A COMPREHENSIVE BENCHMARK OF COMPRESSED LARGE LANGUAGE MODELS ON MOBILE PLATFORMS

Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks

What Does It Mean to Be a Transformer? Insights from a Theoretical Hessian Analysis

Can Reinforcement Learning Solve Asymmetric Combinatorial-Continuous Zero-Sum Games?

Beyond Linear Approximations: A Novel Pruning Approach for Attention Matrix

Standardizing Structural Causal Models

Capturing the Temporal Dependence of Training Data Influence

Reinforcement learning with combinatorial actions for coupled restless bandits

Diffusion Bridge AutoEncoders for Unsupervised Representation Learning

CL-MFAP: A Contrastive Learning-Based Multimodal Foundation Model for Molecular Property Prediction and Antibiotic Screening

Perm: A Parametric Representation for Multi-Style 3D Hair Modeling

Reading Your Heart: Learning ECG Words and Sentences via Pre-training ECG Language Model

Accelerating Goal-Conditioned Reinforcement Learning Algorithms and Research

A Decade's Battle on Dataset Bias: Are We There Yet?

An Effective Theory of Bias Amplification

Warm Diffusion: Recipe for Blur-Noise Mixture Diffusion Models

BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval

Reconciling Model Multiplicity for Downstream Decision Making

Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning

ChroKnowledge: Unveiling Chronological Knowledge of Language Models in Multiple Domains

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words

Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models

Calibrating Expressions of Certainty

Almost Optimal Batch-Regret Tradeoff for Batch Linear Contextual Bandits

Convergent Privacy Loss of Noisy-SGD without Convexity and Smoothness

GLOMA: Global Video Text Spotting with Morphological Association

Denoising as Adaptation: Noise-Space Domain Adaptation for Image Restoration

MR-GSM8K: A Meta-Reasoning Benchmark for Large Language Model Evaluation

CEB: Compositional Evaluation Benchmark for Fairness in Large Language Models

Explanations of GNN on Evolving Graphs via Axiomatic Layer edges

ARB-LLM: Alternating Refined Binarizations for Large Language Models

Unlocking Efficient, Scalable, and Continual Knowledge Editing with Basis-Level Representation Fine-Tuning

Advantage-Guided Distillation for Preference Alignment in Small Language Models

Dynamic Modeling of Patients, Modalities and Tasks via Multi-modal Multi-task Mixture of Experts

Shot2Story: A New Benchmark for Comprehensive Understanding of Multi-shot Videos

Limits of Deep Learning: Sequence Modeling through the Lens of Complexity Theory

Fragment and Geometry Aware Tokenization of Molecules for Structure-Based Drug Design Using Language Models

ASTrA: Adversarial Self-supervised Training with Adaptive-Attacks

MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods

Cross-Attention Head Position Patterns Can Align with Human Visual Concepts in Text-to-Image Generative Models

OSTQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting

GOttack: Universal Adversarial Attacks on Graph Neural Networks via Graph Orbits Learning

Misspecified $Q$-Learning with Sparse Linear Function Approximation: Tight Bounds on Approximation Error

MrSteve: Instruction-Following Agents in Minecraft with What-Where-When Memory

Regret-Optimal List Replicable Bandit Learning: Matching Upper and Lower Bounds

Efficient Imitation under Misspecification

Enhancing Robust Fairness via Confusional Spectral Regularization

Mini-Monkey: Alleviating the Semantic Sawtooth Effect for Lightweight MLLMs via Complementary Image Pyramid

ThermalGaussian: Thermal 3D Gaussian Splatting

FreeCG: Free the Design Space of Clebsch-Gordan Transform for Machine Learning Force Fields

From Layers to States: A State Space Model Perspective to Deep Neural Network Layer Dynamics

From Risk to Uncertainty: Generating Predictive Uncertainty Measures via Bayesian Estimation

Enhancing the Scalability and Applicability of Kohn-Sham Hamiltonians for Molecular Systems

Computationally Efficient RL under Linear Bellman Completeness for Deterministic Dynamics

Optimization with Access to Auxiliary Information

Bandit Learning in Matching Markets with Indifference

Grounding Video Models to Actions through Goal Conditioned Exploration

Proteina: Scaling Flow-based Protein Structure Generative Models

On Speeding Up Language Model Evaluation

You Only Sample Once: Taming One-Step Text-to-Image Synthesis by Self-Cooperative Diffusion GANs

Trajectory-LLM: A Language-based Data Generator for Trajectory Prediction in Autonomous Driving

FairMT-Bench: Benchmarking Fairness for Multi-turn Dialogue in Conversational LLMs

SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints

PAD: Personalized Alignment of LLMs at Decoding-time

Federated $Q$-Learning with Reference-Advantage Decomposition: Almost Optimal Regret and Logarithmic Communication Cost

PaCA: Partial Connection Adaptation for Efficient Fine-Tuning

Gap-Dependent Bounds for Q-Learning using Reference-Advantage Decomposition

What Matters in Learning from Large-Scale Datasets for Robot Manipulation

Accurate and Scalable Graph Neural Networks via Message Invariance

Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural Collapse

Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning

ECHOPulse: ECG Controlled Echocardio-gram Video Generation

Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness

Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression

PuzzleFusion++: Auto-agglomerative 3D Fracture Assembly by Denoise and Verify

MEGA-Bench: Scaling Multimodal Evaluation to over 500 Real-World Tasks

SparsyFed: Sparse Adaptive Federated Learning

CG-Bench: Clue-grounded Question Answering Benchmark for Long Video Understanding

Bootstrapping Language-Guided Navigation Learning with Self-Refining Data Flywheel

Instruct-SkillMix: A Powerful Pipeline for LLM Instruction Tuning

Robust-PIFu: Robust Pixel-aligned Implicit Function for 3D Human Digitalization from a Single Image

Exact Computation of Any-Order Shapley Interactions for Graph Neural Networks

Probe Pruning: Accelerating LLMs through Dynamic Pruning via Model-Probing

Discrete Distribution Networks

The Unreasonable Ineffectiveness of the Deeper Layers

Divergence-enhanced Knowledge-guided Context Optimization for Visual-Language Prompt Tuning

Physics-Informed Diffusion Models

Adaptive Methods through the Lens of SDEs: Theoretical Insights on the Role of Noise

Functional Homotopy: Smoothing Discrete Optimization via Continuous Parameters for LLM Jailbreak Attacks

Predictive Uncertainty Quantification for Bird's Eye View Segmentation: A Benchmark and Novel Loss Function

Adapt-$\infty$: Scalable Continual Multimodal Instruction Tuning via Dynamic Data Selection

econSG: Efficient and Multi-view Consistent Open-Vocabulary 3D Semantic Gaussians

OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text

RaSA: Rank-Sharing Low-Rank Adaptation

MLPs Learn In-Context on Regression and Classification Tasks

Re-Evaluating the Impact of Unseen-Class Unlabeled Data on Semi-Supervised Learning Model

GOAL: A Generalist Combinatorial Optimization Agent Learner

Do Vision & Language Decoders use Images and Text equally? How Self-consistent are their Explanations?

Towards Federated RLHF with Aggregated Client Preference for LLMs

Weak-to-Strong Preference Optimization: Stealing Reward from Weak Aligned Model

Do Large Language Models Truly Understand Geometric Structures?

FreqPrior: Improving Video Diffusion Models with Frequency Filtering Gaussian Noise

Endowing Visual Reprogramming with Adversarial Robustness

ORSO: Accelerating Reward Design via Online Reward Selection and Policy Optimization

On the Crucial Role of Initialization for Matrix Factorization

Activation Gradient based Poisoned Sample Detection Against Backdoor Attacks

Grid Cell-Inspired Fragmentation and Recall for Efficient Map Building

Be More Diverse than the Most Diverse: Optimal Mixtures of Generative Models via Mixture-UCB Bandit Algorithms

ReGen: Generative Robot Simulation via Inverse Design

Self-Supervised Diffusion MRI Denoising via Iterative and Stable Refinement

How Learnable Grids Recover Fine Detail in Low Dimensions: A Neural Tangent Kernel Analysis of Multigrid Parametric Encodings

RobuRCDet: Enhancing Robustness of Radar-Camera Fusion in Bird's Eye View for 3D Object Detection

Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution

AvatarGO: Zero-shot 4D Human-Object Interaction Generation and Animation

DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenes

FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality

DGQ: Distribution-Aware Group Quantization for Text-to-Image Diffusion Models

Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset

InverseBench: Benchmarking Plug-and-Play Diffusion Priors for Inverse Problems in Physical Sciences

Lightweight Predictive 3D Gaussian Splats

IgGM: A Generative Model for Functional Antibody and Nanobody Design

Federated Granger Causality Learning For Interdependent Clients With State Space Representation

MambaPEFT: Exploring Parameter-Efficient Fine-Tuning for Mamba

No Need to Talk: Asynchronous Mixture of Language Models

BingoGuard: LLM Content Moderation Tools with Risk Levels

HyPoGen: Optimization-Biased Hypernetworks for Generalizable Policy Generation

Learning Gain Map for Inverse Tone Mapping

Causal Graph Transformer for Treatment Effect Estimation Under Unknown Interference

Does SGD really happen in tiny subspaces?

The Superposition of Diffusion Models Using the Itô Density Estimator

CBQ: Cross-Block Quantization for Large Language Models

Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMs

Weak-to-Strong Generalization Through the Data-Centric Lens

Magnetic Preference Optimization: Achieving Last-iterate Convergence for Language Model Alignment

Implicit In-context Learning

Understanding the Stability-based Generalization of Personalized Federated Learning

Data-centric Prediction Explanation via Kernelized Stein Discrepancy

GenVP: Generating Visual Puzzles with Contrastive Hierarchical VAEs

MotionDreamer: One-to-Many Motion Synthesis with Localized Generative Masked Transformer

Standard Gaussian Process is All You Need for High-Dimensional Bayesian Optimization

Scaling Speech-Text Pre-training with Synthetic Interleaved Data

Global Convergence of Policy Gradient in Average Reward MDPs

Learning-Augmented Frequent Directions

VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents

SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistency

Pareto Low-Rank Adapters: Efficient Multi-Task Learning with Preferences

MA-RLHF: Reinforcement Learning from Human Feedback with Macro Actions

Decoupling Layout from Glyph in Online Chinese Handwriting Generation

Structuring Benchmark into Knowledge Graphs to Assist Large Language Models in Retrieving and Designing Models

A Quantum Circuit-Based Compression Perspective for Parameter-Efficient Learning

Causal Information Prioritization for Efficient Reinforcement Learning

SRSA: Skill Retrieval and Adaptation for Robotic Assembly Tasks

Robotouille: An Asynchronous Planning Benchmark for LLM Agents

Learning local equivariant representations for quantum operators

Towards Auto-Regressive Next-Token Prediction: In-context Learning Emerges from Generalization

TTVD: Towards a Geometric Framework for Test-Time Adaptation Based on Voronoi Diagram

Towards Empowerment Gain through Causal Structure Learning in Model-Based Reinforcement Learning

LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging

Accelerating Training with Neuron Interaction and Nowcasting Networks

Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusion

SiReRAG: Indexing Similar and Related Information for Multihop Reasoning

DynaPrompt: Dynamic Test-Time Prompt Tuning

MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models

GS-LiDAR: Generating Realistic LiDAR Point Clouds with Panoramic Gaussian Splatting

Forgetting Transformer: Softmax Attention with a Forget Gate

SAM-CP: Marrying SAM with Composable Prompts for Versatile Segmentation

Geometry Image Diffusion: Fast and Data-Efficient Text-to-3D with Image-Based Surface Representation

Test-time Alignment of Diffusion Models without Reward Over-optimization

Lightning-Fast Image Inversion and Editing for Text-to-Image Diffusion Models

Adaptive Retention & Correction: Test-Time Training for Continual Learning

Efficient Model-Based Reinforcement Learning Through Optimistic Thompson Sampling

ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability

Rethinking Audio-Visual Adversarial Vulnerability from Temporal and Modality Perspectives

Preference Optimization for Reasoning with Pseudo Feedback

Theory on Mixture-of-Experts in Continual Learning

Self-Boosting Large Language Models with Synthetic Preference Data

STAFF: Speculative Coreset Selection for Task-Specific Fine-tuning

Adversarial Policy Optimization for Offline Preference-based Reinforcement Learning

Dynamic Assortment Selection and Pricing with Censored Preference Feedback

IntersectionZoo: Eco-driving for Benchmarking Multi-Agent Contextual Reinforcement Learning

High-dimension Prototype is a Better Incremental Object Detection Learner

Diverse Preference Learning for Capabilities and Alignment

Topological Blindspots: Understanding and Extending Topological Deep Learning Through the Lens of Expressivity

Language Representations Can be What Recommenders Need: Findings and Potentials

Causal Effect Estimation with Mixed Latent Confounders and Post-treatment Variables

Fast and Accurate Blind Flexible Docking

3D-MolT5: Leveraging Discrete Structural Information for Molecule-Text Modeling

A Simple yet Effective $\Delta\Delta G$ Predictor is An Unsupervised Antibody Optimizer and Explainer

Efficient Source-Free Time-Series Adaptation via Parameter Subspace Disentanglement

Reconstructive Visual Instruction Tuning

Cafe-Talk: Generating 3D Talking Face Animation with Multimodal Coarse- and Fine-grained Control

Sequential Stochastic Combinatorial Optimization Using Hierarchal Reinforcement Learning

Optimizing Neural Network Representations of Boolean Networks

ExACT: Teaching AI Agents to Explore with Reflective-MCTS and Exploratory Learning

CBGBench: Fill in the Blank of Protein-Molecule Complex Binding Graph

Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models

$R^2$-Guard: Robust Reasoning Enabled LLM Guardrail via Knowledge-Enhanced Logical Reasoning

AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Models

Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse

On the Convergence of Adaptive Gradient Methods for Nonconvex Optimization

Time After Time: Deep-Q Effect Estimation for Interventions on When and What to do

Can Neural Networks Achieve Optimal Computational-statistical Tradeoff? An Analysis on Single-Index Model

Learning Regularized Graphon Mean-Field Games with Unknown Graphons

Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation

Online Preference Alignment for Language Models via Count-based Exploration

Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization

SPORTU: A Comprehensive Sports Understanding Benchmark for Multimodal Large Language Models

Can Video LLMs Refuse to Answer? Alignment for Answerability in Video Large Language Models

BrainUICL: An Unsupervised Individual Continual Learning Framework for EEG Applications

Pursuing Better Decision Boundaries for Long-Tailed Object Detection via Category Information Amount

Mixture of Experts Made Personalized: Federated Prompt Learning for Vision-Language Models

Valid Conformal Prediction for Dynamic GNNs

TestGenEval: A Real World Unit Test Generation and Test Completion Benchmark

LR0.FM: LOW-RESOLUTION ZERO-SHOT CLASSIFICATION BENCHMARK FOR FOUNDATION MODELS

CBraMod: A Criss-Cross Brain Foundation Model for EEG Decoding

Robust Simulation-Based Inference under Missing Data via Neural Processes

NoVo: Norm Voting off Hallucinations with Attention Heads in Large Language Models

Temporal Difference Learning: Why It Can Be Fast and How It Will Be Faster

High-quality Text-to-3D Character Generation with SparseCubes and Sparse Transformers.

E(3)-equivariant models cannot learn chirality: Field-based molecular generation

ToolDial: Multi-turn Dialogue Generation Method for Tool-Augmented Language Models

Deriving Causal Order from Single-Variable Interventions: Guarantees & Algorithm

Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation

VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks

Revisiting Zeroth-Order Optimization: Minimum-Variance Two-Point Estimators and Directionally Aligned Perturbations

Ensembling Diffusion Models via Adaptive Feature Aggregation

Scalable Bayesian Learning with posteriors

EVA: Geometric Inverse Design for Fast Protein Motif-Scaffolding with Coupled Flow

Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents

Point-SAM: Promptable 3D Segmentation Model for Point Clouds

Sharper Guarantees for Learning Neural Network Classifiers with Gradient Methods

TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models

SoftMatcha: A Soft and Fast Pattern Matcher for Billion-Scale Corpus Searches

LICORICE: Label-Efficient Concept-Based Interpretable Reinforcement Learning

Depth Pro: Sharp Monocular Metric Depth in Less Than a Second

Cross-Modal Safety Mechanism Transfer in Large Vision-Language Models

Video-STaR: Self-Training Enables Video Instruction Tuning with Any Supervision

COFlowNet: Conservative Constraints on Flows Enable High-Quality Candidate Generation

Training-free Camera Control for Video Generation

LongMamba: Enhancing Mamba's Long-Context Capabilities via Training-Free Receptive Field Enlargement

Learning Neural Networks with Distribution Shift: Efficiently Certifiable Guarantees

Adaptive backtracking for faster optimization

CodePlan: Unlocking Reasoning Potential in Large Language Models by Scaling Code-form Planning

Accelerated training through iterative gradient propagation along the residual path

Continuous Exposure Learning for Low-light Image Enhancement using Neural ODEs

JetFormer: An autoregressive generative model of raw images and text

Boosting Perturbed Gradient Ascent for Last-Iterate Convergence in Games

AdaRankGrad: Adaptive Gradient Rank and Moments for Memory-Efficient LLMs Training and Fine-Tuning

Towards a Theoretical Understanding of Synthetic Data in LLM Post-Training: A Reverse-Bottleneck Perspective

Vec2Face: Scaling Face Dataset Generation with Loosely Constrained Vectors

Lumina-T2X: Scalable Flow-based Large Diffusion Transformer for Flexible Resolution Generation

Adjoint Matching: Fine-tuning Flow and Diffusion Generative Models with Memoryless Stochastic Optimal Control

REVISITING MULTI-PERMUTATION EQUIVARIANCE THROUGH THE LENS OF IRREDUCIBLE REPRESENTATIONS

Targeted Attack Improves Protection against Unauthorized Diffusion Customization

Quest: Query-centric Data Synthesis Approach for Long-context Scaling of Large Language Model

On the Expressive Power of Sparse Geometric MPNNs

Radar: Fast Long-Context Decoding for Any Transformer

Credal Wrapper of Model Averaging for Uncertainty Estimation in Classification

An Asynchronous Bundle Method for Distributed Learning Problems

Learning the Optimal Stopping for Early Classification within Finite Horizons via Sequential Probability Ratio Test

Geometric Inductive Biases of Deep Networks: The Role of Data and Architecture

MIND over Body: Adaptive Thinking using Dynamic Computation

Interleaved Scene Graphs for Interleaved Text-and-Image Generation Assessment

Random-Set Neural Networks

Active Learning for Continual Learning: Keeping the Past Alive in the Present

DUALFormer: Dual Graph Transformer

Steering Large Language Models between Code Execution and Textual Reasoning

Arithmetic Transformers Can Length-Generalize in Both Operand Length and Count

Breaking Free from MMI: A New Frontier in Rationalization by Probing Input Utilization

Convergence and Implicit Bias of Gradient Descent on Continual Linear Classification

3D-Properties: Identifying Challenges in DPO and Charting a Path Forward

Leave-One-Out Stable Conformal Prediction

DeepGate4: Efficient and Effective Representation Learning for Circuit Design at Scale

GotenNet: Rethinking Efficient 3D Equivariant Graph Neural Networks

Visually Guided Decoding: Gradient-Free Hard Prompt Inversion with Language Models

Tight Time Complexities in Parallel Stochastic Optimization with Arbitrary Computation Dynamics

Swift4D: Adaptive divide-and-conquer Gaussian Splatting for compact and efficient reconstruction of dynamic scene

PortLLM: Personalizing Evolving Large Language Models with Training-Free and Portable Model Patches

Provable Benefit of Annealed Langevin Monte Carlo for Non-log-concave Sampling

SeedLM: Compressing LLM Weights into Seeds of Pseudo-Random Generators

Knowledge Distillation with Multi-granularity Mixture of Priors for Image Super-Resolution

Control-oriented Clustering of Visual Latent Representation

Implicit Search via Discrete Diffusion: A Study on Chess

Ensembles of Low-Rank Expert Adapters

Interactive Speculative Planning: Enhance Agent Efficiency through Co-design of System and User Interface

OS-ATLAS: Foundation Action Model for Generalist GUI Agents

MMSearch: Unveiling the Potential of Large Models as Multi-modal Search Engines

Token Statistics Transformer: Linear-Time Attention via Variational Rate Reduction

RFWave: Multi-band Rectified Flow for Audio Waveform Reconstruction

Apollo-MILP: An Alternating Prediction-Correction Neural Solving Framework for Mixed-Integer Linear Programming

PerturboLLaVA: Reducing Multimodal Hallucinations with Perturbative Visual Training

Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances

VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation

HART: Efficient Visual Generation with Hybrid Autoregressive Transformer

SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training

Classic but Everlasting: Traditional Gradient-Based Algorithms Converge Fast Even in Time-Varying Multi-Player Games

I Can Hear You: Selective Robust Training for Deepfake Audio Detection

(Mis)Fitting Scaling Laws: A Survey of Scaling Law Fitting Techniques in Deep Learning

Generating CAD Code with Vision-Language Models for 3D Designs

An Optimal Discriminator Weighted Imitation Perspective for Reinforcement Learning

A-Bench: Are LMMs Masters at Evaluating AI-generated Images?

Null Counterfactual Factor Interactions for Goal-Conditioned Reinforcement Learning

Generating Physical Dynamics under Priors

Matryoshka Multimodal Models

TDDBench: A Benchmark for Training data detection

GPS: A Probabilistic Distributional Similarity with Gumbel Priors for Set-to-Set Matching

RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph

BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions

$\text{I}^2\text{AM}$: Interpreting Image-to-Image Latent Diffusion Models via Bi-Attribution Maps

Monet: Mixture of Monosemantic Experts for Transformers

Refine-by-Align: Reference-Guided Artifacts Refinement through Semantic Alignment

Aligned Datasets Improve Detection of Latent Diffusion-Generated Images

Group-robust Sample Reweighting for Subpopulation Shifts via Influence Functions

MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?

xFinder: Large Language Models as Automated Evaluators for Reliable Evaluation

CirT: Global Subseasonal-to-Seasonal Forecasting with Geometry-inspired Transformer

SimXRD-4M: Big Simulated X-ray Diffraction Data and Crystal Symmetry Classification Benchmark

MuPT: A Generative Symbolic Music Pretrained Transformer

Shapley-Guided Utility Learning for Effective Graph Inference Data Valuation

A Solvable Attention for Neural Scaling Laws

DyCAST: Learning Dynamic Causal Structure from Time Series

CrossMPT: Cross-attention Message-passing Transformer for Error Correcting Codes

6DGS: Enhanced Direction-Aware Gaussian Splatting for Volumetric Rendering

3D Vision-Language Gaussian Splatting

Order-aware Interactive Segmentation

New Algorithms for the Learning-Augmented k-means Problem

Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG

RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards

Discovering Temporally Compositional Neural Manifolds with Switching Infinite GPFA

ZIP: An Efficient Zeroth-order Prompt Tuning for Black-box Vision-Language Models

Unlearning-based Neural Interpretations

Bridging Information Asymmetry in Text-video Retrieval: A Data-centric Approach

NovelQA: Benchmarking Question Answering on Documents Exceeding 200K Tokens

A Truncated Newton Method for Optimal Transport

MamBEV: Enabling State Space Models to Learn Birds-Eye-View Representations

Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late In Training

Do Deep Neural Network Solutions Form a Star Domain?

On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent

Personalized Representation from Personalized Generation

Beyond Circuit Connections: A Non-Message Passing Graph Transformer Approach for Quantum Error Mitigation

Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Models

ToolACE: Winning the Points of LLM Function Calling

Differentially private optimization for non-decomposable objective functions

Multi-Robot Motion Planning with Diffusion Models

Beyond Graphs: Can Large Language Models Comprehend Hypergraphs?

ImDy: Human Inverse Dynamics from Imitated Observations

HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models

ReMatching Dynamic Reconstruction Flow

Feature Averaging: An Implicit Bias of Gradient Descent Leading to Non-Robustness in Neural Networks

Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstraction

HOPE for a Robust Parameterization of Long-memory State Space Models

CFD: Learning Generalized Molecular Representation via Concept-Enhanced Feedback Disentanglement

Analysis of Linear Mode Connectivity via Permutation-Based Weight Matching: With Insights into Other Permutation Search Methods

Scalable Benchmarking and Robust Learning for Noise-Free Ego-Motion and 3D Reconstruction from Noisy Video

DoF: A Diffusion Factorization Framework for Offline Multi-Agent Reinforcement Learning

THE ROBUSTNESS OF DIFFERENTIABLE CAUSAL DISCOVERY IN MISSPECIFIED SCENARIOS

VL-ICL Bench: The Devil in the Details of Multimodal In-Context Learning

MIND: Math Informed syNthetic Dialogues for Pretraining LLMs

Building Math Agents with Multi-Turn Iterative Preference Learning

Towards Robust Multimodal Open-set Test-time Adaptation via Adaptive Entropy-aware Optimization

Local Loss Optimization in the Infinite Width: Stable Parameterization of Predictive Coding Networks and Target Propagation

Provable Convergence and Limitations of Geometric Tempering for Langevin Dynamics

ShEPhERD: Diffusing shape, electrostatics, and pharmacophores for bioisosteric drug design

Simplifying Deep Temporal Difference Learning

From Search to Sampling: Generative Models for Robust Algorithmic Recourse

Hot-pluggable Federated Learning: Bridging General and Personalized FL via Dynamic Selection

Machine Unlearning via Simulated Oracle Matching

What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?

Linear Partial Gromov-Wasserstein Embedding

Mitigate the Gap: Improving Cross-Modal Alignment in CLIP

Horizon Generalization in Reinforcement Learning

Robust Function-Calling for On-Device Language Model via Function Masking

Improved Sampling Of Diffusion Models In Fluid Dynamics With Tweedie's Formula

Temporal Flexibility in Spiking Neural Networks: Towards Generalization Across Time Steps and Deployment Friendliness

SeCom: On Memory Construction and Retrieval for Personalized Conversational Agents

Determine-Then-Ensemble: Necessity of Top-k Union for Large Language Model Ensembling

Finding Shared Decodable Concepts and their Negations in the Brain

State Space Model Meets Transformer: A New Paradigm for 3D Object Detection

Scaling Optimal LR Across Token Horizons

A Probabilistic Perspective on Unlearning and Alignment for Large Language Models

Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecasting

A primer on analytical learning dynamics of nonlinear neural networks

Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequences

Enhancing Clustered Federated Learning: Integration of Strategies and Improved Methodologies

KiVA: Kid-inspired Visual Analogies for Testing Large Multimodal Models

Can LLMs Understand Time Series Anomalies?

TRACE: Temporal Grounding Video LLM via Causal Event Modeling

Timer-XL: Long-Context Transformers for Unified Time Series Forecasting

ClimaQA: An Automated Evaluation Framework for Climate Question Answering Models

Neural Fluid Simulation on Geometric Surfaces

Recovering Manifold Structure Using Ollivier Ricci Curvature

Investigating the Pre-Training Dynamics of In-Context Learning: Task Recognition vs. Task Learning

Towards Self-Supervised Covariance Estimation in Deep Heteroscedastic Regression

The Complexity of Two-Team Polymatrix Games with Independent Adversaries

EgoSim: Egocentric Exploration in Virtual Worlds with Multi-modal Conditioning

PWM: Policy Learning with Multi-Task World Models

MRAG-Bench: Vision-Centric Evaluation for Retrieval-Augmented Multimodal Models

Distilling Reinforcement Learning Algorithms for In-Context Model-Based Planning

Breaking the $\log(1/\Delta_2)$ Barrier: Better Batched Best Arm Identification with Adaptive Grids

Learning from Imperfect Human Feedback: A Tale from Corruption-Robust Dueling

On the Expressiveness of Rational ReLU Neural Networks With Bounded Depth

Transformer Learns Optimal Variable Selection in Group-Sparse Classification

Graph Neural Networks Gone Hogwild

Adaptive $Q$-Network: On-the-fly Target Selection for Deep Reinforcement Learning

Swing-by Dynamics in Concept Learning and Compositional Generalization

Single-agent Poisoning Attacks Suffice to Ruin Multi-Agent Learning

Do Contemporary Causal Inference Models Capture Real-World Heterogeneity? Findings from a Large-Scale Benchmark

A Differentiable Rank-Based Objective for Better Feature Learning

Mixture of In-Context Prompters for Tabular PFNs

Learning Long Range Dependencies on Graphs via Random Walks

Point-based Instance Completion with Scene Constraints

Geometry-Aware Approaches for Balancing Performance and Theoretical Guarantees in Linear Bandits

Graph Neural Networks Can (Often) Count Substructures

ICLR: In-Context Learning of Representations

Optimized Multi-Token Joint Decoding With Auxiliary Model for LLM Inference

MAGNet: Motif-Agnostic Generation of Molecules from Scaffolds

Spectral Compressive Imaging via Unmixing-driven Subspace Diffusion Refinement

How to Probe: Simple Yet Effective Techniques for Improving Post-hoc Explanations

As large as it gets – Studying Infinitely Large Convolutions via Neural Implicit Frequency Filters

Tracking the Copyright of Large Vision-Language Models through Parameter Learning Adversarial Images

Towards Scalable Exact Machine Unlearning Using Parameter-Efficient Fine-Tuning

Near, far: Patch-ordering enhances vision foundation models' scene understanding

Unifying Causal Representation Learning with the Invariance Principle

Scalable Mechanistic Neural Networks

Deep Signature: Characterization of Large-Scale Molecular Dynamics

Distributional Associations vs In-Context Reasoning: A Study of Feed-forward and Attention Layers

Quality over Quantity in Attention Layers: When Adding More Heads Hurts

PICASO: Permutation-Invariant Context Composition with State Space Models

InstaSHAP: Interpretable Additive Models Explain Shapley Values Instantly

A Large-scale Dataset and Benchmark for Commuting Origin-Destination Flow Generation

VEDIT: Latent Prediction Architecture For Procedural Video Representation Learning

A Multiscale Frequency Domain Causal Framework for Enhanced Pathological Analysis

Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Sampling

Training-Free Activation Sparsity in Large Language Models

Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement

LLMs' Potential Influences on Our Democracy: Challenges and Opportunities

DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Life

Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing

Active Learning for Neural PDE Solvers

Utilitarian Algorithm Configuration for Infinite Parameter Spaces

WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild

Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

X-Fi: A Modality-Invariant Foundation Model for Multimodal Human Sensing

Durable Quantization Conditioned Misalignment Attack on Large Language Models

Beyond Sequence: Impact of Geometric Context for RNA Property Prediction

LLaRA: Supercharging Robot Learning Data for Vision-Language Policy

Epistemic Monte Carlo Tree Search

Advantage Alignment Algorithms

Solving hidden monotone variational inequalities with surrogate losses

HELMET: How to Evaluate Long-context Models Effectively and Thoroughly

Universal Sharpness Dynamics in Neural Network Training: Fixed Point Analysis, Edge of Stability, and Route to Chaos

Diffusion-based Neural Network Weights Generation

Fitting Networks with a Cancellation Trick

Learning Diverse Attacks on Large Language Models for Robust Red-Teaming and Safety Tuning

Poisson-Dirac Neural Networks for Modeling Coupled Dynamical Systems across Domains

AssembleFlow: Rigid Flow Matching with Inertial Frames for Molecular Assembly

Sparse Autoencoders Do Not Find Canonical Units of Analysis

Selective Unlearning via Representation Erasure Using Domain Adversarial Training

Don't flatten, tokenize! Unlocking the key to SoftMoE's efficacy in deep RL

Dynamic Low-Rank Sparse Adaptation for Large Language Models

Learning a Fast Mixing Exogenous Block MDP using a Single Trajectory

Conflict-Averse Gradient Aggregation for Constrained Multi-Objective Reinforcement Learning

CAKE: Cascading and Adaptive KV Cache Eviction with Layer Preferences

Re-Thinking Inverse Graphics With Large Language Models

Rethinking Self-Distillation: Label Averaging and Enhanced Soft Label Refinement with Partial Labels

Identifiability for Gaussian Processes with Holomorphic Kernels

Neural Dueling Bandits: Preference-Based Optimization with Human Feedback

Residual Deep Gaussian Processes on Manifolds

HADAMRNN: BINARY AND SPARSE TERNARY ORTHOGONAL RNNS

U-Nets as Belief Propagation: Efficient Classification, Denoising, and Diffusion in Generative Hierarchical Models

Probabilistic Language-Image Pre-Training

$\phi$-Update: A Class of Policy Update Methods with Policy Convergence Guarantee

NetFormer: An interpretable model for recovering dynamical connectivity in neuronal population dynamics

PaPaGei: Open Foundation Models for Optical Physiological Signals

Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization

Towards Improving Exploration through Sibling Augmented GFlowNets

PianoMotion10M: Dataset and Benchmark for Hand Motion Generation in Piano Performance

On the Transfer of Object-Centric Representation Learning

Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic Learning

Structure Language Models for Protein Conformation Generation

Meta Flow Matching: Integrating Vector Fields on the Wasserstein Manifold

How efficient is LLM-generated code? A rigorous & high-standard benchmark

Bootstrapping Language Models with DPO Implicit Rewards

Hessian Free Efficient Single Loop Iterative Differentiation Methods for Bi-Level Optimization Problems

Mix-CPT: A Domain Adaptation Framework via Decoupling Knowledge Learning and Format Alignment

Is Your Video Language Model a Reliable Judge?

A Riemannian Framework for Learning Reduced-order Lagrangian Dynamics

Commit0: Library Generation from Scratch

CraftRTL: High-quality Synthetic Data Generation for Verilog Code Models with Correct-by-Construction Non-Textual Representations and Targeted Code Repair

Latent Bayesian Optimization via Autoregressive Normalizing Flows

Locality Sensitive Avatars From Video

Conditional Diffusion with Ordinal Regression: Longitudinal Data Generation for Neurodegenerative Disease Studies

Action abstractions for amortized sampling

Adaptive teachers for amortized samplers

Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures

U-shaped and Inverted-U Scaling behind Emergent Abilities of Large Language Models

Is uniform expressivity too restrictive? Towards efficient expressivity of GNNs

Tuning Frequency Bias of State Space Models

Denoising Task Difficulty-based Curriculum for Training Diffusion Models

Interpreting the Second-Order Effects of Neurons in CLIP

Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations

Selective Attention Improves Transformer

Locally Connected Echo State Networks for Time Series Forecasting

Knowledge Entropy Decay during Language Model Pretraining Hinders New Knowledge Acquisition

Range, not Independence, Drives Modularity in Biologically Inspired Representations

HexGen-2: Disaggregated Generative Inference of LLMs in Heterogeneous Environment

Stabilized Neural Prediction of Potential Outcomes in Continuous Time

Model-agnostic meta-learners for estimating heterogeneous treatment effects over time

Feature Responsiveness Scores: Model-Agnostic Explanations for Recourse

Signature Kernel Conditional Independence Tests in Causal Discovery for Stochastic Processes

Interpretable Causal Representation Learning for Biological Data in the Pathway Space

Probabilistic Geometric Principal Component Analysis with application to neural data

Data Scaling Laws in Imitation Learning for Robotic Manipulation

TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio Motion Embedding and Diffusion Interpolation

Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?

DAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking head Video Generation

MCNC: Manifold-Constrained Reparameterization for Neural Compression

Robust Conformal Prediction with a Single Binary Certificate

Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning

RA-TTA: Retrieval-Augmented Test-Time Adaptation for Vision-Language Models

Adaptive Rank Allocation: Speeding Up Modern Transformers with RaNA Adapters

Prevalence of Negative Transfer in Continual Reinforcement Learning: Analyses and a Simple Baseline

SPDIM: Source-Free Unsupervised Conditional and Label Shift Adaptation in EEG

Maximizing the Potential of Synthetic Data: Insights from Random Matrix Theory

Clique Number Estimation via Differentiable Functions of Adjacency Matrix Permutations

UniDetox: Universal Detoxification of Large Language Models via Dataset Distillation

Charting the Design Space of Neural Graph Representations for Subgraph Matching

SyllableLM: Learning Coarse Semantic Units for Speech Language Models

Isometric Regularization for Manifolds of Functional Data

A Deep Generative Learning Approach for Two-stage Adaptive Robust Optimization

Budgeted Online Continual Learning by Adaptive Layer Freezing and Frequency-based Sampling

Decomposition Polyhedra of Piecewise Linear Functions

REGENT: A Retrieval-Augmented Generalist Agent That Can Act In-Context in New Environments

Understanding Virtual Nodes: Oversquashing and Node Heterogeneity

Language Guided Skill Discovery

Privacy-Aware Lifelong Learning

Model-based Offline Reinforcement Learning with Lower Expectile Q-Learning

Approximation algorithms for combinatorial optimization with predictions

Transformers Learn Low Sensitivity Functions: Investigations and Implications

Visually Consistent Hierarchical Image Classification

TSC-Net: Prediction of Pedestrian Trajectories by Trajectory-Scene-Cell Classification

SIM: Surface-based fMRI Analysis for Inter-Subject Multimodal Decoding from Movie-Watching Experiments

Balanced Ranking with Relative Centrality: A multi-core periphery perspective

Fréchet Wavelet Distance: A Domain-Agnostic Metric for Image Generation

Test-time Adaptation for Image Compression with Distribution Regularization

Learning Mask Invariant Mutual Information for Masked Image Modeling

Last Iterate Convergence of Incremental Methods as a Model of Forgetting

Parameter Expanded Stochastic Gradient Markov Chain Monte Carlo

The Utility and Complexity of In- and Out-of-Distribution Machine Unlearning

Looking Backward: Retrospective Backward Synthesis for Goal-Conditioned GFlowNets

Adaptive Gradient Clipping for Robust Federated Learning

Neuroplastic Expansion in Deep Reinforcement Learning

Learning to Plan Before Answering: Self-Teaching LLMs to Learn Abstract Plans for Problem Solving

Improved Regret Bounds for Linear Adversarial MDPs via Linear Optimization

Zero-shot Model-based Reinforcement Learning using Large Language Models

Sufficient Context: A New Lens on Retrieval Augmented Generation Systems

A Large-Scale 3D Face Mesh Video Dataset via Neural Re-parameterized Optimization

Semantic Aware Representation Learning for Lifelong Learning

MrT5: Dynamic Token Merging for Efficient Byte-level Language Models

Min-K%++: Improved Baseline for Pre-Training Data Detection from Large Language Models

An Effective Manifold-based Optimization Method for Distributionally Robust Classification

MambaExtend: A Training-Free Approach to Improve Long Context Extension of Mamba

Detecting Backdoor Samples in Contrastive Language Image Pretraining

Learning to Solve Differential Equation Constrained Optimization Problems

Mitigating Spurious Correlations in Zero-Shot Multimodal Models

Representational Similarity via Interpretable Visual Concepts

Separation Power of Equivariant Neural Networks

Test-Time Adaptation for Combating Missing Modalities in Egocentric Videos

Bundle Neural Network for message diffusion on graphs

Neural Spacetimes for DAG Representation Learning

Training-Free Message Passing for Learning on Hypergraphs

The Value of Sensory Information to a Robot

Manifolds, Random Matrices and Spectral Gaps: The geometric phases of generative diffusion

QPM: Discrete Optimization for Globally Interpretable Image Classification

SegLLM: Multi-round Reasoning Segmentation with Large Language Models

BrainOOD: Out-of-distribution Generalizable Brain Network Analysis

DebGCD: Debiased Learning with Distribution Guidance for Generalized Category Discovery

Cached Multi-Lora Composition for Multi-Concept Image Generation

Robust Feature Learning for Multi-Index Models in High Dimensions

Improving Graph Neural Networks by Learning Continuous Edge Directions

Edge Prompt Tuning for Graph Neural Networks

T2V-Turbo-v2: Enhancing Video Model Post-Training through Data, Reward, and Conditional Guidance Design

Rethinking Spiking Neural Networks from an Ensemble Learning Perspective

Regret Bounds for Episodic Risk-Sensitive Linear Quadratic Regulator

RefactorBench: Evaluating Stateful Reasoning in Language Agents Through Code

MIA-Bench: Towards Better Instruction Following Evaluation of Multimodal LLMs

metabench - A Sparse Benchmark of Reasoning and Knowledge in Large Language Models

Second-Order Fine-Tuning without Pain for LLMs: A Hessian Informed Zeroth-Order Optimizer

Bootstrapped Model Predictive Control

Understanding Model Calibration - A gentle introduction and visual exploration of calibration and the expected calibration error (ECE)

MotionAura: Generating High-Quality and Motion Consistent Videos using Discrete Diffusion

Learning vector fields of differential equations on manifolds with geometrically constrained operator-valued kernels

Multi-Modal and Multi-Attribute Generation of Single Cells with CFGen

Graph Neural Preconditioners for Iterative Solutions of Sparse Linear Systems

Steering LLMs' Behavior with Concept Activation Vectors

Distribution-Free Data Uncertainty for Neural Network Regression

Revolutionizing EMCCD Denoising through a Novel Physics-Based Learning Framework for Noise Modeling

Temporal Heterogeneous Graph Generation with Privacy, Utility, and Efficiency

Memory Efficient Transformer Adapter for Dense Predictions

Learning Robust Representations with Long-Term Information for Generalization in Visual Reinforcement Learning

MOCA: Self-supervised Representation Learning by Predicting Masked Online Codebook Assignments

Unlocking the Potential of Model Calibration in Federated Learning

Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Models

GraphEval: A Lightweight Graph-Based LLM Framework for Idea Evaluation

DiffPuter: Empowering Diffusion Models for Missing Data Imputation

TabDiff: a Mixed-type Diffusion Model for Tabular Data Generation

Towards Faster Decentralized Stochastic Optimization with Communication Compression

MetaMetrics: Calibrating Metrics for Generation Tasks Using Human Preferences

Holistically Evaluating the Environmental Impact of Creating Language Models

Generating Likely Counterfactuals Using Sum-Product Networks

A Sanity Check for AI-generated Image Detection

Conformalized Survival Analysis for General Right-Censored Data

Sensitivity-Constrained Fourier Neural Operators for Forward and Inverse Problems in Parametric Differential Equations

Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models

See What You Are Told: Visual Attention Sink in Large Multimodal Models

MeToken: Uniform Micro-environment Token Boosts Post-Translational Modification Prediction

The Foundations of Tokenization: Statistical and Computational Concerns

To Code or Not To Code? Exploring Impact of Code in Pre-training

Make Haste Slowly: A Theory of Emergent Structured Mixed Selectivity in Feature Learning ReLU Networks

MathGAP: Out-of-Distribution Evaluation on Problems with Arbitrarily Complex Proofs

POTEC: Off-Policy Contextual Bandits for Large Action Spaces via Policy Decomposition

A General Framework for Off-Policy Learning with Partially-Observed Reward

SeRA: Self-Reviewing and Alignment of LLMs using Implicit Reward Margins

PolyNet: Learning Diverse Solution Strategies for Neural Combinatorial Optimization

Streamlining Prediction in Bayesian Deep Learning

Learning 3D Perception from Others' Predictions

Graph Sparsification via Mixture of Graphs

Rethinking Graph Prompts: Unraveling the Power of Data Manipulation in Graph Neural Networks

Training Language Models to Self-Correct via Reinforcement Learning

Joint Fine-tuning and Conversion of Pretrained Speech and Language Models towards Linear Complexity

Generalization Guarantees for Representation Learning via Data-Dependent Gaussian Mixture Priors

How many samples are needed to train a deep neural network?

Revisiting In-context Learning Inference Circuit in Large Language Models

Neural Wave Equation for Irregularly Sampled Sequence Data

Deep Learning Alternatives Of The Kolmogorov Superposition Theorem

Understanding Long Videos with Multimodal Language Models

Residual Stream Analysis with Multi-Layer SAEs

When Attention Sink Emerges in Language Models: An Empirical View

Protecting against simultaneous data poisoning attacks

Rethinking Reward Modeling in Preference-based Large Language Model Alignment

Rethinking Artistic Copyright Infringements In the Era Of Text-to-Image Generative Models

On Calibration of LLM-based Guard Models for Reliable Content Moderation

Exploiting Hankel-Toeplitz Structures for Fast Computation of Kernel Precision Matrices

MuHBoost: Multi-Label Boosting For Practical Longitudinal Human Behavior Modeling

PETRA: Parallel End-to-end Training with Reversible Architectures

Diffusion On Syntax Trees For Program Synthesis

What Makes a Good Diffusion Planner for Decision Making?

Test-time Adaptation for Regression by Subspace Alignment

Attributing Culture-Conditioned Generations to Pretraining Corpora

X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scale

Semantix: An Energy-guided Sampler for Semantic Style Transfer

LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decoding

ConcreTizer: Model Inversion Attack via Occupancy Classification and Dispersion Control for 3D Point Cloud Restoration

Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond

Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models

No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion Models

Efficient Off-Policy Learning for High-Dimensional Action Spaces

Towards Semantic Equivalence of Tokenization in Multimodal LLM

Searching for Optimal Solutions with LLMs via Bayesian Optimization

RandLoRA: Full rank parameter-efficient fine-tuning of large models

AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models

Precise Parameter Localization for Textual Generation in Diffusion Models

Decoupled Graph Energy-based Model for Node Out-of-Distribution Detection on Heterophilic Graphs

Toward Generalizing Visual Brain Decoding to Unseen Subjects

Debiasing Mini-Batch Quadratics for Applications in Deep Learning

Optimal Protocols for Continual Learning via Statistical Physics and Control Theory

A Theory of Initialisation's Impact on Specialisation

Correlating instruction-tuning (in multimodal models) with vision-language processing (in the brain)

Non-Equilibrium Dynamics of Hybrid Continuous-Discrete Ground-State Sampling

Do as I do (Safely): Mitigating Task-Specific Fine-tuning Risks in Large Language Models

Disentangling 3D Animal Pose Dynamics with Scrubbed Conditional Latent Variables

Towards Interpreting Visual Information Processing in Vision-Language Models

L-WISE: Boosting Human Visual Category Learning Through Model-Based Image Selection and Enhancement

In-context Time Series Predictor

The Loss Landscape of Deep Linear Neural Networks: a Second-order Analysis

Task-Adaptive Pretrained Language Models via Clustered-Importance Sampling

Feedback Favors the Generalization of Neural ODEs

Zero-cost Proxy for Adversarial Robustness Evaluation

Safety Alignment Should be Made More Than Just a Few Tokens Deep

MaestroMotif: Skill Design from Artificial Intelligence Feedback

Optimal Learning of Kernel Logistic Regression for Complex Classification Scenarios

GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models

Privately Counting Partially Ordered Data

CONGO: Compressive Online Gradient Optimization

EIA: ENVIRONMENTAL INJECTION ATTACK ON GENERALIST WEB AGENTS FOR PRIVACY LEAKAGE

Graph Neural Networks for Edge Signals: Orientation Equivariance and Invariance

SAM 2: Segment Anything in Images and Videos

Extreme Risk Mitigation in Reinforcement Learning using Extreme Value Theory

Systems with Switching Causal Relations: A Meta-Causal Perspective

Towards Scalable Topological Regularizers

ToVE: Efficient Vision-Language Learning via Knowledge Transfer from Vision Experts

ChartMoE: Mixture of Diversely Aligned Expert Connector for Chart Understanding

LeanAgent: Lifelong Learning for Formal Theorem Proving

CLOVER: Cross-Layer Orthogonal Vectors Pruning and Fine-Tuning

Enhancing Graph Of Thought: Enhancing Prompts with LLM Rationales and Dynamic Temperature Control

GOFA: A Generative One-For-All Model for Joint Graph Language Modeling

Edge-aware Image Smoothing with Relative Wavelet Domain Representation

When does compositional structure yield compositional generalization? A kernel theory.

When GNNs meet symmetry in ILPs: an orbit-based feature augmentation approach

Sail into the Headwind: Alignment via Robust Rewards and Dynamic Labels against Reward Hacking

Programming Refusal with Conditional Activation Steering

Mentored Learning: Improving Generalization and Convergence of Student Learner

Towards General-Purpose Model-Free Reinforcement Learning

Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces

Soft Merging of Experts with Adaptive Routing

Scaling Autonomous Agents via Automatic Reward Modeling And Planning

Scaling Laws for Adversarial Attacks on Language Model Activations and Tokens

EC-DIT: Scaling Diffusion Transformers with Adaptive Expert-Choice Routing

TVNet: A Novel Time Series Analysis Method Based on Dynamic Convolution and 3D-Variation

DiffGAD: A Diffusion-based Unsupervised Graph Anomaly Detector

The Hyperfitting Phenomenon: Sharpening and Stabilizing LLMs for Open-Ended Text Generation

Generative Adversarial Ranking Nets

ADMM for Nonconvex Optimization under Minimal Continuity Assumption

Leveraging Sub-Optimal Data for Human-in-the-Loop Reinforcement Learning

Root Cause Analysis of Anomalies in Multivariate Time Series through Granger Causal Discovery

UniWav: Towards Unified Pre-training for Speech Representation Learning and Generation

Provable unlearning in topic modeling and downstream tasks

Object-Centric Pretraining via Target Encoder Bootstrapping

A Simple Framework for Open-Vocabulary Zero-Shot Segmentation

LLaVA-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models

Weakly-Supervised Affordance Grounding Guided by Part-Level Semantic Priors

RMP-SAM: Towards Real-Time Multi-Purpose Segment Anything

Strength Estimation and Human-Like Strength Adjustment in Games

LASeR: Towards Diversified and Generalizable Robot Design with Large Language Models

OptionZero: Planning with Learned Options

Towards Automated Knowledge Integration From Human-Interpretable Representations

Divergence-Regularized Discounted Aggregation: Equilibrium Finding in Multiplayer Partially Observable Stochastic Games

Risk-Sensitive Diffusion: Robustly Optimizing Diffusion Models with Noisy Samples

Schur's Positive-Definite Network: Deep Learning in the SPD cone with structure

Empowering LLM Agents with Zero-Shot Optimal Decision-Making through Q-learning

Discovering Group Structures via Unitary Representation Learning

What's New in My Data? Novelty Exploration via Contrastive Generation

Language Agents Meet Causality -- Bridging LLMs and Causal World Models

Revisit Large-Scale Image-Caption Data in Pre-training Multimodal Foundation Models

Rethinking Visual Counterfactual Explanations Through Region Constraint

IGL-Bench: Establishing the Comprehensive Benchmark for Imbalanced Graph Learning

Beyond Random Masking: When Dropout meets Graph Convolutional Networks

Not-So-Optimal Transport Flows for 3D Point Cloud Generation

Node Identifiers: Compact, Discrete Representations for Efficient Graph Learning

MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts

Pacmann: Efficient Private Approximate Nearest Neighbor Search

PiCO: Peer Review in LLMs based on Consistency Optimization

RRM: Robust Reward Model Training Mitigates Reward Hacking

MMEgo: Towards Building Egocentric Multimodal LLMs for Video QA

Can We Ignore Labels in Out of Distribution Detection?

MoDGS: Dynamic Gaussian Splatting from Casually-captured Monocular Videos with Depth Priors

A Non-Contrastive Learning Framework for Sequential Recommendation with Preference-Preserving Profile Generation

The Same but Different: Structural Similarities and Differences in Multilingual Language Modeling

Training-Free Dataset Pruning for Instance Segmentation

SEMDICE: Off-policy State Entropy Maximization via Stationary Distribution Correction Estimation

SpaceGNN: Multi-Space Graph Neural Network for Node Anomaly Detection with Extremely Limited Labels

ADePT: Adaptive Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning

Boosting Neural Combinatorial Optimization for Large-Scale Vehicle Routing Problems

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks

A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoals

Task Descriptors Help Transformers Learn Linear Models In-Context

Fast Direct: Query-Efficient Online Black-box Guidance for Diffusion-model Target Generation

Boosting the visual interpretability of CLIP via adversarial fine-tuning

LLMs Can Plan Only If We Tell Them

Topological Schrödinger Bridge Matching

Extending Mercer's expansion to indefinite and asymmetric kernels

FreDF: Learning to Forecast in the Frequency Domain

Differentially Private Federated Learning with Time-Adaptive Privacy Spending

Solving Video Inverse Problems Using Image Diffusion Models

Breaking the Reclustering Barrier in Centroid-based Deep Clustering

Should VLMs be Pre-trained with Image Data?

Efficient Alternating Minimization with Applications to Weighted Low Rank Approximation

On a Connection Between Imitation Learning and RLHF

Competitive Fair Scheduling with Predictions

Bayesian Experimental Design Via Contrastive Diffusions

Estimation of single-cell and tissue perturbation effect in spatial transcriptomics via Spatial Causal Disentanglement

Learning a Neural Solver for Parametric PDEs to Enhance Physics-Informed Methods

Second-Order Min-Max Optimization with Lazy Hessians

DenseMatcher: Learning 3D Semantic Correspondence for Category-Level Manipulation from a Single Demo

3DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation

Online-to-Offline RL for Agent Alignment

More RLHF, More Trust? On The Impact of Preference Alignment On Trustworthiness

URLOST: Unsupervised Representation Learning without Stationarity or Topology

Lambda-Skip Connections: the architectural component that prevents Rank Collapse

Decision Tree Induction Through LLMs via Semantically-Aware Evolution

Active Task Disambiguation with LLMs

Examining Alignment of Large Language Models through Representative Heuristics: the case of political stereotypes

Knowledge Localization: Mission Not Accomplished? Enter Query Localization!

MIRAGE: Evaluating and Explaining Inductive Reasoning Process in Language Models

Controlled LLM Decoding via Discrete Auto-regressive Biasing

ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time

Partially Observed Trajectory Inference using Optimal Transport and a Dynamics Prior

Optimization by Parallel Quasi-Quantum Annealing with Gradient-Based Sampling

OSCAR: Operating System Control via State-Aware Reasoning and Re-Planning

Exploring the Effectiveness of Object-Centric Representations in Visual Question Answering: Comparative Insights with Foundation Models

Bayesian Optimization of Antibodies Informed by a Generative Model of Evolving Sequences

Diverse Policies Recovering via Pointwise Mutual Information Weighted Imitation Learning

Advancing Graph Generation through Beta Diffusion

GenSE: Generative Speech Enhancement via Language Models using Hierarchical Modeling

Certifying Counterfactual Bias in LLMs

A Black Swan Hypothesis: The Role of Human Irrationality in AI Safety

Enhancing Cognition and Explainability of Multimodal Foundation Models with Self-Synthesized Data

AIMS.au: A Dataset for the Analysis of Modern Slavery Countermeasures in Corporate Statements

MQuAKE-Remastered: Multi-Hop Knowledge Editing Can Only Be Advanced with Reliable Evaluations

Laplace Sample Information: Data Informativeness Through a Bayesian Lens

S4M: S4 for multivariate time series forecasting with Missing values

Weak to Strong Generalization for Large Language Models with Multi-capabilities

On the Benefits of Memory for Modeling Time-Dependent PDEs

Studying the Interplay Between the Actor and Critic Representations in Reinforcement Learning

The Case for Cleaner Biosignals: High-fidelity Neural Compressor Enables Transfer from Cleaner iEEG to Noisier EEG

Monitoring Latent World States in Language Models with Propositional Probes

BAMDP Shaping: a Unified Framework for Intrinsic Motivation and Reward Shaping

Do LLMs have Consistent Values?

Multilevel Generative Samplers for Investigating Critical Phenomena

Sensor-Invariant Tactile Representation

Gaussian Ensemble Belief Propagation for Efficient Inference in High-Dimensional, Black-box Systems

Rethinking Invariance Regularization in Adversarial Training to Improve Robustness-Accuracy Trade-off

3D-SPATIAL MULTIMODAL MEMORY

Adaptive Transformer Programs: Bridging the Gap Between Performance and Interpretability in Transformers

Controllable Blur Data Augmentation Using 3D-Aware Motion Estimation

A Causal Lens for Learning Long-term Fair Policies

Mechanism and Emergence of Stacked Attention Heads in Multi-Layer Transformers

Optimizing 4D Gaussians for Dynamic Scene Video from Single Landscape Images

ComaDICE: Offline Cooperative Multi-Agent Reinforcement Learning with Stationary Distribution Shift Regularization

Global Identifiability of Overcomplete Dictionary Learning via L1 and Volume Minimization

ControlAR: Controllable Image Generation with Autoregressive Models

Fat-to-Thin Policy Optimization: Offline Reinforcement Learning with Sparse Policies

MaskBit: Embedding-free Image Generation via Bit Tokens

Connectome Mapping: Shape-Memory Network via Interpretation of Contextual Semantic Information

Mind the Gap: Examining the Self-Improvement Capabilities of Large Language Models

Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspective

When LLMs Play the Telephone Game: Cultural Attractors as Conceptual Tools to Evaluate LLMs in Multi-turn Settings

Probabilistic Learning to Defer: Handling Missing Expert Annotations and Controlling Workload Distribution

CPSample: Classifier Protected Sampling for Guarding Training Data During Diffusion

STAR: Synthesis of Tailored Architectures

RetroInText: A Multimodal Large Language Model Enhanced Framework for Retrosynthetic Planning via In-Context Representation Learning

PhyloLM: Inferring the Phylogeny of Large Language Models and Predicting their Performances in Benchmarks

Logically Consistent Language Models via Neuro-Symbolic Integration

Improving Text-to-Image Consistency via Automatic Prompt Optimization

OvercookedV2: Rethinking Overcooked for Zero-Shot Coordination

SFESS: Score Function Estimators for $k$-Subset Sampling

ET-SEED: EFFICIENT TRAJECTORY-LEVEL SE(3) EQUIVARIANT DIFFUSION POLICY

Generating Less Certain Adversarial Examples Improves Robust Generalization

Discretization-invariance? On the Discretization Mismatch Errors in Neural Operators

Select before Act: Spatially Decoupled Action Repetition for Continuous Control

Score-based free-form architectures for high-dimensional Fokker-Planck equations

ACTIVE: Offline Reinforcement Learning via Adaptive Imitation and In-sample $V$-Ensemble

Offline RL with Smooth OOD Generalization in Convex Hull and its Neighborhood

Revisiting Mode Connectivity in Neural Networks with Bezier Surface

Inverse decision-making using neural amortized Bayesian actors

Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing

Approximating Full Conformal Prediction for Neural Network Regression with Gauss-Newton Influence

SWEb: A Large Web Dataset for the Scandinavian Languages

Reveal Object in Lensless Photography via Region Gaze and Amplification

Leveraging Submodule Linearity Enhances Task Arithmetic Performance in LLMs

ReSi: A Comprehensive Benchmark for Representational Similarity Measures

Operator Deep Smoothing for Implied Volatility

Learning from negative feedback, or positive feedback or both

Vertical Federated Learning with Missing Features During Training and Inference

Exploiting Hidden Symmetry to Improve Objective Perturbation for DP Linear Learners with a Nonsmooth L1-Norm

Deep Weight Factorization: Sparse Learning Through the Lens of Artificial Symmetries

The Power of LLM-Generated Synthetic Data for Stance Detection in Online Political Discussions

A Second-Order Perspective on Model Compositionality and Incremental Learning

Going Beyond Feature Similarity: Effective Dataset distillation based on Class-aware Conditional Mutual Information

Adversarially Robust Out-of-Distribution Detection Using Lyapunov-Stabilized Embeddings

Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning

Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF

Self-supervised contrastive learning performs non-linear system identification

Learning on One Mode: Addressing Multi-modality in Offline Reinforcement Learning

Continual Slow-and-Fast Adaptation of Latent Neural Dynamics (CoSFan): Meta-Learning What-How & When to Adapt

Reflective Gaussian Splatting

Proxy Denoising for Source-Free Domain Adaptation

GeoLoRA: Geometric integration for parameter efficient fine-tuning

Concept Bottleneck Large Language Models

A transfer learning framework for weak to strong generalization

Higher-Order Graphon Neural Networks: Approximation and Cut Distance

Generalization, Expressivity, and Universality of Graph Neural Networks on Attributed Graphs

LiveXiv - A Multi-Modal live benchmark based on Arxiv papers content

Generalization Bounds for Canonicalization: A Comparative Study with Group Averaging

Scalable Influence and Fact Tracing for Large Language Model Pretraining

Open-Set Graph Anomaly Detection via Normal Structure Regularisation

Efficient Distribution Matching of Representations via Noise-Injected Deep InfoMax

DreamCatalyst: Fast and High-Quality 3D Editing via Controlling Editability and Identity Preservation

Enhance Multi-View Classification Through Multi-Scale Alignment and Expanded Boundary

OVTR: End-to-End Open-Vocabulary Multiple Object Tracking with Transformer

Variational Best-of-N Alignment

Learning Efficient Positional Encodings with Graph Neural Networks

Training Neural Networks as Recognizers of Formal Languages

Compositional simulation-based inference for time series

Controllable Context Sensitivity and the Knob Behind It

Pangea: A Fully Open Multilingual Multimodal LLM for 39 Languages

KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language Models

Towards more rigorous evaluations of language models

Continuous Ensemble Weather Forecasting with Diffusion models

Ada-K Routing: Boosting the Efficiency of MoE-based LLMs

Balancing Bias in Two-sided Markets for Fair Stable Matchings

Multiview Equivariance Improves 3D Correspondence Understanding with Minimal Feature Finetuning

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency

Efficiently Democratizing Medical LLMs for 50 Languages via a Mixture of Language Family Experts

KBLaM: Knowledge Base augmented Language Model

Fantastic Copyrighted Beasts and How (Not) to Generate Them

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

The Belief State Transformer

CubeDiff: Repurposing Diffusion-Based Image Models for Panorama Generation

DRoP: Distributionally Robust Data Pruning

Improving Reasoning Performance in Large Language Models via Representation Engineering

Interpreting Language Reward Models via Contrastive Explanations

Neural Context Flows for Meta-Learning of Dynamical Systems

From Complexity to Clarity: Analytical Expressions of Deep Neural Network Weights via Clifford Algebra and Convexity

PnP-Flow: Plug-and-Play Image Restoration with Flow Matching

Minimal Variance Model Aggregation: A principled, non-intrusive, and versatile integration of black box models

Scaling and evaluating sparse autoencoders

MIRACLE 3D: Memory-efficient Integrated Robust Approach for Continual Learning on 3D Point Clouds via Shape Model Construction

Distributed Speculative Inference (DSI): Speculation Parallelism for Provably Faster Lossless Language Model Inference

Posterior-Mean Rectified Flow: Towards Minimum MSE Photo-Realistic Image Restoration

Controllable Generation via Locally Constrained Resampling

Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation Model

Deep Networks Learn Features From Local Discontinuities in the Label Function

Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models

Linear Mode Connectivity in Differentiable Tree Ensembles

Text4Seg: Reimagining Image Segmentation as Text Generation

SIMPL: Scalable and hassle-free optimisation of neural representations from behaviour

Building Blocks of Differentially Private Training

Language Models Trained to do Arithmetic Predict Human Risky and Intertemporal Choice

Formation of Representations in Neural Networks

Federated Few-Shot Class-Incremental Learning

Contractive Dynamical Imitation Policies for Efficient Out-of-Sample Recovery

Inference Scaling for Long-Context Retrieval Augmented Generation

Vision and Language Synergy for Rehearsal Free Continual Learning

Large Language Models Assume People are More Rational than We Really are

Beyond correlation: The impact of human uncertainty in measuring the effectiveness of automatic evaluation and LLM-as-a-judge

RESuM: A Rare Event Surrogate Model for Physics Detector Design

Reinforcement Learning for Control of Non-Markovian Cellular Population Dynamics

Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model

Composable Interventions for Language Models

PRISM: Privacy-Preserving Improved Stochastic Masking for Federated Generative Models

Graph-based Document Structure Analysis

SV-RAG: LoRA-Contextualizing Adaptation of MLLMs for Long Document Understanding

LICO: Large Language Models for In-Context Molecular Optimization

Bisimulation Metric for Model Predictive Control

Causal Identification for Complex Functional Longitudinal Studies

Geometry of Lightning Self-Attention: Identifiability and Dimension

Taming Overconfidence in LLMs: Reward Calibration in RLHF

Fourier Head: Helping Large Language Models Learn Complex Probability Distributions

Mutual Effort for Efficiency: A Similarity-based Token Pruning for Vision Transformers in Self-Supervised Learning

DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing

TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies

Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think

RevisEval: Improving LLM-as-a-Judge via Response-Adapted References

Efficient Model Editing with Task-Localized Sparse Fine-tuning

Minimalistic Predictions for Online Class Constraint Scheduling

Linear combinations of latents in generative models: subspaces and beyond

XAIguiFormer: explainable artificial intelligence guided transformer for brain disorder identification

Benchmarking Predictive Coding Networks -- Made Simple

Shifting the Paradigm: A Diffeomorphism Between Time Series Data Manifolds for Achieving Shift-Invariancy in Deep Learning

Data Distillation for extrapolative protein design through exact preference optimization

Risk-Controlling Model Selection via Guided Bayesian Optimization

On Scaling Up 3D Gaussian Splatting Training

Coreset Selection via Reducible Loss in Continual Learning

Generator Matching: Generative modeling with arbitrary Markov processes

A Percolation Model of Emergence: Analyzing Transformers Trained on a Formal Language

PhyloVAE: Unsupervised Learning of Phylogenetic Trees via Variational Autoencoders

Underdamped Diffusion Bridges with Applications to Sampling

Simulating Training Dynamics to Reconstruct Training Data from Deep Neural Networks

Sequential Controlled Langevin Diffusions

Interpreting Global Perturbation Robustness of Image Models using Axiomatic Spectral Importance Decomposition

Solving Inverse Problems with Model Mismatch using Untrained Neural Networks within Model-based Architectures

GraphArena: Evaluating and Exploring Large Language Models on Graph Computation

GDrag:Towards General-Purpose Interactive Editing with Anti-ambiguity Point Diffusion

Find A Winning Sign: Sign Is All We Need to Win the Lottery

Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models

AnyTouch: Learning Unified Static-Dynamic Representation across Multiple Visuo-tactile Sensors

SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement

Handling Delay in Real-Time Reinforcement Learning

Watermark Anything With Localized Messages

How Low Can You Go? Searching for the Intrinsic Dimensionality of Complex Networks using Metric Node Embeddings

CircuitFusion: Multimodal Circuit Representation Learning for Agile Chip Design

Can Generative AI Solve Your In-Context Learning Problem? A Martingale Perspective

Lift Your Molecules: Molecular Graph Generation in Latent Euclidean Space

WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct

Statistical Tractability of Off-policy Evaluation of History-dependent Policies in POMDPs

Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning

SPA: 3D Spatial-Awareness Enables Effective Embodied Representation

COAT: Compressing Optimizer states and Activations for Memory-Efficient FP8 Training

Mechanistic Interpretability Meets Vision Language Models: Insights and Limitations

A Little Goes a Long Way: Efficient Long Context Training and Inference with Partial Contexts

Efficient and Trustworthy Causal Discovery with Latent Variables and Complex Relations

Video Action Differencing

Hierarchical Uncertainty Estimation for Learning-based Registration in Neuroimaging

Recovery of Causal Graph Involving Latent Variables via Homologous Surrogates

GenEx: Generating an Explorable World

Understanding and Enhancing the Transferability of Jailbreaking Attacks

Compositional 4D Dynamic Scenes Understanding with Physics Priors for Video Question Answering

Training LLMs over Neurally Compressed Text

Autoregressive Pretraining with Mamba in Vision

Mastering Task Arithmetic: $\tau$Jp as a Key Indicator for Weight Disentanglement

Instance-dependent Early Stopping

SFS: Smarter Code Space Search improves LLM Inference Scaling

YOLO-RD: Introducing Relevant and Compact Explicit Knowledge to YOLO by Retriever-Dictionary

Fictitious Synthetic Data Can Improve LLM Factuality via Prerequisite Learning

Rational Decision-Making Agent with Learning Internal Utility Judgment

IFORMER: INTEGRATING CONVNET AND TRANSFORMER FOR MOBILE APPLICATION

TypedThinker: Diversify Large Language Model Reasoning with Typed Thinking

Identification of Intermittent Temporal Latent Process

Failures to Find Transferable Image Jailbreaks Between Vision-Language Models

Synergy Between Sufficient Changes and Sparse Mixing Procedure for Disentangled Representation Learning

Causal Representation Learning from Multimodal Biomedical Observations

Diffusion-NPO: Negative Preference Optimization for Better Preference Aligned Generation of Diffusion Models

Sparse autoencoders reveal selective remapping of visual concepts during adaptation

How much of my dataset did you use? Quantitative Data Usage Inference in Machine Learning

Discovering Influential Neuron Path in Vision Transformers

SGD with memory: fundamental properties and stochastic acceleration

Reconsidering Faithfulness in Regular, Self-Explainable and Domain Invariant GNNs

Beyond Surface Structure: A Causal Assessment of LLMs' Comprehension ability

OCCAM: Towards Cost-Efficient and Accuracy-Aware Classification Inference

StringLLM: Understanding the String Processing Capability of Large Language Models

Transformer-Squared: Self-adaptive LLMs

Intrinsic Dimension Correlation: uncovering nonlinear connections in multimodal representations

Agent Skill Acquisition for Large Language Models via CycleQD

Controlling the Fidelity and Diversity of Deep Generative Models via Pseudo Density

Personalized Visual Instruction Tuning

PFGuard: A Generative Framework with Privacy and Fairness Safeguards

Hessian-Free Online Certified Unlearning

Integrative Decoding: Improving Factuality via Implicit Self-consistency

Kolmogorov-Arnold Transformer

GraphBridge: Towards Arbitrary Transfer Learning in GNNs

Factual Context Validation and Simplification: A Scalable Method to Enhance GPT Trustworthiness and Efficiency

HG-Adapter: Improving Pre-Trained Heterogeneous Graph Neural Networks with Dual Adapters

A General Framework for Producing Interpretable Semantic Text Embeddings

Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback

ColPali: Efficient Document Retrieval with Vision Language Models

NRGBoost: Energy-Based Generative Boosted Trees

Neuron based Personality Trait Induction in Large Language Models

Support is All You Need for Certified VAE Training

Robust Barycenter Estimation using Semi-Unbalanced Neural Optimal Transport

SmartPretrain: Model-Agnostic and Dataset-Agnostic Representation Learning for Motion Prediction

Quamba: A Post-Training Quantization Recipe for Selective State Space Models

SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?

Universal generalization guarantees for Wasserstein distributionally robust models

Scaling In-the-Wild Training for Diffusion-based Illumination Harmonization and Editing by Imposing Consistent Light Transport

Generating Graphs via Spectral Diffusion

Sparse components distinguish visual pathways & their alignment to neural networks

GaussianAnything: Interactive Point Cloud Flow Matching for 3D Generation

LongVILA: Scaling Long-Context Visual Language Models for Long Videos

BirdSet: A Large-Scale Dataset for Audio Classification in Avian Bioacoustics

Eliciting Human Preferences with Language Models

What Makes a Maze Look Like a Maze?

Identifying latent state transitions in non-linear dynamical systems

Selective Task Group Updates for Multi-Task Optimization

TULIP: Token-length Upgraded CLIP

From Few to Many: Self-Improving Many-Shot Reasoners Through Iterative Optimization and Generation

Real-time design of architectural structures with differentiable mechanics and neural networks

Scalable Decentralized Learning with Teleportation

PhiNets: Brain-inspired Non-contrastive Learning Based on Temporal Prediction Hypothesis

Self-Supervised Diffusion Models for Electron-Aware Molecular Representation Learning

Learning Distributions of Complex Fluid Simulations with Diffusion Graph Networks

Palu: KV-Cache Compression with Low-Rank Projection

REFINE: Inversion-Free Backdoor Defense via Model Reprogramming

To Trust or Not to Trust? Enhancing Large Language Models' Situated Faithfulness to External Contexts

Approaching Rate-Distortion Limits in Neural Compression with Lattice Transform Coding

Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training

Mitigating Object Hallucination in MLLMs via Data-augmented Phrase-level Alignment

AI2TALE: An Innovative Information Theory-based Approach for Learning to Localize Phishing Attacks

E-Valuating Classifier Two-Sample Tests

Bayesian Image Regression with Soft-thresholded Conditional Autoregressive Prior

Explore Theory of Mind: program-guided adversarial data generation for theory of mind reasoning

BEEM: Boosting Performance of Early Exit DNNs using Multi-Exit Classifiers as Experts

Linear Recurrences Accessible to Everyone

Varying Shades of Wrong: Aligning LLMs with Wrong Answers Only

The Ramanujan Library - Automated Discovery on the Hypergraph of Integer Relations

PersonalLLM: Tailoring LLMs to Individual Preferences

Language Imbalance Driven Rewarding for Multilingual Self-improving

Balanced Neural ODEs: nonlinear model order reduction and Koopman operator approximations

APE: Faster and Longer Context-Augmented Generation via Adaptive Parallel Encoding

ManiSkill-HAB: A Benchmark for Low-Level Manipulation in Home Rearrangement Tasks

HiLo: A Learning Framework for Generalized Category Discovery Robust to Domain Shifts

More Experts Than Galaxies: Conditionally-Overlapping Experts with Biologically-Inspired Fixed Routing

Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model

Score Forgetting Distillation: A Swift, Data-Free Method for Machine Unlearning in Diffusion Models

Provable weak-to-strong generalization via benign overfitting

Non-Stationary Dueling Bandits Under a Weighted Borda Criterion

Scalable Decision-Making in Stochastic Environments through Learned Temporal Abstraction

Has the Deep Neural Network learned the Stochastic Process? An Evaluation Viewpoint

Beyond Mere Token Analysis: A Hypergraph Metric Space Framework for Defending Against Socially Engineered LLM Attacks

Adversarial Search Engine Optimization for Large Language Models

Adversarial Perturbations Cannot Reliably Protect Artists From Generative AI

OLMoE: Open Mixture-of-Experts Language Models

Gramian Multimodal Representation Learning and Alignment

Measuring Non-Adversarial Reproduction of Training Data in Large Language Models

O(d/T) Convergence Theory for Diffusion Probabilistic Models under Minimal Assumptions

SINGAPO: Single Image Controlled Generation of Articulated Parts in Objects

Hierarchical Autoregressive Transformers: Combining Byte- and Word-Level Processing for Robust, Adaptable Language Models

One Model Transfer to All: On Robust Jailbreak Prompts Generation against LLMs

IRIS: LLM-Assisted Static Analysis for Detecting Security Vulnerabilities

Scalable Extraction of Training Data from Aligned, Production Language Models

Reti-Diff: Illumination Degradation Image Restoration with Retinex-based Latent Diffusion Model

Overcoming False Illusions in Real-World Face Restoration with Multi-Modal Guided Diffusion Model

Gap Preserving Distillation by Building Bidirectional Mappings with A Dynamic Teacher

GenDataAgent: On-the-fly Dataset Augmentation with Synthetic Data

Sylber: Syllabic Embedding Representation of Speech from Raw Audio

Learning Interpretable Hierarchical Dynamical Systems Models from Time Series Data

CAT-3DGS: A Context-Adaptive Triplane Approach to Rate-Distortion-Optimized 3DGS Compression

Causal Graphical Models for Vision-Language Compositional Understanding

A Unified Theory of Quantum Neural Network Loss Landscapes

Emergence of meta-stable clustering in mean-field transformer models

Counterfactual Generative Modeling with Variational Causal Inference

Bias Mitigation in Graph Diffusion Models

VibeCheck: Discover and Quantify Qualitative Differences in Large Language Models

AutoCLIP: Auto-tuning Zero-Shot Classifiers for Vision-Language Models

Improved Sampling Algorithms for Lévy-Itô Diffusion Models

Aioli: A Unified Optimization Framework for Language Model Data Mixing

ActionReasoningBench: Reasoning about Actions with and without Ramification Constraints

Counterfactual Realizability

MMD-Regularized Unbalanced Optimal Transport

Variance-Reducing Couplings for Random Features

Geometry of Neural Reinforcement Learning in Continuous State and Action Spaces

Differentiable and Learnable Wireless Simulation with Geometric Transformers

Optimal Strong Regret and Violation in Constrained MDPs via Policy Optimization

Do vision models perceive objects like toddlers ?

Open-World Reinforcement Learning over Long Short-Term Imagination

Flash Inference: Near Linear Time Inference for Long Convolution Sequence Models and Beyond

Expected Return Symmetries

Fast training and sampling of Restricted Boltzmann Machines

Spreading Out-of-Distribution Detection on Graphs

Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval

Bayesian Optimization via Continual Variational Last Layer Training

Relation-Aware Diffusion for Heterogeneous Graphs with Partially Observed Features

On Rollouts in Model-Based Reinforcement Learning

TabReD: Analyzing Pitfalls and Filling the Gaps in Tabular Deep Learning Benchmarks

Sports-Traj: A Unified Trajectory Generation Model for Multi-Agent Movement in Sports

Scale-Free Graph-Language Models

Accessing Vision Foundation Models via ImageNet-1K

Samba: Synchronized Set-of-Sequences Modeling for Multiple Object Tracking

Subgraph Federated Learning for Local Generalization

Does Refusal Training in LLMs Generalize to the Past Tense?

Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks

NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals

GETS: Ensemble Temperature Scaling for Calibration in Graph Neural Networks

Selective induction Heads: How Transformers Select Causal Structures in Context

DreamDistribution: Learning Prompt Distribution for Diverse In-distribution Generation

DeepRTL: Bridging Verilog Understanding and Generation with a Unified Representation Model

Is In-Context Learning Sufficient for Instruction Following in LLMs?

InstantSwap: Fast Customized Concept Swapping across Sharp Shape Differences

Swift Hydra: Self-Reinforcing Generative Framework for Anomaly Detection with Multiple Mamba Models

Learning to Discover Regulatory Elements for Gene Expression Prediction

Open-YOLO 3D: Towards Fast and Accurate Open-Vocabulary 3D Instance Segmentation

AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulation

Improved Training Technique for Latent Consistency Models

Does Training with Synthetic Data Truly Protect Privacy?

InterMask: 3D Human Interaction Generation via Collaborative Masked Modeling

KOR-Bench: Benchmarking Language Models on Knowledge-Orthogonal Reasoning Tasks

MDSGen: Fast and Efficient Masked Diffusion Temporal-Aware Transformers for Open-Domain Sound Generation

Exact Byte-Level Probabilities from Tokenized Language Models for FIM-Tasks and Model Ensembles

MA$^2$E: Addressing Partial Observability in Multi-Agent Reinforcement Learning with Masked Auto-Encoder

Multi-Task Corrupted Prediction for Learning Robust Audio-Visual Speech Representation

Multi-Perspective Data Augmentation for Few-shot Object Detection

Automated Filtering of Human Feedback Data for Aligning Text-to-Image Diffusion Models

TOP-ERL: Transformer-based Off-Policy Episodic Reinforcement Learning

Rapid Selection and Ordering of In-Context Demonstrations via Prompt Embedding Clustering

Plug, Play, and Generalize: Length Extrapolation with Pointer-Augmented Neural Memory

FlickerFusion: Intra-trajectory Domain Generalizing Multi-agent Reinforcement Learning

EDiT: A Local-SGD-Based Efficient Distributed Training Method for Large Language Models

Deconstructing Denoising Diffusion Models for Self-Supervised Learning

An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual Pixels

Student-Informed Teacher Training

Stochastic variance-reduced Gaussian variational inference on the Bures-Wasserstein manifold

Generalization through variance: how noise shapes inductive biases in diffusion models

A deep inverse-mapping model for a flapping robotic wing

Capability Localization: Capabilities Can be Localized rather than Individual Knowledge

Learning Successor Features with Distributed Hebbian Temporal Memory

Dist Loss: Enhancing Regression in Few-Shot Region through Distribution Distance Constraint

JudgeLM: Fine-tuned Large Language Models are Scalable Judges

Robust Transfer of Safety-Constrained Reinforcement Learning Agents

On Discriminative Probabilistic Modeling for Self-Supervised Representation Learning

SplineGS: Learning Smooth Trajectories in Gaussian Splatting for Dynamic Scene Reconstruction

SLMRec: Distilling Large Language Models into Small for Sequential Recommendation

PADRe: A Unifying Polynomial Attention Drop-in Replacement for Efficient Vision Transformer

Accelerated Over-Relaxation Heavy-Ball Method: Achieving Global Accelerated Convergence with Broad Generalization

BaB-ND: Long-Horizon Motion Planning with Branch-and-Bound and Neural Dynamics

Towards Generalizable Reinforcement Learning via Causality-Guided Self-Adaptive Representations

PolyhedronNet: Representation Learning for Polyhedra with Surface-attributed Graph

Gaussian Splatting Lucas-Kanade

Test of Time: A Benchmark for Evaluating LLMs on Temporal Reasoning

Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation

Mind the GAP: Glimpse-based Active Perception improves generalization and sample efficiency of visual reasoning

SCBench: A KV Cache-Centric Analysis of Long-Context Methods

Exponential Topology-enabled Scalable Communication in Multi-agent Reinforcement Learning

On the self-verification limitations of large language models on reasoning and planning tasks

Multi-modal brain encoding models for multi-modal stimuli

Brain Bandit: A Biologically Grounded Neural Network for Efficient Control of Exploration

Robustness Auditing for Linear Regression: To Singularity and Beyond

Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts

Joint Graph Rewiring and Feature Denoising via Spectral Resonance

Expected Sliced Transport Plans

Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion

HAMSTER: Hierarchical Action Models for Open-World Robot Manipulation

Regularization by Texts for Latent Diffusion Inverse Solvers

Partial Gromov-Wasserstein Metric

CFG++: Manifold-constrained Classifier Free Guidance for Diffusion Models

Improving Large Language Model Planning with Action Sequence Similarity

Differential Transformer

Bayesian Analysis of Combinatorial Gaussian Process Bandits

Atomas: Hierarchical Adaptive Alignment on Molecule-Text for Unified Molecule Understanding and Generation

Demystifying the Token Dynamics of Deep Selective State Space Models

Visual Haystacks: A Vision-Centric Needle-In-A-Haystack Benchmark

Language-Image Models with 3D Understanding

CausalRivers - Scaling up benchmarking of causal discovery for real-world time-series

DenoiseVAE: Learning Molecule-Adaptive Noise Distributions for Denoising-based 3D Molecular Pre-training

DarkBench: Benchmarking Dark Patterns in Large Language Models

Methods with Local Steps and Random Reshuffling for Generally Smooth Non-Convex Federated Optimization

MAST: model-agnostic sparsified training

Generating Freeform Endoskeletal Robots

Wasserstein-Regularized Conformal Prediction under General Distribution Shift

Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems

You Only Prune Once: Designing Calibration-Free Model Compression With Policy Learning

PQMass: Probabilistic Assessment of the Quality of Generative Models using Probability Mass Estimation

Rethinking the role of frames for SE(3)-invariant crystal structure modeling

Iterative Label Refinement Matters More than Preference Optimization under Weak Supervision

Uncovering Gaps in How Humans and LLMs Interpret Subjective Language

Periodic Materials Generation using Text-Guided Joint Diffusion Model

SynFlowNet: Design of Diverse and Novel Molecules with Synthesis Constraints

Towards Unbiased Calibration using Meta-Regularization

Fast Training of Sinusoidal Neural Fields via Scaling Initialization

Learning the Complexity of Weakly Noisy Quantum States

Fast unsupervised ground metric learning with tree-Wasserstein distance

Learning system dynamics without forgetting

QERA: an Analytical Framework for Quantization Error Reconstruction

VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents

Self-Improvement for Neural Combinatorial Optimization: Sample Without Replacement, but Improvement

AI Sandbagging: Language Models can Strategically Underperform on Evaluations

Improving Pretraining Data Using Perplexity Correlations

Retri3D: 3D Neural Graphics Representation Retrieval

On the Price of Differential Privacy for Hierarchical Clustering

CogCoM: A Visual Language Model with Chain-of-Manipulations Reasoning

Learning-Augmented Search Data Structures

MixMax: Distributional Robustness in Function Space via Optimal Data Mixtures

AdaWM: Adaptive World Model based Planning for Autonomous Driving

HASARD: A Benchmark for Vision-Based Safe Reinforcement Learning in Embodied Agents

Toward Understanding In-context vs. In-weight Learning

LoRA Done RITE: Robust Invariant Transformation Equilibration for LoRA Optimization

Improving Unsupervised Constituency Parsing via Maximizing Semantic Information

GIFT: Unlocking Full Potential of Labels in Distilled Dataset at Near-zero Cost

CoMRes: Semi-Supervised Time Series Forecasting Utilizing Consensus Promotion of Multi-Resolution

Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization

Optimal Transport for Time Series Imputation

Is Large-scale Pretraining the Secret to Good Domain Generalization?

Cross-Domain Off-Policy Evaluation and Learning for Contextual Bandits

Multimodal Unsupervised Domain Generalization by Retrieving Across the Modality Gap

ANaGRAM: A Natural Gradient Relative to Adapted Model for efficient PINNs learning

Systematic Outliers in Large Language Models

Fantastic Targets for Concept Erasure in Diffusion Models and Where To Find Them

Needle Threading: Can LLMs Follow Threads Through Near-Million-Scale Haystacks?

Residual Connections and Normalization Can Provably Prevent Oversmoothing in GNNs

Gaussian Mixture Counterfactual Generator

Efficient Top-m Data Values Identification for Data Selection

Gradient correlation is a key ingredient to accelerate SGD with momentum

Learning to Search from Demonstration Sequences

An Information Criterion for Controlled Disentanglement of Multimodal Data

Mitigating Parameter Interference in Model Merging via Sharpness-Aware Fine-Tuning

Language Models Are Implicitly Continuous

Weighted Point Set Embedding for Multimodal Contrastive Learning Toward Optimal Similarity Metric

PABBO: Preferential Amortized Black-Box Optimization

Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model

Jump Your Steps: Optimizing Sampling Schedule of Discrete Diffusion Models

PRDP: Progressively Refined Differentiable Physics

TweedieMix: Improving Multi-Concept Fusion for Diffusion-based Image/Video Generation

Generalized Consistency Trajectory Models for Image Manipulation

Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with Imagination

NeurFlow: Interpreting Neural Networks through Neuron Groups and Functional Interactions

HyperPLR: Hypergraph Generation through Projection, Learning, and Reconstruction

Semi-Parametric Retrieval via Binary Bag-of-Tokens Index

M^3PC: Test-time Model Predictive Control using Pretrained Masked Trajectory Model

Imputation for prediction: beware of diminishing returns.

Forking Paths in Neural Text Generation

RECAST: Reparameterized, Compact weight Adaptation for Sequential Tasks

Broaden your SCOPE! Efficient Multi-turn Conversation Planning for LLMs with Semantic Space

HALL-E: Hierarchical Neural Codec Language Model for Minute-Long Zero-Shot Text-to-Speech Synthesis

Adapters for Altering LLM Vocabularies: What Languages Benefit the Most?

Scaling LLM Test-Time Compute Optimally Can be More Effective than Scaling Parameters for Reasoning

Model Equality Testing: Which Model is this API Serving?

Decoupled Finetuning for Domain Generalizable Semantic Segmentation

Interpretable Vision-Language Survival Analysis with Ordinal Inductive Bias for Computational Pathology

Context Clues: Evaluating Long Context Models for Clinical Prediction Tasks on EHR Data

Enhancing Uncertainty Estimation and Interpretability with Bayesian Non-negative Decision Layer

Progressive Token Length Scaling in Transformer Encoders for Efficient Universal Segmentation

Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment

Positive-Unlabeled Diffusion Models for Preventing Sensitive Data Generation

Equivariant Neural Functional Networks for Transformers

Intermediate Layer Classifiers for OOD generalization

Jamba: Hybrid Transformer-Mamba Language Models

From Tokens to Words: On the Inner Lexicon of LLMs

A Curious Case of the Missing Measure: Better Scores and Worse Generation

Add-it: Training-Free Object Insertion in Images With Pretrained Diffusion Models

Self-Updatable Large Language Models by Integrating Context into Model Parameters

Exploiting Distribution Constraints for Scalable and Efficient Image Retrieval

Dimension Agnostic Neural Processes

HR-Extreme: A High-Resolution Dataset for Extreme Weather Forecasting

ViSAGe: Video-to-Spatial Audio Generation

Revisiting Energy Based Models as Policies: Ranking Noise Contrastive Estimation and Interpolating Energy Models

Fine-tuning with Reserved Majority for Noise Reduction

Shallow diffusion networks provably learn hidden low-dimensional structure

Deep Kernel Posterior Learning under Infinite Variance Prior Weights

Credit-based self organizing maps: training deep topographic networks with minimal performance degradation

Privacy Auditing of Large Language Models

Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching

Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding

Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better

An Efficient Framework for Crediting Data Contributors of Diffusion Models

TexTailor: Customized Text-aligned Texturing via Effective Resampling

ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation

A Large-scale Training Paradigm for Graph Generative Models

PooDLe🐩: Pooled and dense self-supervised learning from naturalistic videos

From GNNs to Trees: Multi-Granular Interpretability for Graph Neural Networks

Stable Segment Anything Model

Attention as a Hypernetwork

Node Similarities under Random Projections: Limits and Pathological Cases

OCEAN: Offline Chain-of-thought Evaluation and Alignment in Large Language Models

Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs

Breaking Class Barriers: Efficient Dataset Distillation via Inter-Class Feature Compensator

STORM: Spatio-TempOral Reconstruction Model For Large-Scale Outdoor Scenes

UniGEM: A Unified Approach to Generation and Property Prediction for Molecules

Harnessing Webpage UIs for Text-Rich Visual Understanding

Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows

Prompt as Knowledge Bank: Boost Vision-language model via Structural Representation for zero-shot medical detection

How do we interpret the outputs of a neural network trained on classification?

ONLINE EPSILON NET & PIERCING SET FOR GEOMETRIC CONCEPTS

Vision CNNs trained to estimate spatial latents learned similar ventral-stream-aligned representations

Online Reward-Weighted Fine-Tuning of Flow Matching with Wasserstein Regularization

Unsupervised Meta-Learning via In-Context Learning

MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization

AdaGrad under Anisotropic Smoothness

Re-evaluating Open-ended Evaluation of Large Language Models

A Skewness-Based Criterion for Addressing Heteroscedastic Noise in Causal Discovery

Towards Fast, Specialized Machine Learning Force Fields: Distilling Foundation Models via Energy Hessians

Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF

Beyond-Expert Performance with Limited Demonstrations: Efficient Imitation Learning with Double Exploration

PPT: Patch Order Do Matters In Time Series Pretext Task

Bridging Jensen Gap for Max-Min Group Fairness Optimization in Recommendation

Efficient Discovery of Pareto Front for Multi-Objective Reinforcement Learning

Constructing Confidence Intervals for Average Treatment Effects from Multiple Datasets

Efficient Training of Neural Stochastic Differential Equations by Matching Finite Dimensional Distributions

The Computational Complexity of Circuit Discovery for Inner Interpretability

ImpScore: A Learnable Metric For Quantifying The Implicitness Level of Sentences

Immunogenicity Prediction with Dual Attention Enables Vaccine Target Selection

ConvCodeWorld: Benchmarking Conversational Code Generation in Reproducible Feedback Environments

Counterfactual Concept Bottleneck Models

“I Am the One and Only, Your Cyber BFF”: Understanding the Impact of GenAI Requires Understanding the Impact of Anthropomorphic AI

Predicate Hierarchies Improve Few-Shot State Classification

Expand and Compress: Exploring Tuning Principles for Continual Spatio-Temporal Graph Forecasting

Air Quality Prediction with Physics-Guided Dual Neural ODEs in Open Systems

Track-On: Transformer-based Online Point Tracking with Memory

Towards Neural Scaling Laws for Time Series Foundation Models

Enhancing Document Understanding with Group Position Embedding: A Novel Approach to Incorporate Layout Information

First-Person Fairness in Chatbots

Interactive Adjustment for Human Trajectory Prediction with Individual Feedback

On the Modeling Capabilities of Large Language Models for Sequential Decision Making

AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution

LeanQuant: Accurate and Scalable Large Language Model Quantization with Loss-error-aware Grid

PIG: Physics-Informed Gaussians as Adaptive Parametric Mesh Representations

Transformer Encoder Satisfiability: Complexity and Impact on Formal Reasoning

Learning Causal Alignment for Reliable Disease Diagnosis

Refining CLIP's Spatial Awareness: A Visual-Centric Perspective

Near-Optimal Online Learning for Multi-Agent Submodular Coordination: Tight Approximation and Communication Efficiency

YouTube-SL-25: A Large-Scale, Open-Domain Multilingual Sign Language Parallel Corpus

AIR-BENCH 2024: A Safety Benchmark based on Regulation and Policies Specified Risk Categories

Computational Limits of Low-Rank Adaptation (LoRA) Fine-Tuning for Transformer Models

Mini-batch Coresets for Memory-efficient Language Model Training on Data Mixtures

QA-Calibration of Language Model Confidence Scores

Speech Robust Bench: A Robustness Benchmark For Speech Recognition

Segment Any 3D Object with Language

ComPC: Completing a 3D Point Cloud with 2D Diffusion Priors

Beyond Autoregression: Discrete Diffusion for Complex Reasoning and Planning

Beyond single neurons: population response geometry in digital twins of mouse visual cortex

A Conditional Independence Test in the Presence of Discretization

Towards Unbiased Learning in Semi-Supervised Semantic Segmentation

Chain-of-Focus Prompting: Leveraging Sequential Visual Cues to Prompt Large Autoregressive Vision Models

Flow: Modularized Agentic Workflow Automation

From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks

Stochastic Polyak Step-sizes and Momentum: Convergence Guarantees and Practical Performance

Prototype antithesis for biological few-shot class-incremental learning

PointOBB-v2: Towards Simpler, Faster, and Stronger Single Point Supervised Oriented Object Detection

Towards Explaining the Power of Constant-depth Graph Neural Networks for Structured Linear Programming

On the Optimization Landscape of Low Rank Adaptation Methods for Large Language Models

Multi-modal Learning: A Look Back and the Road Ahead

Execution-guided within-prompt search for programming-by-example

Metric-Driven Attributions for Vision Transformers

Correlation and Navigation in the Vocabulary Key Representation Space of Language Models

LLMOPT: Learning to Define and Solve General Optimization Problems from Scratch

OPTAMI: Global Superlinear Convergence of High-order Methods

SOO-Bench: Benchmarks for Evaluating the Stability of Offline Black-Box Optimization

Centrality-guided Pre-training for Graph

Emergent Orientation Maps —— Mechanisms, Coding Efficiency and Robustness

Unveiling the Magic of Code Reasoning through Hypothesis Decomposition and Amendment

Do not write that jailbreak paper

Dynamic Gaussians Mesh: Consistent Mesh Reconstruction from Dynamic Scenes

It Helps to Take a Second Opinion: Teaching Smaller LLMs To Deliberate Mutually via Selective Rationale Optimisation

Symbolic regression via MDLformer-guided search: from minimizing prediction error to minimizing description length

Learning Partial Graph Matching via Optimal Partial Transport

ComLoRA: A Competitive Learning Approach for Enhancing LoRA

Learnable Expansion of Graph Operators for Multi-Modal Feature Fusion

MTSAM: Multi-Task Fine-Tuning for Segment Anything Model

HeadMap: Locating and Enhancing Knowledge Circuits in LLMs

Learning to Explore and Exploit with GNNs for Unsupervised Combinatorial Optimization

Trajectory-Class-Aware Multi-Agent Reinforcement Learning

Generalized Video Moment Retrieval

Modeling Unseen Environments with Language-guided Composable Causal Components in Reinforcement Learning

HiRA: Parameter-Efficient Hadamard High-Rank Adaptation for Large Language Models

Sharpness-Aware Black-Box Optimization

Better Instruction-Following Through Minimum Bayes Risk

AFlow: Automating Agentic Workflow Generation

Long-Short Decision Transformer: Bridging Global and Local Dependencies for Generalized Decision-Making

Training-free LLM-generated Text Detection by Mining Token Probability Sequences

Leveraging Driver Field-of-View for Multimodal Ego-Trajectory Prediction

Collab: Controlled Decoding using Mixture of Agents for LLM Alignment

VL-Cache: Sparsity and Modality-Aware KV Cache Compression for Vision-Language Model Inference Acceleration

Joint Gradient Balancing for Data Ordering in Finite-Sum Multi-Objective Optimization

Advancing Out-of-Distribution Detection via Local Neuroplasticity

Hierarchically Encapsulated Representation for Protocol Design in Self-Driving Labs

RTop-K: Ultra-Fast Row-Wise Top-K Selection for Neural Network Acceleration on GPUs

The Journey Matters: Average Parameter Count over Pre-training Unifies Sparse and Dense Scaling Laws

Manifold Constraint Reduces Exposure Bias in Accelerated Diffusion Sampling

Scaling Wearable Foundation Models

Topological Zigzag Spaghetti for Diffusion-based Generation and Prediction on Graphs

Divergence of Neural Tangent Kernel in Classification Problems

SplatFormer: Point Transformer for Robust 3D Gaussian Splatting

The Optimization Landscape of SGD Across the Feature Learning Strength

Depth Any Video with Scalable Synthetic Data

Learning Multi-Index Models with Neural Networks via Mean-Field Langevin Dynamics

DOPL: Direct Online Preference Learning for Restless Bandits with Preference Feedback

SynQ: Accurate Zero-shot Quantization by Synthesis-aware Fine-tuning

Sensitivity-Aware Amortized Bayesian Inference

Combining Induction and Transduction for Abstract Reasoning

How DNNs break the Curse of Dimensionality: Compositionality and Symmetry Learning

LLM Unlearning via Loss Adjustment with Only Forget Data

Topograph: An Efficient Graph-Based Framework for Strictly Topology Preserving Image Segmentation

Scale-aware Recognition in Satellite Images under Resource Constraints

KGARevion: An AI Agent for Knowledge-Intensive Biomedical QA

Measuring memorization in RLHF for code completion

Denoising Levy Probabilistic Models

Why In-Context Learning Models are Good Few-Shot Learners?

Boltzmann-Aligned Inverse Folding Model as a Predictor of Mutational Effects on Protein-Protein Interactions

Co$^{\mathbf{3}}$Gesture: Towards Coherent Concurrent Co-speech 3D Gesture Generation with Interactive Diffusion

Latent Action Pretraining from Videos

Improving Generalization and Robustness in SNNs Through Signed Rate Encoding and Sparse Encoding Attacks

Event-Driven Online Vertical Federated Learning

Do WGANs succeed because they minimize the Wasserstein Distance? Lessons from Discrete Generators

Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs

Training Free Exponential Context Extension via Cascading KV Cache

Mixture Compressor for Mixture-of-Experts LLMs Gains More

A Training-Free Sub-quadratic Cost Transformer Model Serving Framework with Hierarchically Pruned Attention

Transformers Handle Endogeneity in In-Context Linear Regression

Language-Assisted Feature Transformation for Anomaly Detection

Training Language Models on Synthetic Edit Sequences Improves Code Synthesis

MOFFlow: Flow Matching for Structure Prediction of Metal-Organic Frameworks

BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games

The Illustrated AlphaFold

Noise-conditioned Energy-based Annealed Rewards (NEAR): A Generative Framework for Imitation Learning from Observation

Improved Convergence Rate for Diffusion Probabilistic Models

Probing the Latent Hierarchical Structure of Data via Diffusion Models

SymDiff: Equivariant Diffusion via Stochastic Symmetrisation

Prediction Risk and Estimation Risk of the Ridgeless Least Squares Estimator under General Assumptions on Regression Errors

L3Ms — Lagrange Large Language Models

Learning High-Degree Parities: The Crucial Role of the Initialization

Learning to Contextualize Web Pages for Enhanced Decision Making by LLM Agents

Microcanonical Langevin Ensembles: Advancing the Sampling of Bayesian Neural Networks

TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separation

A Watermark for Order-Agnostic Language Models

Efficient Neuron Segmentation in Electron Microscopy by Affinity-Guided Queries

ADBM: Adversarial Diffusion Bridge Model for Reliable Adversarial Purification

LoLCATs: On Low-Rank Linearizing of Large Language Models

DynAlign: Unsupervised Dynamic Taxonomy Alignment for Cross-Domain Segmentation

On Conformal Isometry of Grid Cells: Learning Distance-Preserving Position Embedding

Amortized Control of Continuous State Space Feynman-Kac Model for Irregular Time Series

DS-LLM: Leveraging Dynamical Systems to Enhance Both Training and Inference of Large Language Models

Interpreting Emergent Planning in Model-Free Reinforcement Learning

Robust Weight Initialization for Tanh Neural Networks with Fixed Point Analysis

Diff-PIC: Revolutionizing Particle-In-Cell Nuclear Fusion Simulation with Diffusion Models

Effective post-training embedding compression via temperature control in contrastive training

SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networks

In vivo cell-type and brain region classification via multimodal contrastive learning

Spectral-Refiner: Accurate Fine-Tuning of Spatiotemporal Fourier Neural Operator for Turbulent Flows

LucidPPN: Unambiguous Prototypical Parts Network for User-centric Interpretable Computer Vision

DeepLTL: Learning to Efficiently Satisfy Complex LTL Specifications for Multi-Task RL

FlashRNN: I/O-Aware Optimization of Traditional RNNs on modern hardware

TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters

Vision-LSTM: xLSTM as Generic Vision Backbone

MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark

Efficiently Parameterized Neural Metriplectic Systems

MatExpert: Decomposing Materials Discovery By Mimicking Human Experts

VAE-Var: Variational Autoencoder-Enhanced Variational Methods for Data Assimilation in Meteorology

Neural Stochastic Differential Equations for Uncertainty-Aware Offline RL

Stiefel Flow Matching for Moment-Constrained Structure Elucidation

Robust Root Cause Diagnosis using In-Distribution Interventions

CSA: Data-efficient Mapping of Unimodal Features to Multimodal Features

Efficient and Robust Neural Combinatorial Optimization via Wasserstein-Based Coresets

Safety-Prioritizing Curricula for Constrained Reinforcement Learning

Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs

Benchmarking LLMs' Judgments with No Gold Standard

UIFace: Unleashing Inherent Model Capabilities to Enhance Intra-Class Diversity in Synthetic Face Recognition

LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior

Transformers Provably Learn Two-Mixture of Linear Classification via Gradient Flow

Forewarned is Forearmed: Harnessing LLMs for Data Synthesis via Failure-induced Exploration

CheapNet: Cross-attention on Hierarchical representations for Efficient protein-ligand binding Affinity Prediction

Provable Uncertainty Decomposition via Higher-Order Calibration

Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models

SePer: Measure Retrieval Utility Through The Lens Of Semantic Perplexity Reduction

A Generic Framework for Conformal Fairness

Representative Guidance: Diffusion Model Sampling with Coherence

Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment

Swiss Army Knife: Synergizing Biases in Knowledge from Vision Foundation Models for Multi-Task Learning

Optimizing importance weighting in the presence of sub-population shifts

Synthesizing Realistic fMRI: A Physiological Dynamics-Driven Hierarchical Diffusion Model for Efficient fMRI Acquisition

Logical Consistency of Large Language Models in Fact-Checking

ProtComposer: Compositional Protein Structure Generation with 3D Ellipsoids

TAU-106K: A New Dataset for Comprehensive Understanding of Traffic Accident

Conditional Diffusion Models are Minimax-Optimal and Manifold-Adaptive for Conditional Distribution Estimation

CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs

HARDMath: A Benchmark Dataset for Challenging Problems in Applied Mathematics

Multimodal Lego: Model Merging and Fine-Tuning Across Topologies and Modalities in Biomedicine

Intent3D: 3D Object Detection in RGB-D Scans Based on Human Intention

Elliptic Loss Regularization

Tuning-Free Bilevel Optimization: New Algorithms and Convergence Analysis

How to visualize training dynamics in neural networks

Progressive Compression with Universally Quantized Diffusion Models

AstroCompress: A benchmark dataset for multi-purpose compression of astronomical data

Private Mechanism Design via Quantile Estimation

SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation

Implicit Bias of Mirror Flow for Shallow Neural Networks in Univariate Regression

Multi-Label Test-Time Adaptation with Bound Entropy Minimization

Subtask-Aware Visual Reward Learning from Segmented Demonstrations

Slot-Guided Adaptation of Pre-trained Diffusion Models for Object-Centric Learning and Compositional Generation

Trusted Multi-View Classification via Evolutionary Multi-View Fusion

Federated Residual Low-Rank Adaption of Large Language Models

Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural Networks

On the Importance of Language-driven Representation Learning for Heterogeneous Federated Learning

Pareto Prompt Optimization

Revisiting Random Walks for Learning on Graphs

Algorithmic Stability Based Generalization Bounds for Adversarial Training

A Generalist Hanabi Agent

WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning

Following the Human Thread in Social Navigation

Population Transformer: Learning Population-level Representations of Neural Activity

Strategist: Self-improvement of LLM Decision Making via Bi-Level Tree Search

CoTFormer: A Chain of Thought Driven Architecture with Budget-Adaptive Computation Cost at Inference

LancBiO: Dynamic Lanczos-aided Bilevel Optimization via Krylov Subspace

ReAttention: Training-Free Infinite Context with Finite Attention Scope

PCNN: Probable-Class Nearest-Neighbor Explanations Improve Fine-Grained Image Classification Accuracy for AIs and Humans

Bringing NeRFs to the Latent Space: Inverse Graphics Autoencoder

Matrix Product Sketching via Coordinated Sampling

Uncovering Latent Memories in Large Language Models

PIORF: Physics-Informed Ollivier-Ricci Flow for Long–Range Interactions in Mesh Graph Neural Networks

Learning Spatiotemporal Dynamical Systems from Point Process Observations

NeRAF: 3D Scene Infused Neural Radiance and Acoustic Fields

TimeInf: Time Series Data Contribution via Influence Functions

Trivialized Momentum Facilitates Diffusion Generative Modeling on Lie Groups

Multi-Field Adaptive Retrieval

Diffusion Generative Modeling for Spatially Resolved Gene Expression Inference from Histology Images

Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements

Learning General-purpose Biomedical Volume Representations using Randomized Synthesis

Context Steering: Controllable Personalization at Inference Time

Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward Pass

ST-GCond: Self-supervised and Transferable Graph Dataset Condensation

Asynchronous Federated Reinforcement Learning with Policy Gradient Updates: Algorithm Design and Convergence Analysis

A new framework for evaluating model out-of-distribution generalisation for the biochemical domain

Think Thrice Before You Act: Progressive Thought Refinement in Large Language Models

Multiplicative Logit Adjustment Approximates Neural-Collapse-Aware Decision Boundary Adjustment

Improving Equivariant Networks with Probabilistic Symmetry Breaking

Duoduo CLIP: Efficient 3D Understanding with Multi-View Images

Conformal Structured Prediction

Straightness of Rectified Flow: A Theoretical Insight into Wasserstein Convergence

Rare event modeling with self-regularized normalizing flows: what can we learn from a single failure?

Adaptive Pruning of Pretrained Transformer via Differential Inclusions

Optimal Non-Asymptotic Rates of Value Iteration for Average-Reward Markov Decision Processes

SmartRAG: Jointly Learn RAG-Related Tasks From the Environment Feedback

SOREL: A Stochastic Algorithm for Spectral Risks Minimization

Controlling Language and Diffusion Models by Transporting Activations

TopoDiffusionNet: A Topology-aware Diffusion Model

Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates

FairDen: Fair Density-Based Clustering

Diffusion Models are Evolutionary Algorithms

OATS: Outlier-Aware Pruning Through Sparse and Low Rank Decomposition

Discrete Copula Diffusion

RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment

Learn hybrid prototypes for multivariate time series anomaly detection

Efficient Biological Data Acquisition through Inference Set Design

MetaOOD: Automatic Selection of OOD Detection Models

Transformer Block Coupling and its Correlation with Generalization in LLMs

Collapsed Language Models Promote Fairness

Glauber Generative Model: Discrete Diffusion Models via Binary Classification

SMITE: Segment Me In TimE

Privacy-Preserving Personalized Federated Prompt Learning for Multimodal Large Language Models

LLaMaFlex: Many-in-one LLMs via Generalized Pruning and Weight Sharing

Once-for-All: Controllable Generative Image Compression with Dynamic Granularity Adaptation

Generative Monoculture in Large Language Models

ClassDiffusion: More Aligned Personalization Tuning with Explicit Class Guidance

Image and Video Tokenization with Binary Spherical Quantization

Training Robust Ensembles Requires Rethinking Lipschitz Continuity

MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion

Distilling Structural Representations into Protein Sequence Models

Motion-Agent: A Conversational Framework for Human Motion Generation with LLMs

COPER: Correlation-based Permutations for Multi-View Clustering

MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding

KinPFN: Bayesian Approximation of RNA Folding Kinetics using Prior-Data Fitted Networks

SMT: Fine-Tuning Large Language Models with Sparse Matrices

Provence: efficient and robust context pruning for retrieval-augmented generation

Long-Context Linear System Identification

Spectro-Riemannian Graph Neural Networks

Efficient Evolutionary Search Over Chemical Space with Large Language Models

Efficient Sparse PCA via Block-Diagonalization

Chain-of-region: Visual Language Models Need Details for Diagram Analysis

Reasoning of Large Language Models over Knowledge Graphs with Super-Relations

Aligned LLMs Are Not Aligned Browser Agents

SiMHand: Mining Similar Hands for Large-Scale 3D Hand Pose Pre-training

Minimal Impact ControlNet: Advancing Multi-ControlNet Integration

Unbounded: A Generative Infinite Game of Character Life Simulation

Noise Stability Optimization for Finding Flat Minima: A Hessian-based Regularization Approach

Three-in-One: Fast and Accurate Transducer for Hybrid-Autoregressive ASR

Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens

A Unified Framework for Forward and Inverse Problems in Subsurface Imaging using Latent Space Translations

Interference Among First-Price Pacing Equilibria: A Bias and Variance Analysis

MAGE: Model-Level Graph Neural Networks Explanations via Motif-based Graph Generation

Transformers Struggle to Learn to Search

Adversarial Latent Feature Augmentation for Fairness

Simple Guidance Mechanisms for Discrete Diffusion Models

Layer Swapping for Zero-Shot Cross-Lingual Transfer in Large Language Models

Improved Finite-Particle Convergence Rates for Stein Variational Gradient Descent

Learning Randomized Algorithms with Transformers

Encryption-Friendly LLM Architecture

Bonsai: Gradient-free Graph Condensation for Node Classification

Sensitivity Verification for Additive Decision Tree Ensembles

Can LLMs Really Learn to Translate a Low-Resource Language from One Grammar Book?

An Undetectable Watermark for Generative Image Models

Diffusion Models and Gaussian Flow Matching: Two Sides of the Same Coin

Differentiable Causal Discovery for Latent Hierarchical Causal Models

On the Relation between Trainability and Dequantization of Variational Quantum Learning Models

Sketching for Convex and Nonconvex Regularized Least Squares with Sharp Guarantees

Lawma: The Power of Specialization for Legal Annotation

Fengbo: a Clifford Neural Operator pipeline for 3D PDEs in Computational Fluid Dynamics

Problem-Parameter-Free Federated Learning

Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs

LoRA-X: Bridging Foundation Models with Training-Free Cross-Model Adaptation

Beyond FVD: An Enhanced Evaluation Metrics for Video Generation Distribution Quality

Dual Process Learning: Controlling Use of In-Context vs. In-Weights Strategies with Weight Forgetting

VOILA: Evaluation of MLLMs For Perceptual Understanding and Analogical Reasoning

Differentiable Optimization of Similarity Scores Between Models and Brains

Progressive distillation induces an implicit curriculum

Enhanced Diffusion Sampling via Extrapolation with Multiple ODE Solutions

McEval: Massively Multilingual Code Evaluation

E(n) Equivariant Topological Neural Networks

Tell me about yourself: LLMs are aware of their learned behaviors

Conformal Language Model Reasoning with Coherent Factuality

Better than Your Teacher: LLM Agents that learn from Privileged AI Feedback

Finding and Only Finding Differential Nash Equilibria by Both Pretending to be a Follower

TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning

CarbonSense: A Multimodal Dataset and Baseline for Carbon Flux Modelling

On the Inherent Privacy Properties of Discrete Denoising Diffusion Models

Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It

Self-Improving Robust Preference Optimization

NatureLM-audio: an Audio-Language Foundation Model for Bioacoustics

Synthio: Augmenting Small-Scale Audio Classification Datasets with Synthetic Data

Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching

Fugatto 1: Foundational Generative Audio Transformer Opus 1

Gumbel Counterfactual Generation From Language Models

Linear Representations of Political Perspective Emerge in Large Language Models

Looking Backward: Streaming Video-to-Video Translation with Feature Banks

Why Does the Effective Context Length of LLMs Fall Short?

Weighted Multi-Prompt Learning with Description-free Large Language Model Distillation

Dobi-SVD: Differentiable SVD for LLM Compression and Some New Perspectives

Pitfalls of Evidence-Based AI Policy

Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation

Towards Understanding Text Hallucination of Diffusion Models via Local Generation Bias

Model-Agnostic Knowledge Guided Correction for Improved Neural Surrogate Rollout

Learning Splitting Heuristics in Divide-and-Conquer SAT Solvers with Reinforcement Learning

Singular Subspace Perturbation Bounds via Rectangular Random Matrix Diffusions

Decoding Game: On Minimax Optimality of Heuristic Text Generation Strategies

Leveraging Variable Sparsity to Refine Pareto Stationarity in Multi-Objective Optimization

Stochastic Bandits Robust to Adversarial Attacks

Model-Free Offline Reinforcement Learning with Enhanced Robustness

Efficient stagewise pretraining via progressive subnetworks

A Multi-Power Law for Loss Curve Prediction Across Learning Rate Schedules

SONICS: Synthetic Or Not - Identifying Counterfeit Songs

Behavioral Entropy-Guided Dataset Generation for Offline Reinforcement Learning

Learned Reference-based Diffusion Sampler for multi-modal distributions

PolaFormer: Polarity-aware Linear Attention for Vision Transformers

BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation Experiments

Effective Interplay between Sparsity and Quantization: From Theory to Practice

On the Convergence of No-Regret Dynamics in Information Retrieval Games with Proportional Ranking Functions

Diffusion Models as Cartoonists: The Curious Case of High Density Regions

Fine-Tuning Attention Modules Only: Enhancing Weight Disentanglement in Task Arithmetic

ForecastBench: A Dynamic Benchmark of AI Forecasting Capabilities

Generalization and Distributed Learning of GFlowNets

ToolGen: Unified Tool Retrieval and Calling via Generation

Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient

WardropNet: Traffic Flow Predictions via Equilibrium-Augmented Learning

When do GFlowNets learn the right distribution?

CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking

Equivariant Denoisers Cannot Copy Graphs: Align Your Graph Diffusion Models

Towards a Complete Logical Framework for GNN Expressiveness

Improving Semantic Understanding in Speech Language Models via Brain-tuning

Perplexed by Perplexity: Perplexity-Based Data Pruning With Small Reference Models

ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQL

Efficient and Context-Aware Label Propagation for Zero-/Few-Shot Training-Free Adaptation of Vision-Language Model

Scaling Laws for Precision

Human-inspired Episodic Memory for Infinite Context LLMs

Rethinking Shapley Value for Negative Interactions in Non-convex Games

MeteoRA: Multiple-tasks Embedded LoRA for Large Language Models

Matérn Kernels for Tunable Implicit Surface Reconstruction

Brain-inspired $L_p$-Convolution benefits large kernels and aligns better with visual cortex

In Search of the Engram in LLMs: A Neuroscience Perspective on the Memory Functions in AI Models

GLoRa: A Benchmark to Evaluate the Ability to Learn Long-Range Dependencies in Graphs

Progress or Regress? Self-Improvement Reversal in Post-training

MAESTRO: Masked Encoding Set Transformer with Self-Distillation

dEBORA: Efficient Bilevel Optimization-based low-Rank Adaptation

DataEnvGym: Data Generation Agents in Teacher Environments with Student Feedback

Endless Jailbreaks with Bijection Learning

Multi-session, multi-task neural decoding from distinct cell-types and brain regions

Towards Multiple Character Image Animation Through Enhancing Implicit Decoupling

Offline Model-Based Optimization by Learning to Rank

Open-CK: A Large Multi-Physics Fields Coupling benchmarks in Combustion Kinetics

Self-Improvement in Language Models: The Sharpening Mechanism

RecDreamer: Consistent Text-to-3D Generation via Uniform Score Distillation

Nonasymptotic Analysis of Stochastic Gradient Descent with the Richardson–Romberg Extrapolation

CameraCtrl: Enabling Camera Control for Video Diffusion Models

RoboCat: A Self-Improving Generalist Agent for Robotic Manipulation

Feature-Based Online Bilateral Trade

DiffSplat: Repurposing Image Diffusion Models for Scalable Gaussian Splat Generation

Layout-your-3D: Controllable and Precise 3D Generation with 2D Blueprint

No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images

Comparing Targeting Strategies for Maximizing Social Welfare with Limited Resources

Dynamic Sparse Training versus Dense Training: The Unexpected Winner in Image Corruption Robustness

MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models

MotionClone: Training-Free Motion Cloning for Controllable Video Generation

Systematic Relational Reasoning With Epistemic Graph Neural Networks

CapeX: Category-Agnostic Pose Estimation from Textual Point Explanation

System 1.x: Learning to Balance Fast and Slow Planning with Language Models

LLM-wrapper: Black-Box Semantic-Aware Adaptation of Vision-Language Models for Referring Expression Comprehension

Understanding the Generalization of In-Context Learning in Transformers: An Empirical Study

Halton Scheduler for Masked Generative Image Transformer

Continuity-Preserving Convolutional Autoencoders for Learning Continuous Latent Dynamical Models from Images

$\sigma$-zero: Gradient-based Optimization of $\ell_0$-norm Adversarial Examples

pMoE: Prompting Diverse Experts Together Wins More in Visual Adaptation

Comparing noisy neural population dynamics using optimal transport distances

Physics-Informed Deep Inverse Operator Networks for Solving PDE Inverse Problems

ALLaM: Large Language Models for Arabic and English

ParFam -- (Neural Guided) Symbolic Regression via Continuous Global Optimization

OSDA Agent: Leveraging Large Language Models for De Novo Design of Organic Structure Directing Agents

Progressive Compositionality in Text-to-Image Generative Models

Analyzing and Boosting the Power of Fine-Grained Visual Recognition for Multi-modal Large Language Models

Learning to engineer protein flexibility

OmniPhysGS: 3D Constitutive Gaussians for General Physics-Based Dynamics Generation

Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation

ACES: Automatic Cohort Extraction System for Event-Stream Datasets

Learning multi-modal generative models with permutation-invariant encoders and tighter variational objectives

To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning

RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation

GRAIN: Exact Graph Reconstruction from Gradients

Synergy and Diversity in CLIP: Enhancing Performance Through Adaptive Backbone Ensembling

Diff-2-in-1: Bridging Generation and Dense Perception with Diffusion Models

Gradient descent with generalized Newton’s method

Methods for Convex $(L_0,L_1)$-Smooth Optimization: Clipping, Acceleration, and Adaptivity

Exposing and Addressing Cross-Task Inconsistency in Unified Vision-Language Models

PeriodWave: Multi-Period Flow Matching for High-Fidelity Waveform Generation

Nesterov acceleration in benignly non-convex landscapes

Towards hyperparameter-free optimization with differential privacy

MMAD: A Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly Detection

See It from My Perspective: How Language Affects Cultural Bias in Image Understanding

LevAttention: Time, Space and Streaming Efficient Algorithm for Heavy Attentions

Ctrl-Adapter: An Efficient and Versatile Framework for Adapting Diverse Controls to Any Diffusion Model

From Attention to Activation: Unraveling the Enigmas of Large Language Models

Generative Inbetweening: Adapting Image-to-Video Models for Keyframe Interpolation

Long-time asymptotics of noisy SVGD outside the population limit

MamKO: Mamba-based Koopman operator for modeling and predictive control

FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Streaming Algorithms For $\ell_p$ Flows and $\ell_p$ Regression

MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs

Improving the Sparse Structure Learning of Spiking Neural Networks from the View of Compression Efficiency

A Theory for Token-Level Harmonization in Retrieval-Augmented Generation

Emergence of a High-Dimensional Abstraction Phase in Language Transformers

Model merging with SVD to tie the Knots

Temporal Reasoning Transfer from Text to Video

Revealing the 3D Cosmic Web through Gravitationally Constrained Neural Fields

Peeking Behind Closed Doors: Risks of LLM Evaluation by Private Data Curators

Reassessing EMNLP 2024’s Best Paper: Does Divergence-Based Calibration for MIAs Hold Up?

Mining your own secrets: Diffusion Classifier Scores for Continual Personalization of Text-to-Image Diffusion Models

Herald: A Natural Language Annotated Lean 4 Dataset

SoftCVI: Contrastive variational inference with self-generated soft labels

ContraDiff: Planning Towards High Return States via Contrastive Learning

Class Distribution-induced Attention Map for Open-vocabulary Semantic Segmentations

Concept Pinpoint Eraser for Text-to-image Diffusion Models via Residual Attention Gate

Rethinking Fair Representation Learning for Performance-Sensitive Tasks

Reconstruction-Guided Policy: Enhancing Decision-Making through Agent-Wise State Consistency

BOFormer: Learning to Solve Multi-Objective Bayesian Optimization via Non-Markovian RL

From Probability to Counterfactuals: the Increasing Complexity of Satisfiability in Pearl's Causal Hierarchy

Exploring The Loss Landscape Of Regularized Neural Networks Via Convex Duality

Reasoning Elicitation in Language Models via Counterfactual Feedback

TSVD: Bridging Theory and Practice in Continual Learning with Pre-trained Models

InCoDe: Interpretable Compressed Descriptions For Image Generation

Coreset Spectral Clustering

ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation Grounding

Diffusion Attribution Score: Evaluating Training Data Influence in Diffusion Models

Efficient and Accurate Explanation Estimation with Distribution Compression

Fundamental Limitations on Subquadratic Alternatives to Transformers

Latent-EnSF: A Latent Ensemble Score Filter for High-Dimensional Data Assimilation with Sparse Observation Data

A Meta-Learning Approach to Bayesian Causal Discovery

Start Smart: Leveraging Gradients For Enhancing Mask-based XAI Methods

Learning Chaos In A Linear Way

Improving Instruction-Following in Language Models through Activation Steering

Unearthing Skill-level Insights for Understanding Trade-offs of Foundation Models

Union-over-Intersections: Object Detection beyond Winner-Takes-All

Compositional Entailment Learning for Hyperbolic Vision-Language Models

Implicit Neural Surface Deformation with Explicit Velocity Fields

Intelligence at the Edge of Chaos

Multimodal Situational Safety

Analysing The Spectral Biases in Generative Models

Learning to Communicate Through Implicit Communication Channels

Discrete GCBF Proximal Policy Optimization for Multi-agent Safe Optimal Control

Learning Continually by Spectral Regularization

MGDA Converges under Generalized Smoothness, Provably

Boundary constrained Gaussian processes for robust physics-informed machine learning of linear partial differential equations

Multi-Task Dense Predictions via Unleashing the Power of Diffusion

Law of the Weakest Link: Cross Capabilities of Large Language Models

InvestESG: A multi-agent reinforcement learning benchmark for studying climate investment as a social dilemma

Bayesian Regularization of Latent Representation

Boosting Ray Search Procedure of Hard-label Attacks with Transfer-based Priors

BOND: Aligning LLMs with Best-of-N Distillation

Can LLMs Solve Longer Math Word Problems Better?

UGMathBench: A Diverse and Dynamic Benchmark for Undergraduate-Level Mathematical Reasoning with Large Language Models

Can Knowledge Editing Really Correct Hallucinations?

Improving Uncertainty Estimation through Semantically Diverse Language Generation

F-Fidelity: A Robust Framework for Faithfulness Evaluation of Explainable AI

Auto-GDA: Automatic Domain Adaptation for Efficient Grounding Verification in Retrieval-Augmented Generation

Evaluating Large Language Models through Role-Guide and Self-Reflection: A Comparative Study

Stochastic Semi-Gradient Descent for Learning Mean Field Games with Population-Aware Function Approximation

Solving Differential Equations with Constrained Learning

Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning

On Generalization Across Environments In Multi-Objective Reinforcement Learning

TASAR: Transfer-based Attack on Skeletal Action Recognition

Diffusion Policy Policy Optimization

Optimizing Posterior Samples for Bayesian Optimization via Rootfinding

DEPfold: RNA Secondary Structure Prediction as Dependency Parsing.

Open-Source vs Close-Source: The Context Utilization Challenge

Aria-MIDI: A Dataset of Piano MIDI Files for Symbolic Music Modeling

Enhancing Language Model Agents using Diversity of Thoughts

Variational Bayesian Pseudo-Coreset

ThinK: Thinner Key Cache by Query-Driven Pruning

Actions Speak Louder Than Words: Rate-Reward Trade-off in Markov Decision Processes

Efficient Inference for Large Language Model-based Generative Recommendation

Scaling up the Banded Matrix Factorization Mechanism for Large Scale Differentially Private ML

NetMoE: Accelerating MoE Training through Dynamic Sample Placement

Adversarial Machine Unlearning

Storybooth: Training-Free Multi-Subject Consistency for Improved Visual Storytelling

Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing

Morphing Tokens Draw Strong Masked Image Models

BoneMet: An Open Large-Scale Multi-Modal Murine Dataset for Breast Cancer Bone Metastasis Diagnosis and Prognosis

Adaptive Camera Sensor for Vision Models

Nonlinear multiregion neural dynamics with parametric impulse response communication channels

DELIFT: Data Efficient Language model Instruction Fine-Tuning

On the Almost Sure Convergence of the Stochastic Three Points Algorithm

On-the-fly Preference Alignment via Principle-Guided Decoding

Normed Spaces for Graph Embedding

Asymptotic Analysis of Two-Layer Neural Networks after One Gradient Step under Gaussian Mixtures Data with Structure

Dataset Ownership Verification in Contrastive Pre-trained Models

Equivariant Symmetry Breaking Sets

Size-Generalizable RNA Structure Evaluation by Exploring Hierarchical Geometries

Semialgebraic Neural Networks: From roots to representations

Geometry-aware RL for Manipulation of Varying Shapes and Deformable Objects

Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulation

Nova: Generative Language Models for Assembly Code with Hierarchical Attention and Contrastive Learning

Towards Synergistic Path-based Explanations for Knowledge Graph Completion: Exploration and Evaluation

Build-A-Scene: Interactive 3D Layout Control for Diffusion-Based Image Generation

Flow matching achieves almost minimax optimal convergence

LaGeM: A Large Geometry Model for 3D Representation Learning and Diffusion

Direct Distributional Optimization for Provable Alignment of Diffusion Models

Enabling Realtime Reinforcement Learning at Scale with Staggered Asynchronous Inference

Causal Concept Graph Models: Beyond Causal Opacity in Deep Learning

ADAPT: Attentive Self-Distillation and Dual-Decoder Prediction Fusion for Continual Panoptic Segmentation

Learning to Steer Markovian Agents under Model Uncertainty

PvNeXt: Rethinking Network Design and Temporal Motion for Point Cloud Video Recognition

Flow With What You Know

KLay: Accelerating Arithmetic Circuits for Neurosymbolic AI

Difference-of-submodular Bregman Divergence

Transformers are Universal In-context Learners

Differential learning kinetics govern the transition from memorization to generalization during in-context learning

MMDisCo: Multi-Modal Discriminator-Guided Cooperative Diffusion for Joint Audio and Video Generation

Improving Convergence Guarantees of Random Subspace Second-order Algorithm for Nonconvex Optimization

GameGen-X: Interactive Open-world Game Video Generation

Attention in Large Language Models Yields Efficient Zero-Shot Re-Rankers

DexTrack: Towards Generalizable Neural Tracking Control for Dexterous Manipulation from Human References

ContextGNN: Beyond Two-Tower Recommendation Systems

Machine Unlearning Fails to Remove Data Poisoning Attacks

SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning

Vector-ICL: In-context Learning with Continuous Vector Representations

TabM: Advancing tabular deep learning with parameter-efficient ensembling

Fourier Sliced-Wasserstein Embedding for Multisets and Measures

Minimax Optimal Reinforcement Learning with Quasi-Optimism

EffoVPR: Effective Foundation Model Utilization for Visual Place Recognition

RFMamba: Frequency-Aware State Space Model for RF-Based Human-Centric Perception

EC-Diffuser: Multi-Object Manipulation via Entity-Centric Behavior Generation

Demystifying Topological Message-Passing with Relational Structures: A Case Study on Oversquashing in Simplicial Message-Passing

Revealing and Mitigating Over-Attention in Knowledge Editing

SCOPE: A Self-supervised Framework for Improving Faithfulness in Conditional Text Generation

SSLAM: Enhancing Self-Supervised Models with Audio Mixtures for Polyphonic Soundscapes

When narrower is better: the narrow width limit of Bayesian parallel branching neural networks

MeshMask: Physics-Based Simulations with Masked Graph Neural Networks

Scalable Universal T-Cell Receptor Embeddings from Adaptive Immune Repertoires

Improved Algorithms for Kernel Matrix-Vector Multiplication Under Sparsity Assumptions

Neural Exploratory Landscape Analysis for Meta-Black-Box-Optimization

NextBestPath: Efficient 3D Mapping of Unseen Environments

Safety Representations for Safer Policy Learning

Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning

MotherNet: Fast Training and Inference via Hyper-Network Transformers

No Preference Left Behind: Group Distributional Preference Optimization

RankSHAP: Shapley Value Based Feature Attributions for Learning to Rank

Optimistic Games for Combinatorial Bayesian Optimization with Application to Protein Design

POGEMA: A Benchmark Platform for Cooperative Multi-Agent Pathfinding

Physiome-ODE: A Benchmark for Irregularly Sampled Multivariate Time-Series Forecasting Based on Biological ODEs

Agent-Oriented Planning in Multi-Agent Systems

Differentially private learners for heterogeneous treatment effects

Probabilistic Conformal Prediction with Approximate Conditional Validity

STRAP: Robot Sub-Trajectory Retrieval for Augmented Policy Learning

Meta-Dynamical State Space Models for Integrative Neural Data Analysis

Diffusion Transformer Captures Spatial-Temporal Dependencies: A Theory for Gaussian Process Data

Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling

Provable Convergence Bounds for Hybrid Dynamical Sampling and Optimization

Overcoming Slow Decision Frequencies in Continuous Control: Model-Based Sequence Reinforcement Learning for Model-Free Control

A Rainbow in Deep Network Black Boxes

Large Scale Knowledge Washing

The Effectiveness of Curvature-Based Rewiring and the Role of Hyperparameters in GNNs Revisited

Building Interactable Replicas of Complex Articulated Objects via Gaussian Splatting

NUDGE: Lightweight Non-Parametric Fine-Tuning of Embeddings for Retrieval

ConFIG: Towards Conflict-free Training of Physics Informed Neural Networks

Multi-Dimensional Conformal Prediction

MorphoDiff: Cellular Morphology Painting with Diffusion Models

Generalization v.s. Memorization: Tracing Language Models’ Capabilities Back to Pretraining Data

On Linear Representations and Pretraining Data Frequency in Language Models

PN-GAIL: Leveraging Non-optimal Information from Imperfect Demonstrations

Exploring channel distinguishability in local neighborhoods of the model space in quantum neural networks

Rethinking Graph Neural Networks From A Geometric Perspective Of Node Features

InfoGS: Efficient Structure-Aware 3D Gaussians via Lightweight Information Shaping

GI-GS: Global Illumination Decomposition on Gaussian Splatting for Inverse Rendering

IV-mixed Sampler: Leveraging Image Diffusion Models for Enhanced Video Synthesis

Animate Your Thoughts: Reconstruction of Dynamic Natural Vision from Human Brain Activity

Unified Parameter-Efficient Unlearning for LLMs

Breaking Mental Set to Improve Reasoning through Diverse Multi-Agent Debate

Consistency Checks for Language Model Forecasters

Multi-objective Differentiable Neural Architecture Search

Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues

uniINF: Best-of-Both-Worlds Algorithm for Parameter-Free Heavy-Tailed MABs

Quantitative Approximation for Neural Operators in Nonlinear Parabolic Equations

Neural Interactive Proofs

RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models

OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code

CAX: Cellular Automata Accelerated in JAX

Sparse Autoencoders Reveal Temporal Difference Learning in Large Language Models

Modeling dynamic social vision highlights gaps between deep learning and humans

LLM-based Typed Hyperresolution for Commonsense Reasoning with Knowledge Bases

MoLEx: Mixture of Layer Experts for Fine-tuning with Sparse Upcycling

Generalization in VAE and Diffusion Models: A Unified Information-Theoretic Analysis

Transformer Meets Twicing: Harnessing Unattended Residual Information

RAG-SR: Retrieval-Augmented Generation for Neural Symbolic Regression

Unlocking Guidance for Discrete State-Space Diffusion and Flow Models

Causal Order: The Key to Leveraging Imperfect Experts in Causal Inference

INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge

Tight Clusters Make Specialized Experts

Facilitating Multi-turn Function Calling for LLMs via Compositional Instruction Tuning

CAMEx: Curvature-aware Merging of Experts

ClawMachine: Learning to Fetch Visual Tokens for Referential Comprehension

Distribution-Specific Agnostic Conditional Classification With Halfspaces

Last-Iterate Convergence Properties of Regret-Matching Algorithms in Games

Joint Reward and Policy Learning with Demonstrations and Human Feedback Improves Alignment

Learning to Discretize Denoising Diffusion ODEs

Divide and Translate: Compositional First-Order Logic Translation and Verification for Complex Logical Reasoning

REBIND: Enhancing Ground-state Molecular Conformation Prediction via Force-Based Graph Rewiring

Token-Supervised Value Models for Enhancing Mathematical Problem-Solving Capabilities of Large Language Models

Test-Time Ensemble via Linear Mode Connectivity: A Path to Better Adaptation

Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control

Solving Token Gradient Conflict in Mixture-of-Experts for Large Vision-Language Model

TopoGaussian: Inferring Internal Topology Structures from Visual Clues

SonicSim: A customizable simulation platform for speech processing in moving sound source scenarios

Inverse Attention Agents for Multi-Agent Systems

ToddlerDiffusion: Interactive Structured Image Generation with Cascaded Schrödinger Bridge

SelectFormer in Data Markets: Privacy-Preserving and Efficient Data Selection for Transformers with Multi-Party Computation

Zeroth-Order Policy Gradient for Reinforcement Learning from Human Feedback without Reward Inference

Differentiable Rule Induction from Raw Sequence Inputs

Atlas Gaussians Diffusion for 3D Generation

Generalizing Reasoning Problems to Longer Lengths

Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Learn-by-interact: A Data-Centric Framework For Self-Adaptive Agents in Realistic Environments

Intrinsic User-Centric Interpretability through Global Mixture of Experts

RegMix: Data Mixture as Regression for Language Model Pre-training

Inner Information Analysis Algorithm for Deep Neural Network based on Community

Verifying Properties of Binary Neural Networks Using Sparse Polynomial Optimization

Scaling up Masked Diffusion Models on Text

GPUDrive: Data-driven, multi-agent driving simulation at 1 million FPS

On the Learn-to-Optimize Capabilities of Transformers in In-Context Sparse Recovery

Data-adaptive Differentially Private Prompt Synthesis for In-Context Learning

Optimal Flow Transport and its Entropic Regularization: a GPU-friendly Matrix Iterative Algorithm for Flow Balance Satisfaction

Semantics-Adaptive Activation Intervention for LLMs via Dynamic Steering Vectors

IDInit: A Universal and Stable Initialization Method for Neural Network Training

Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace

EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh Generation

Action Sequence Augmentation for Action Anticipation

IterGen: Iterative Semantic-aware Structured LLM Generation with Backtracking

ZETA: Leveraging $Z$-order Curves for Efficient Top-$k$ Attention

AnalogGenie: A Generative Engine for Automatic Discovery of Analog Circuit Topologies

The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD

Unified Convergence Analysis for Score-Based Diffusion Models with Deterministic Samplers

Near-Exact Privacy Amplification for Matrix Mechanisms

Selective Aggregation for Low-Rank Adaptation in Federated Learning

Adaptive Shrinkage Estimation for Personalized Deep Kernel Regression in Modeling Brain Trajectories

VTDexManip: A Dataset and Benchmark for Visual-tactile Pretraining and Dexterous Manipulation with Reinforcement Learning

GameArena: Evaluating LLM Reasoning through Live Computer Games

Learning to Select Nodes in Branch and Bound with Sufficient Tree Representation

Looking into User’s Long-term Interests through the Lens of Conservative Evidential Learning

SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction

Large-scale and Fine-grained Vision-language Pre-training for Enhanced CT Image Understanding

MarS: a Financial Market Simulation Engine Powered by Generative Foundation Model

Computational Explorations of Total Variation Distance

Presto! Distilling Steps and Layers for Accelerating Music Generation

TopoLM: brain-like spatio-functional organization in a topographic language model

Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs

Convex Formulations for Training Two-Layer ReLU Neural Networks

Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Grokking at the Edge of Numerical Stability

Accelerating Task Generalisation with Multi-Level Skill Hierarchies

SSOLE: Rethinking Orthogonal Low-rank Embedding for Self-Supervised Learning

Regretful Decisions under Label Noise

Large Convolutional Model Tuning via Filter Subspace

ACC-Collab: An Actor-Critic Approach to Multi-Agent LLM Collaboration

Improving Language Model Distillation through Hidden State Matching

Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization

Lightweight Neural App Control

Plastic Learning with Deep Fourier Features

A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement

DPaI: Differentiable Pruning at Initialization with Node-Path Balance Principle

Erasing Concept Combination from Text-to-Image Diffusion Model

Test-time Adaptation for Cross-modal Retrieval with Query Shift

What's the Move? Hybrid Imitation Learning via Salient Points

Metalic: Meta-Learning In-Context with Protein Language Models

Unlocking Global Optimality in Bilevel Optimization: A Pilot Study

GOPlan: Goal-conditioned Offline Reinforcement Learning by Planning with Learned Models

Balancing Act: Diversity and Consistency in Large Language Model Ensembles

What should a neuron aim for? Designing local objective functions based on information theory

Tackling Data Corruption in Offline Reinforcement Learning via Sequence Modeling

DynaMath: A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language Models

Fast Summation of Radial Kernels via QMC Slicing

DELTA: DENSE EFFICIENT LONG-RANGE 3D TRACKING FOR ANY VIDEO

Tailoring Mixup to Data for Calibration

Restyling Unsupervised Concept Based Interpretable Networks with Generative Models

BlendRL: A Framework for Merging Symbolic and Neural Policy Learning

MGMapNet: Multi-Granularity Representation Learning for End-to-End Vectorized HD Map Construction

MUSE: Machine Unlearning Six-Way Evaluation for Language Models

GMValuator: Similarity-based Data Valuation for Generative Models

On Evaluating the Durability of Safeguards for Open-Weight LLMs

Not All LLM-Generated Data Are Equal: Rethinking Data Weighting in Text Classification

LeanVec: Searching vectors faster by making them fit

HiBug2: Efficient and Interpretable Error Slice Discovery for Comprehensive Model Debugging

Gated Delta Networks: Improving Mamba2 with Delta Rule

No Free Lunch: Fundamental Limits of Learning Non-Hallucinating Generative Models

Efficient Dictionary Learning with Switch Sparse Autoencoders

Curriculum-aware Training for Discriminating Molecular Property Prediction Models

MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models

Trajectory attention for fine-grained video motion control

MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering

Surprising Effectiveness of pretraining Ternary Language Model at Scale

PARTNR: A Benchmark for Planning and Reasoning in Embodied Multi-agent Tasks

Rationalizing and Augmenting Dynamic Graph Neural Networks

Large Language Models can Become Strong Self-Detoxifiers

From Promise to Practice: Realizing High-performance Decentralized Training

Which Tasks Should Be Compressed Together? A Causal Discovery Approach for Efficient Multi-Task Representation Compression

High-Quality Joint Image and Video Tokenization with Causal VAE

ReGenesis: LLMs can Grow into Reasoning Generalists via Self-Improvement

Attribute-based Visual Reprogramming for Vision-Language Models

Maintaining Structural Integrity in Parameter Spaces for Parameter Efficient Fine-tuning

VideoPhy: Evaluating Physical Commonsense for Video Generation

Text-to-Image Rectified Flow as Plug-and-Play Priors

On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data Poisoning

Evidential Learning-based Certainty Estimation for Robust Dense Feature Matching

Long-Sequence Recommendation Models Need Decoupled Embeddings

Outlier Synthesis via Hamiltonian Monte Carlo for Out-of-Distribution Detection

Style Outweighs Substance: Failure Modes of LLM Judges in Alignment Benchmarking

AtomSurf: Surface Representation for Learning on Protein Structures

Policy Design in Long-run Welfare Dynamics

Controllable Satellite-to-Street-View Synthesis with Precise Pose Alignment and Zero-Shot Environmental Control

ImProver: Agent-Based Automated Proof Optimization

KAA: Kolmogorov-Arnold Attention for Enhancing Attentive Graph Neural Networks

Policy Gradient with Kernel Quadrature

Hydra-SGG: Hybrid Relation Assignment for One-stage Scene Graph Generation

DECO: Unleashing the Potential of ConvNets for Query-based Detection and Segmentation

A Theoretical Framework for Partially-Observed Reward States in RLHF

LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias

Global Convergence in Neural ODEs: Impact of Activation Functions

InstaTrain: Adaptive Training via Ultra-Fast Natural Annealing within Dynamical Systems

Repetition Improves Language Model Embeddings

SPA-BENCH: A COMPREHENSIVE BENCHMARK FOR SMARTPHONE AGENT EVALUATION

h4rm3l: A Language for Composable Jailbreak Attack Synthesis

Black-Box Detection of Language Model Watermarks

Merging LoRAs like Playing LEGO: Pushing the Modularity of LoRA to Extremes Through Rank-Wise Clustering

Optimizing Backward Policies in GFlowNets via Trajectory Likelihood Maximization

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment

Regulatory DNA Sequence Design with Reinforcement Learning

Learning Transformer-based World Models with Contrastive Predictive Coding

Decoupling Angles and Strength in Low-rank Adaptation

Variational Search Distributions

Interpretable Bilingual Multimodal Large Language Model for Diverse Biomedical Tasks

Stable Hadamard Memory: Revitalizing Memory-Augmented Agents for Reinforcement Learning

Building, Reusing, and Generalizing Abstract Representations from Concrete Sequences

DeeperForward: Enhanced Forward-Forward Training for Deeper and Better Performance

ELBOing Stein: Variational Bayes with Stein Mixture Inference

Revealing and Reducing Gender Biases in Vision and Language Assistants (VLAs)

SAMRefiner: Taming Segment Anything Model for Universal Mask Refinement

SVBench: A Benchmark with Temporal Multi-Turn Dialogues for Streaming Video Understanding

Spherical Tree-Sliced Wasserstein Distance

Distance-Based Tree-Sliced Wasserstein Distance

MAI: A Multi-turn Aggregation-Iteration Model for Composed Image Retrieval

Disentangled Representation Learning with the Gromov-Monge Gap

Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization

kNN Attention Demystified: A Theoretical Exploration for Scalable Transformers

Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers

Chunk-Distilled Language Modeling

u-$\mu$P: The Unit-Scaled Maximal Update Parametrization

Diffusion Models Are Real-Time Game Engines

Arithmetic Without Algorithms: Language Models Solve Math with a Bag of Heuristics

UV-Attack: Physical-World Adversarial Attacks on Person Detection via Dynamic-NeRF-based UV Mapping

Towards Unified Human Motion-Language Understanding via Sparse Interpretable Characterization

Efficient Low-Bit Quantization with Adaptive Scales for Multi-Task Co-Training

SelKD: Selective Knowledge Distillation via Optimal Transport Perspective

Regularizing Energy among Training Samples for Out-of-Distribution Generalization

Rethinking and Improving Autoformalization: Towards a Faithful Metric and a Dependency Retrieval-based Approach

Learning Structured Universe Graph with Outlier OOD Detection for Partial Matching

What Secrets Do Your Manifolds Hold? Understanding the Local Geometry of Generative Models

To Clip or not to Clip: the Dynamics of SGD with Gradient Clipping in High-Dimensions

Locality Alignment Improves Vision-Language Models

Robust LLM safeguarding via refusal feature adversarial training

UniCO: On Unified Combinatorial Optimization via Problem Reduction to Matrix-Encoded General TSP

Lasso Bandit with Compatibility Condition on Optimal Arm

Preference Elicitation for Offline Reinforcement Learning

Unify ML4TSP: Drawing Methodological Principles for TSP and Beyond from Streamlined Design Space of Learning and Search

Guaranteed Generation from Large Language Models

Forget the Data and Fine-Tuning! Just Fold the Network to Compress

Statistical Advantages of Perturbing Cosine Router in Mixture of Experts

Zero-Shot Natural Language Explanations

Learning Geometric Reasoning Networks For Robot Task And Motion Planning

Learning to Help in Multi-Class Settings

Variational Diffusion Posterior Sampling with Midpoint Guidance

Disentangling Representations through Multi-task Learning

Prompting Fairness: Integrating Causality to Debias Large Language Models

T-JEPA: Augmentation-Free Self-Supervised Learning for Tabular Data

Causal Discovery via Bayesian Optimization

Deep Incomplete Multi-view Learning via Cyclic Permutation of VAEs

Contrastive Learning from Synthetic Audio Doppelgängers

When Selection Meets Intervention: Additional Complexities in Causal Discovery

AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language Models

Dynamic Negative Guidance of Diffusion Models

Bilinear MLPs enable weight-based mechanistic interpretability

Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization

Direct Post-Training Preference Alignment for Multi-Agent Motion Generation Model Using Implicit Feedback from Pre-training Demonstrations

SaRA: High-Efficient Diffusion Model Fine-tuning with Progressive Sparse Low-Rank Adaptation

MediConfusion: Can you trust your AI radiologist? Probing the reliability of multimodal medical foundation models

AdaFisher: Adaptive Second Order Optimization via Fisher Information

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models

The Directionality of Optimization Trajectories in Neural Networks

Expressivity of Neural Networks with Random Weights and Learned Biases

Beyond Random Augmentations: Pretraining with Hard Views

Attention layers provably solve single-location regression

Fine-Tuning Token-Based Large Multimodal Models: What Works, What Doesn’t and What's Next

Lines of Thought in Large Language Models

Density estimation with LLMs: a geometric investigation of in-context learning trajectories

NEAR: A Training-Free Pre-Estimator of Machine Learning Model Performance

Training-Free Diffusion Model Alignment with Sampling Demons

The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities

Towards Certification of Uncertainty Calibration under Adversarial Attacks

Shh, don't say that! Domain Certification in LLMs

Revisiting Feature Prediction for Learning Visual Representations from Video

Simulating Human-like Daily Activities with Desire-driven Autonomy

Newton Meets Marchenko-Pastur: Massively Parallel Second-Order Optimization with Hessian Sketching and Debiasing

Theory, Analysis, and Best Practices for Sigmoid Self-Attention

Uncertainty-Aware Decoding with Minimum Bayes Risk

TopoNets: High performing vision and language models with brain-like topography

OptiBench Meets ReSocratic: Measure and Improve LLMs for Optimization Modeling

Hierarchical World Models as Visual Whole-Body Humanoid Controllers

Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced Reasoning

FormalAlign: Automated Alignment Evaluation for Autoformalization

LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics

Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF

PharmacoMatch: Efficient 3D Pharmacophore Screening via Neural Subgraph Matching

Tracking objects that change in appearance with phase synchrony

InversionGNN: A Dual Path Network for Multi-Property Molecular Optimization

Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs

CoInD: Enabling Logical Compositions in Diffusion Models

Descent with Misaligned Gradients and Applications to Hidden Convexity

OASIS Uncovers: High-Quality T2I Models, Same Old Stereotypes

Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy

$\mathbb{X}$-Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs

Diffusion State-Guided Projected Gradient for Inverse Problems

LiveBench: A Challenging, Contamination-Limited LLM Benchmark

Filtered not Mixed: Filtering-Based Online Gating for Mixture of Large Language Models

API Pack: A Massive Multi-Programming Language Dataset for API Call Generation

Learning from weak labelers as constraints

Hummingbird: High Fidelity Image Generation via Multimodal Context Alignment

Neuron Platonic Intrinsic Representation From Dynamics Using Contrastive Learning

Instant Policy: In-Context Imitation Learning via Graph Diffusion

Group Downsampling with Equivariant Anti-aliasing

LoRA Learns Less and Forgets Less

A Distributional Approach to Uncertainty-Aware Preference Alignment Using Offline Demonstrations

Estimating the Probabilities of Rare Outputs in Language Models

Self-Normalized Resets for Plasticity in Continual Learning

DiSK: Differentially Private Optimizer with Simplified Kalman Filter for Noise Reduction

Addax: Utilizing Zeroth-Order Gradients to Improve Memory Efficiency and Performance of SGD for Fine-Tuning Language Models

On Minimizing Adversarial Counterfactual Error in Adversarial Reinforcement Learning

Revisiting Nearest Neighbor for Tabular Data: A Deep Tabular Baseline Two Decades Later

Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentation

Limits to scalable evaluation at the frontier: LLM as judge won’t beat twice the data

Parameter and Memory Efficient Pretraining via Low-rank Riemannian Optimization

Reward Learning from Multiple Feedback Types

Probabilistic Neural Pruning via Sparsity Evolutionary Fokker-Planck-Kolmogorov Equation

Training on the Test Task Confounds Evaluation and Emergence

Homomorphism Expressivity of Spectral Invariant Graph Neural Networks

Towards Marginal Fairness Sliced Wasserstein Barycenter

How Do Large Language Models Understand Graph Patterns? A Benchmark for Graph Pattern Comprehension

MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequences

CO-MOT: Boosting End-to-end Transformer-based Multi-Object Tracking via Coopetition Label Assignment and Shadow Sets

Does Spatial Cognition Emerge in Frontier Models?

Chemistry-Inspired Diffusion with Non-Differentiable Guidance

Cut Your Losses in Large-Vocabulary Language Models

COME: Test-time Adaption by Conservatively Minimizing Entropy

CoMotion: Concurrent Multi-person 3D Motion

GNNs Getting ComFy: Community and Feature Similarity Guided Rewiring

MMRole: A Comprehensive Framework for Developing and Evaluating Multimodal Role-Playing Agents

DRoC: Elevating Large Language Models for Complex Vehicle Routing via Decomposed Retrieval of Constraints

Oracle efficient truncated statistics

Training Free Guided Flow-Matching with Optimal Control

6D Object Pose Tracking in Internet Videos for Robotic Manipulation

SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation

MGCFNN: A Neural MultiGrid Solver with Novel Fourier Neural Network for High Wave Number Helmholtz Equations

BTBS-LNS: Binarized-Tightening, Branch and Search on Learning LNS Policies for MIP

How new data permeates LLM knowledge and how to dilute it

Pre-training of Foundation Adapters for LLM Fine-tuning

Spiking Vision Transformer with Saccadic Attention

NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule Generation

NeuroLM: A Universal Multi-task Foundation Model for Bridging the Gap between Language and EEG Signals

Diffusion Feedback Helps CLIP See Better

Stabilizing Reinforcement Learning in Differentiable Multiphysics Simulation

Conformalized Interactive Imitation Learning: Handling Expert Shift and Intermittent Feedback

Agents' Room: Narrative Generation through Multi-step Collaboration

ND-SDF: Learning Normal Deflection Fields for High-Fidelity Indoor Reconstruction

LeFusion: Controllable Pathology Synthesis via Lesion-Focused Diffusion Models

Efficient Active Imitation Learning with Random Network Distillation

A Computational Framework for Modeling Emergence of Color Vision in the Human Brain

GEVRM: Goal-Expressive Video Generation Model For Robust Visual Manipulation

Do Mice Grok? Glimpses of Hidden Progress in Sensory Cortex

From Sparse Dependence to Sparse Attention: Unveiling How Chain-of-Thought Enhances Transformer Sample Efficiency

Unsupervised Multiple Kernel Learning for Graphs via Ordinality Preservation

Revisiting text-to-image evaluation with Gecko: on metrics, prompts, and human rating

Mitigating Information Loss in Tree-Based Reinforcement Learning via Direct Optimization

Salvage: Shapley-distribution Approximation Learning Via Attribution Guided Exploration for Explainable Image Classification

Collaborative Discrete-Continuous Black-Box Prompt Learning for Language Models

Overcoming Lower-Level Constraints in Bilevel Optimization: A Novel Approach with Regularized Gap Functions

Adversarial Training for Defense Against Label Poisoning Attacks

qNBO: quasi-Newton Meets Bilevel Optimization

Faster Inference of Flow-Based Generative Models via Improved Data-Noise Coupling

Generalizable Human Gaussians from Single-View Image

Leveraging Flatness to Improve Information-Theoretic Generalization Bounds for SGD

Certified Robustness Under Bounded Levenshtein Distance

Block-Attention for Efficient Prefilling

Efficient Interpolation between Extragradient and Proximal Methods for Weak MVIs

Rotated Runtime Smooth: Training-Free Activation Smoother for accurate INT4 inference

TODO: Enhancing LLM Alignment with Ternary Preferences

Learning Dynamics of LLM Finetuning

Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models

Injective flows for star-like manifolds

Exploring Prosocial Irrationality for LLM Agents: A Social Cognition View

Causally Motivated Sycophancy Mitigation for Large Language Models

VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking

Flaws of ImageNet, Computer Vision's Favourite Dataset

Influence Functions for Scalable Data Attribution in Diffusion Models

HShare: Fast LLM Decoding by Hierarchical Key-Value Sharing

ACE: All-round Creator and Editor Following Instructions via Diffusion Transformer

Indirect Gradient Matching for Adversarial Robust Distillation

Streamlining Redundant Layers to Compress Large Language Models

Lossy Compression with Pretrained Diffusion Models

DiscoveryBench: Towards Data-Driven Discovery with Large Language Models

Finally Rank-Breaking Conquers MNL Bandits: Optimal and Efficient Algorithms for MNL Assortment

Multi-agent cooperation through learning-aware policy gradients

Highly Efficient Self-Adaptive Reward Shaping for Reinforcement Learning

SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration

GeSubNet: Gene Interaction Inference for Disease Subtype Network Generation

The Pitfalls of Memorization: When Memorization Hurts Generalization

IPDreamer: Appearance-Controllable 3D Object Generation with Complex Image Prompts

GeoX: Geometric Problem Solving Through Unified Formalized Vision-Language Pre-training

Feedback Schrödinger Bridge Matching

Drama: Mamba-Enabled Model-Based Reinforcement Learning Is Sample and Parameter Efficient

Deep Distributed Optimization for Large-Scale Quadratic Programming

Field-DiT: Diffusion Transformer on Unified Video, 3D, and Game Field Generation

Safety Layers in Aligned Large Language Models: The Key to LLM Security

PIN: Prolate Spheroidal Wave Function-based Implicit Neural Representations

Learning Harmonized Representations for Speculative Sampling

High-Precision Dichotomous Image Segmentation via Probing Diffusion Capacity

PEAR: Primitive Enabled Adaptive Relabeling for Boosting Hierarchical Reinforcement Learning

REEF: Representation Encoding Fingerprints for Large Language Models

From Tokens to Lattices: Emergent Lattice Structures in Language Models

The Computational Complexity of Positive Non-Clashing Teaching in Graphs

Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling

Accelerating Diffusion Transformers with Token-wise Feature Caching

Revisiting Prefix-tuning: Statistical Benefits of Reparameterization among Prompts

Extendable and Iterative Structure Learning Strategy for Bayesian Networks

Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Transformers

Efficient Reinforcement Learning with Large Language Model Priors

KinFormer: Generalizable Dynamical Symbolic Regression for Catalytic Organic Reaction Kinetics

Transformers Provably Solve Parity Efficiently with Chain of Thought

Rethinking Classifier Re-Training in Long-Tailed Recognition: Label Over-Smooth Can Balance

Pedestrian Motion Reconstruction: A Large-scale Benchmark via Mixed Reality Rendering with Multiple Perspectives and Modalities

IDArb: Intrinsic Decomposition for Arbitrary Number of Input Views and Illuminations

SimpleTM: A Simple Baseline for Multivariate Time Series Forecasting

CLIPure: Purification in Latent Space via CLIP for Adversarially Robust Zero-Shot Classification

Models trained with unnormalized density functions: A need for a course correction

Composing Unbalanced Flows for Flexible Docking and Relaxation

REMEDY: Recipe Merging Dynamics in Large Vision-Language Models

Generalized Behavior Learning from Diverse Demonstrations

Semi-Supervised CLIP Adaptation by Enforcing Semantic and Trapezoidal Consistency

Holographic Node Representations: Pre-training Task-Agnostic Node Embeddings

Realistic Evaluation of Deep Partial-Label Learning Algorithms

Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality

PostEdit: Posterior Sampling for Efficient Zero-Shot Image Editing

AniSDF: Fused-Granularity Neural Surfaces with Anisotropic Encoding for High-Fidelity 3D Reconstruction

Closed-Form Merging of Parameter-Efficient Modules for Federated Continual Learning

Noise Separation guided Candidate Label Reconstruction for Noisy Partial Label Learning

ILLUSION: Unveiling Truth with a Comprehensive Multi-Modal, Multi-Lingual Deepfake Dataset

MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation

Boosting Multiple Views for pretrained-based Continual Learning

Neural ODE Transformers: Analyzing Internal Dynamics and Adaptive Fine-tuning

PaLD: Detection of Text Partially Written by Large Language Models

Benchmarking Agentic Workflow Generation

SAVA: Scalable Learning-Agnostic Data Valuation

ADMM for Structured Fractional Minimization

Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness

Projection Head is Secretly an Information Bottleneck

Boltzmann Semantic Score: A Semantic Metric for Evaluating Large Vision Models Using Large Language Models

Unsupervised Zero-Shot Reinforcement Learning via Dual-Value Forward-Backward Representation

LoCoDL: Communication-Efficient Distributed Learning with Local Training and Compression

IDA-VLM: Towards Movie Understanding via ID-Aware Large Vision-Language Model

XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning

MindSimulator: Exploring Brain Concept Localization via Synthetic fMRI

SELF-EVOLVED REWARD LEARNING FOR LLMS

RuAG: Learned-rule-augmented Generation for Large Language Models

On the Adversarial Vulnerability of Label-Free Test-Time Adaptation

IMDPrompter: Adapting SAM to Image Manipulation Detection by Cross-View Automated Prompt Learning

Autocorrelation Matters: Understanding the Role of Initialization Schemes for State Space Models

ReCogLab: a framework testing relational reasoning & cognitive hypotheses on LLMs

GraphRouter: A Graph-based Router for LLM Selections

SOAP: Improving and Stabilizing Shampoo using Adam for Language Modeling

When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers

Anti-Exposure Bias in Diffusion Models

Easing Training Process of Rectified Flow Models Via Lengthening Inter-Path Distance

How Does Critical Batch Size Scale in Pre-training?

A New Perspective on Shampoo's Preconditioner

Deconstructing What Makes a Good Optimizer for Autoregressive Language Models

Mixture of Parrots: Experts improve memorization more than reasoning

Revisiting a Design Choice in Gradient Temporal Difference Learning

Towards Understanding Why FixMatch Generalizes Better Than Supervised Learning

Doubly Optimal Policy Evaluation for Reinforcement Learning

InsightBench: Evaluating Business Analytics Agents Through Multi-Step Insight Generation

Efficient Policy Evaluation with Safety Constraint for Reinforcement Learning

Transformers Can Learn Temporal Difference Methods for In-Context Reinforcement Learning

LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token

LLaMA-Omni: Seamless Speech Interaction with Large Language Models

Unleashing the Potential of Vision-Language Pre-Training for 3D Zero-Shot Lesion Segmentation via Mask-Attribute Alignment

Rethinking the generalization of drug target affinity prediction algorithms via similarity aware evaluation

MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding

Learning Shape-Independent Transformation via Spherical Representations for Category-Level Object Pose Estimation

Improving Deep Regression with Tightness

RainbowPO: A Unified Framework for Combining Improvements in Preference Optimization

Generative Verifiers: Reward Modeling as Next-Token Prediction

GSE: Group-wise Sparse and Explainable Adversarial Attacks

Understanding Methods for Scalable MCTS

Dynamic Multimodal Evaluation with Flexible Complexity by Vision-Language Bootstrapping

Neural Sampling from Boltzmann Densities: Fisher-Rao Curves in the Wasserstein Geometry

eQMARL: Entangled Quantum Multi-Agent Reinforcement Learning for Distributed Cooperation over Quantum Channels

AnoLLM: Large Language Models for Tabular Anomaly Detection

The impact of allocation strategies in subset learning on the expressive power of neural networks

Fine-tuning can Help Detect Pretraining Data from Large Language Models

Boost Self-Supervised Dataset Distillation via Parameterization, Predefined Augmentation, and Approximation

Exploring Learning Complexity for Efficient Downstream Dataset Pruning

REvolve: Reward Evolution with Large Language Models using Human Feedback

UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation

Wavelet Diffusion Neural Operator

CL-DiffPhyCon: Closed-loop Diffusion Control of Complex Physical Systems

Metamizer: A Versatile Neural Optimizer for Fast and Accurate Physics Simulations

Long-tailed Adversarial Training with Self-Distillation

TaskGalaxy: Scaling Multi-modal Instruction Fine-tuning with Tens of Thousands Vision Task Types

VCR: A Task for Pixel-Level Complex Reasoning in Vision Language Models via Restoring Occluded Text

MallowsPO: Fine-Tune Your LLM with Preference Dispersions

MoS: Unleashing Parameter Efficiency of Low-Rank Adaptation with Mixture of Shards

MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic Approximation

OccProphet: Pushing the Efficiency Frontier of Camera-Only 4D Occupancy Forecasting with an Observer-Forecaster-Refiner Framework

Painting with Words: Elevating Detailed Image Captioning with Benchmark and Alignment Learning

Nonlinear Sequence Embedding by Monotone Variational Inequality

Kernel-based Optimally Weighted Conformal Time-Series Prediction

Agree to Disagree: Demystifying Homogeneous Deep Ensembles through Distributional Equivalence

Quantum (Inspired) $D^2$-sampling with Applications

Inspection and Control of Self-Generated-Text Recognition Ability in Llama3-8b-Instruct

Concept Bottleneck Language Models For Protein Design

Discovering Clone Negatives via Adaptive Contrastive Learning for Image-Text Matching

PostCast: Generalizable Postprocessing for Precipitation Nowcasting via Unsupervised Blurriness Modeling

Mitigating Reward Over-Optimization in RLHF via Behavior-Supported Regularization

A Closer Look at Machine Unlearning for Large Language Models

Looking Inward: Language Models Can Learn About Themselves by Introspection

Perplexity Trap: PLM-Based Retrievers Overrate Low Perplexity Documents

Influence-Guided Diffusion for Dataset Distillation

IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation

MaxCutPool: differentiable feature-aware Maxcut for pooling in graph neural networks

DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads

Glad: A Streaming Scene Generator for Autonomous Driving

DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation

Resolution Attack: Exploiting Image Compression to Deceive Deep Neural Networks

Stem-OB: Generalizable Visual Imitation Learning with Stem-Like Convergent Observation through Diffusion Inversion

Circuit Transformer: A Transformer That Preserves Logical Equivalence

Information Theoretic Text-to-Image Alignment

GeoILP: A Synthetic Dataset to Guide Large-Scale Rule Induction

Rethinking Reward Model Evaluation: Are We Barking up the Wrong Tree?

CREIMBO: Cross-Regional Ensemble Interactions in Multi-view Brain Observations

EvA: Erasing Spurious Correlations with Activations

SysBench: Can LLMs Follow System Message?

Walk the Talk? Measuring the Faithfulness of Large Language Model Explanations

Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting

ProtPainter: Draw or Drag Protein via Topology-guided Diffusion

Redefining the task of Bioactivity Prediction

CtD: Composition through Decomposition in Emergent Communication

Reframing Structure-Based Drug Design Model Evaluation via Metrics Correlated to Practical Needs

Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior

Mask in the Mirror: Implicit Sparsification

The Rise and Down of Babel Tower: Investigating the Evolution Process of Multilingual Code Large Language Model

Score-based Self-supervised MRI Denoising

Revisit Micro-batch Clipping: Adaptive Data Pruning via Gradient Manipulation

Contextualizing biological perturbation experiments through language

PhyMPGN: Physics-encoded Message Passing Graph Network for spatiotemporal PDE systems

Local Patterns Generalize Better for Novel Anomalies

MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance

Model Risk-sensitive Offline Reinforcement Learning

Beyond Squared Error: Exploring Loss Design for Enhanced Training of Generative Flow Networks

Offline RL in Regular Decision Processes: Sample Efficiency via Language Metrics

TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval

CViT: Continuous Vision Transformer for Operator Learning

Rethinking Multiple-Instance Learning From Feature Space to Probability Space

SVG: 3D Stereoscopic Video Generation via Denoising Frame Matrix

AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agents

TabWak: A Watermark for Tabular Diffusion Models

Interpretable Unsupervised Joint Denoising and Enhancement for Real-World low-light Scenarios

FIRING-Net: A filtered feature recycling network for speech enhancement

Can We Talk Models Into Seeing the World Differently?

ZooProbe: A Data Engine for Evaluating, Exploring, and Evolving Large-scale Training Data for Multimodal LLMs

DLEFT-MKC: Dynamic Late Fusion Multiple Kernel Clustering with Robust Tensor Learning via Min-Max Optimization

Simple yet Effective Incomplete Multi-view Clustering: Similarity-level Imputation and Intra-view Hybrid-group Prototype Construction

Causal Reasoning and Large Language Models: Opening a New Frontier for Causality

An Online Learning Theory of Trading-Volume Maximization

UniCBE: An Uniformity-driven Comparing Based Evaluation Framework with Unified Multi-Objective Optimization

Dynamical Diffusion: Learning Temporal Dynamics with Diffusion Models

Mitigating Memorization in Language Models

Predicting the Energy Landscape of Stochastic Dynamical System via Physics-informed Self-supervised Learning

Image Watermarks are Removable using Controllable Regeneration from Clean Noise

Fair Clustering in the Sliding Window Model

ELICIT: LLM Augmentation Via External In-context Capability

Personality Alignment of Large Language Models

Neural Causal Graph for Interpretable and Intervenable Classification

Language Models are Advanced Anonymizers

Ward: Provable RAG Dataset Inference via LLM Watermarks

Towards Homogeneous Lexical Tone Decoding from Heterogeneous Intracranial Recordings

NutriBench: A Dataset for Evaluating Large Language Models in Nutrition Estimation from Meal Descriptions

SciLitLLM: How to Adapt LLMs for Scientific Literature Understanding

Linear Spherical Sliced Optimal Transport: A Fast Metric for Comparing Spherical Data

CycleResearcher: Improving Automated Research via Automated Review

MMQA: Evaluating LLMs with Multi-Table Multi-Hop Complex Questions

Human Simulacra: Benchmarking the Personification of Large Language Models

DAMO: Decoding by Accumulating Activations Momentum for Mitigating Hallucinations in Vision-Language Models

UniRestore3D: A Scalable Framework For General Shape Restoration

Offline Hierarchical Reinforcement Learning via Inverse Optimization

Generative Representational Instruction Tuning

Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis

Adversarially Robust Anomaly Detection through Spurious Negative Pair Mitigation

An Exploration with Entropy Constrained 3D Gaussians for 2D Video Compression

Learning Fine-Grained Representations through Textual Token Disentanglement in Composed Video Retrieval

Decentralized Sporadic Federated Learning: A Unified Algorithmic Framework with Convergence Guarantees

LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory

T2V2: A Unified Non-Autoregressive Model for Speech Recognition and Synthesis via Multitask Learning

Moner: Motion Correction in Undersampled Radial MRI with Unsupervised Neural Representation

One Hundred Neural Networks and Brains Watching Videos: Lessons from Alignment

BrainACTIV: Identifying visuo-semantic properties driving cortical selectivity using diffusion-based image manipulation

Multi-Draft Speculative Sampling: Canonical Decomposition and Theoretical Limits

TD-Paint: Faster Diffusion Inpainting Through Time-Aware Pixel Conditioning

Modeling Complex System Dynamics with Flow Matching Across Time and Conditions

One for all and all for one: Efficient computation of partial Wasserstein distances on the line

Learning Dynamics of Deep Matrix Factorization Beyond the Edge of Stability

Beyond Canonicalization: How Tensorial Messages Improve Equivariant Message Passing

Manifold Induced Biases for Zero-shot and Few-shot Detection of Generated Images

Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction

Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation

DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous Driving

An Engorgio Prompt Makes Large Language Model Babble on

MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models

SVDQuant: Absorbing Outliers by Low-Rank Component for 4-Bit Diffusion Models

Hotspot-Driven Peptide Design via Multi-Fragment Autoregressive Extension

SANA: Efficient High-Resolution Text-to-Image Synthesis with Linear Diffusion Transformers

Any-step Dynamics Model Improves Future Predictions for Online and Offline Reinforcement Learning

Dynamic Loss-Based Sample Reweighting for Improved Large Language Model Pretraining

Semantic Temporal Abstraction via Vision-Language Model Guidance for Efficient Reinforcement Learning

Scaling FP8 training to trillion-token LLMs

Enhancing Pre-trained Representation Classifiability can Boost its Interpretability

Efficient Multi-agent Offline Coordination via Diffusion-based Trajectory Stitching

Supervised and Semi-Supervised Diffusion Maps with Label-Driven Diffusion

Tree-Wasserstein Distance for High Dimensional Data with a Latent Feature Hierarchy

Reassessing How to Compare and Improve the Calibration of Machine Learning Models

On Stochastic Contextual Bandits with Knapsacks in Small Budget Regime

ChemAgent: Self-updating Memories in Large Language Models Improves Chemical Reasoning

For Better or For Worse? Learning Minimum Variance Features With Label Augmentation

Audio Large Language Models Can Be Descriptive Speech Quality Evaluators

Residual-MPPI: Online Policy Customization for Continuous Control

ImagineNav: Prompting Vision-Language Models as Embodied Navigator through Scene Imagination

X-Drive: Cross-modality Consistent Multi-Sensor Data Synthesis for Driving Scenarios

Self-Attention-Based Contextual Modulation Improves Neural System Identification

Restructuring Vector Quantization with the Rotation Trick

GoodDrag: Towards Good Practices for Drag Editing with Diffusion Models

RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style

Analyzing Neural Scaling Laws in Two-Layer Networks with Power-Law Data Spectra

Distribution Backtracking Builds A Faster Convergence Trajectory for Diffusion Distillation

FaceShot: Bring Any Character into Life

Fully-inductive Node Classification on Arbitrary Graphs

On Large Language Model Continual Unlearning

MolSpectra: Pre-training 3D Molecular Representation with Multi-modal Energy Spectra

Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models

LayerDAG: A Layerwise Autoregressive Diffusion Model for Directed Acyclic Graph Generation

AdaManip: Adaptive Articulated Object Manipulation Environments and Policy Learning

MMFakeBench: A Mixed-Source Multimodal Misinformation Detection Benchmark for LVLMs

Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distribution

Non-myopic Generation of Language Models for Reasoning and Planning

On the Optimization and Generalization of Multi-head Attention

Tamper-Resistant Safeguards for Open-Weight LLMs

DCT-CryptoNets: Scaling Private Inference in the Frequency Domain

Learning Structured Representations by Embedding Class Hierarchy with Fast Optimal Transport

Words in Motion: Extracting Interpretable Control Vectors for Motion Transformers

FOSP: Fine-tuning Offline Safe Policy through World Models

Adversaries With Incentives: A Strategic Alternative to Adversarial Robustness

Ctrl-U: Robust Conditional Image Generation via Uncertainty-aware Reward Modeling

SAGEPhos: Sage Bio-Coupled and Augmented Fusion for Phosphorylation Site Detection

MaRS: A Fast Sampler for Mean Reverting Diffusion based on ODE and SDE Solvers

Precise Localization of Memories: A Fine-grained Neuron-level Knowledge Editing Technique for LLMs

CatVTON: Concatenation Is All You Need for Virtual Try-On with Diffusion Models

Progressive Mixed-Precision Decoding for Efficient LLM Inference

SC-OmniGS: Self-Calibrating Omnidirectional Gaussian Splatting

DRESSing Up LLM: Efficient Stylized Question-Answering via Style Subspace Editing

EmbedLLM: Learning Compact Representations of Large Language Models

AgentSquare: Automatic LLM Agent Search in Modular Design Space

ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning

TPO: Aligning Large Language Models with Multi-branch & Multi-step Preference Trees

Bridging the Gap Between f-divergences and Bayes Hilbert Spaces

Designing Mechanical Meta-Materials by Learning Equivariant Flows

DeepTAGE: Deep Temporal-Aligned Gradient Enhancement for Optimizing Spiking Neural Networks

Round and Round We Go! What makes Rotary Positional Encodings useful?

SysCaps: Language Interfaces for Simulation Surrogates of Complex Systems

Sparse Learning for State Space Models on Mobile

Revisit the Open Nature of Open Vocabulary Semantic Segmentation

Are Transformers Able to Reason by Connecting Separated Knowledge in Training Data?

Multi-Scale Fusion for Object Representation

Recognize Any Surgical Object: Unleashing the Power of Weakly-Supervised Data

GOLD: Graph Out-of-Distribution Detection via Implicit Adversarial Latent Generation

SafeWatch: An Efficient Safety-Policy Following Video Guardrail Model with Transparent Explanations

Fine-tuning can cripple your foundation model; preserving features may be the solution

GALA: Geometry-Aware Local Adaptive Grids for Detailed 3D Generation

Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy

Hyperbolic Genome Embeddings

Triples as the Key: Structuring Makes Decomposition and Verification Easier in LLM-based TableQA

Data Pruning by Information Maximization

An Evolved Universal Transformer Memory

VLAS: Vision-Language-Action Model with Speech Instructions for Customized Robot Manipulation

Memory Mosaics

X-NeMo: Expressive Neural Motion Reenactment via Disentangled Latent Attention

Gradient-Free Generation for Hard-Constrained Systems

CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale Scenes

FreeVS: Generative View Synthesis on Free Driving Trajectory

Improving Long-Text Alignment for Text-to-Image Diffusion Models

Enhancing End-to-End Autonomous Driving with Latent World Model

On the Computation of the Fisher Information in Continual Learning

DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference

SimulPL: Aligning Human Preferences in Simultaneous Machine Translation

CREAM: Consistency Regularized Self-Rewarding Language Models

Beware of Calibration Data for Pruning Large Language Models

Rectified Diffusion: Straightness Is Not Your Need in Rectified Flow

3DMolFormer: A Dual-channel Framework for Structure-based Drug Discovery

Does Editing Provide Evidence for Localization?

A Geometric Framework for Understanding Memorization in Generative Models

TLDR: Token-Level Detective Reward Model for Large Vision Language Models

Glimpse: Enabling White-Box Methods to Use Proprietary Models for Zero-Shot LLM-Generated Text Detection

SqueezeAttention: 2D Management of KV-Cache in LLM Inference via Layer-wise Optimal Budget

Understanding and Enhancing Safety Mechanisms of LLMs via Safety-Specific Neuron

ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing

Towards Domain Adaptive Neural Contextual Bandits

Investigating Pattern Neurons in Urban Time Series Forecasting

Transformers Learn to Implement Multi-step Gradient Descent with Chain of Thought

DARE the Extreme: Revisiting Delta-Parameter Pruning For Fine-Tuned Models

Adding Conditional Control to Diffusion Models with Reinforcement Learning

Distilling Dataset into Neural Field

Black Sheep in the Herd: Playing with Spuriously Correlated Attributes for Vision-Language Recognition

Dissecting Adversarial Robustness of Multimodal LM Agents

Incorporating Visual Correspondence into Diffusion Model for Virtual Try-On

Wayward Concepts In Multimodal Models

SLoPe: Double-Pruned Sparse Plus Lazy Low-Rank Adapter Pretraining of LLMs

Can Watermarks be Used to Detect LLM IP Infringement For Free?

Learning Diagrams: A Graphical Language for Compositional Training Regimes

EcoFace: Audio-Visual Emotional Co-Disentanglement Speech-Driven 3D Talking Face Generation

Neural Approximate Mirror Maps for Constrained Diffusion Models

Self-MoE: Towards Compositional Large Language Models with Self-Specialized Experts

Satisficing Regret Minimization in Bandits

Controlling Space and Time with Diffusion Models

Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMs

Exploring the Design Space of Visual Context Representation in Video MLLMs

GANDALF: Generative AttentioN based Data Augmentation and predictive modeLing Framework for personalized cancer treatment

Towards Realistic Data Generation for Real-World Super-Resolution

Provably Safeguarding a Classifier from OOD and Adversarial Samples

Mask-DPO: Generalizable Fine-grained Factuality Alignment of LLMs

MindSearch: Mimicking Human Minds Elicits Deep AI Searcher

Navigation-Guided Sparse Scene Representation for End-to-End Autonomous Driving

DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?

Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models

Uncertainty modeling for fine-tuned implicit functions

On the Fourier analysis in the SO(3) space : the EquiLoPO Network

Modeling Future Conversation Turns to Teach LLMs to Ask Clarifying Questions

HaDeMiF: Hallucination Detection and Mitigation in Large Language Models

Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis

Guided Score identity Distillation for Data-Free One-Step Text-to-Image Generation

Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Step

Adapting Multi-modal Large Language Model to Concept Drift From Pre-training Onwards

Optimizing $(L_0, L_1)$-Smooth Functions by Gradient Methods

cryoSPHERE: Single-Particle HEterogeneous REconstruction from cryo EM

Bridging the Gap between Variational Inference and Stochastic Gradient MCMC in Function Space

Grammar Reinforcement Learning: path and cycle counting in graphs with a Context-Free Grammar and Transformer approach

DICE: Data Influence Cascade in Decentralized Learning

HyperFace: Generating Synthetic Face Recognition Datasets by Exploring Face Embedding Hypersphere

Rare-to-Frequent: Unlocking Compositional Generation Power of Diffusion Models on Rare Concepts with LLM Guidance

Release the Powers of Prompt Tuning: Cross-Modality Prompt Transfer

HMoRA: Making LLMs More Effective with Hierarchical Mixture of LoRA Experts

Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents

Going Beyond Static: Understanding Shifts with Time-Series Attribution

Scrutinize What We Ignore: Reining In Task Representation Shift Of Context-Based Offline Meta Reinforcement Learning

Confidence Elicitation: A New Attack Vector for Large Language Models

PIED: Physics-Informed Experimental Design for Inverse Problems

RelitLRM: Generative Relightable Radiance for Large Reconstruction Models

BIRD: A Trustworthy Bayesian Inference Framework for Large Language Models

Decentralized Optimization with Coupled Constraints

Repulsive Latent Score Distillation for Solving Inverse Problems

A Visual Dive into Conditional Flow Matching

Youku Dense Caption: A Large-scale Chinese Video Dense Caption Dataset and Benchmarks

Refine Knowledge of Large Language Models via Adaptive Contrastive Learning

Frame-Voyager: Learning to Query Frames for Video Large Language Models

Zero-shot Imputation with Foundation Inference Models for Dynamical Systems

Qinco2: Vector Compression and Search with Improved Implicit Neural Codebooks

Holistic Reasoning with Long-Context LMs: A Benchmark for Database Operations on Massive Textual Data

Large Language Models Often Say One Thing and Do Another

Can a Large Language Model be a Gaslighter?

Deep Random Features for Scalable Interpolation of Spatiotemporal Data

Enhancing Vision-Language Model with Unmasked Token Alignment

A3D: Does Diffusion Dream about 3D Alignment?

Input Space Mode Connectivity in Deep Neural Networks

Making Transformer Decoders Better Differentiable Indexers

What Makes Large Language Models Reason in (Multi-Turn) Code Generation?

P-SPIKESSM: HARNESSING PROBABILISTIC SPIKING STATE SPACE MODELS FOR LONG-RANGE DEPENDENCY TASKS

The KoLMogorov Test: Compression by Code Generation

Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models

General Scene Adaptation for Vision-and-Language Navigation

How to Evaluate Reward Models for RLHF

Long Context Compression with Activation Beacon

RouteLLM: Learning to Route LLMs from Preference Data

SpikeLLM: Scaling up Spiking Neural Network to Large Language Models via Saliency-based Spiking

Making Text Embedders Few-Shot Learners

K-HALU: Multiple Answer Korean Hallucination Benchmark for Large Language Models

MMTEB: Massive Multilingual Text Embedding Benchmark

AutoUAD: Hyper-parameter Optimization for Unsupervised Anomaly Detection

FlashMask: Efficient and Rich Mask Extension of FlashAttention

EgoExo-Gen: Ego-centric Video Prediction by Watching Exo-centric Videos

CipherPrune: Efficient and Scalable Private Transformer Inference

OpenHands: An Open Platform for AI Software Developers as Generalist Agents

DON’T STOP ME NOW: EMBEDDING BASED SCHEDULING FOR LLMS

EMMA: Empowering Multi-modal Mamba with Structural and Hierarchical Alignment

FreCaS: Efficient Higher-Resolution Image Generation via Frequency-aware Cascaded Sampling

How Much is Unseen Depends Chiefly on Information About the Seen

ZAPBench: A Benchmark for Whole-Brain Activity Prediction in Zebrafish

Spatial-Mamba: Effective Visual State Space Models via Structure-Aware State Fusion

Loss Landscape of Shallow ReLU-like Neural Networks: Stationary Points, Saddle Escape, and Network Embedding

Quantum-PEFT: Ultra parameter-efficient fine-tuning

Data Selection via Optimal Control for Language Models

TeaserGen: Generating Teasers for Long Documentaries

Aligning Visual Contrastive learning models via Preference Optimization

VVC-Gym: A Fixed-Wing UAV Reinforcement Learning Environment for Multi-Goal Long-Horizon Problems

Exploring a Principled Framework for Deep Subspace Clustering

HERO: Human-Feedback Efficient Reinforcement Learning for Online Diffusion Model Finetuning

Scaling Laws for Downstream Task Performance in Machine Translation

Ranking-aware adapter for text-driven image ordering with CLIP

Towards Optimal Multi-draft Speculative Decoding

On the Feature Learning in Diffusion Models

Q-SFT: Q-Learning for Language Models via Supervised Fine-Tuning

CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer

One Step Diffusion via Shortcut Models

OGBench: Benchmarking Offline Goal-Conditioned RL

Random Is All You Need: Random Noise Injection on Feature Statistics for Generalizable Deep Image Denoising

Prioritized Generative Replay

CURIE: Evaluating LLMs on Multitask Scientific Long-Context Understanding and Reasoning

Multimodal Quantitative Language for Generative Recommendation

FreSh: Frequency Shifting for Accelerated Neural Representation Learning

SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression

Precedence-Constrained Winter Value for Effective Graph Data Valuation

Seeing Eye to AI: Human Alignment via Gaze-Based Response Rewards for Large Language Models

Uncertainty Modeling in Graph Neural Networks via Stochastic Differential Equations

LASER: A Neuro-Symbolic Framework for Learning Spatio-Temporal Scene Graphs with Weak Supervision

Omni-MATH: A Universal Olympiad Level Mathematic Benchmark for Large Language Models

Federated Continual Learning Goes Online: Uncertainty-Aware Memory Management for Vision Tasks and Beyond

Diversity-Rewarded CFG Distillation

Gaussian Differentially Private Human Faces Under a Face Radial Curve Representation

MANTRA: The Manifold Triangulations Assemblage

Diffusion-Based Planning for Autonomous Driving with Flexible Guidance

Skill Expansion and Composition in Parameter Space

What Do You See in Common? Learning Hierarchical Prototypes over Tree-of-Life to Discover Evolutionary Traits

Backdooring Vision-Language Models with Out-Of-Distribution Data

Geometry of Long-Tailed Representation Learning: Rebalancing Features for Skewed Distributions

Gaussian-Det: Learning Closed-Surface Gaussians for 3D Object Detection

A Transfer Attack to Image Watermarks

Dysca: A Dynamic and Scalable Benchmark for Evaluating Perception Ability of LVLMs

MM-EMBED: UNIVERSAL MULTIMODAL RETRIEVAL WITH MULTIMODAL LLMS

NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models

GenXD: Generating Any 3D and 4D Scenes

Locality-aware Gaussian Compression for Fast and High-quality Rendering

EditRoom: LLM-parameterized Graph Diffusion for Composable 3D Room Layout Editing

MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos

SlowFast-VGen: Slow-Fast Learning for Action-Driven Long Video Generation

Meta-Continual Learning of Neural Fields

Faster Algorithms for Structured Linear and Kernel Support Vector Machines

On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback

Semi-Supervised Vision-Centric 3D Occupancy World Model for Autonomous Driving

Adversarial Attacks on Data Attribution

Energy-Weighted Flow Matching for Offline Reinforcement Learning

DPLM-2: A Multimodal Diffusion Protein Language Model

CONTRA: Conformal Prediction Region via Normalizing Flow Transformation

OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation

Show-o: One Single Transformer to Unify Multimodal Understanding and Generation

Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models

UTILITY: Utilizing Explainable Reinforcement Learning to Improve Reinforcement Learning

Efficient Diversity-Preserving Diffusion Alignment via Gradient-Informed GFlowNets

Can Large Language Models Understand Symbolic Graphics Programs?

DistillHGNN: A Knowledge Distillation Approach for High-Speed Hypergraph Neural Networks

Deep Kernel Relative Test for Machine-generated Text Detection

Continuous Autoregressive Modeling with Stochastic Monotonic Alignment for Speech Synthesis

Trained Transformer Classifiers Generalize and Exhibit Benign Overfitting In-Context

Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solver

Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems

Visual Agents as Fast and Slow Thinkers

Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents

Grounding Multimodal Large Language Model in GUI World

Denoising with a Joint-Embedding Predictive Architecture

LoR-VP: Low-Rank Visual Prompting for Efficient Vision Model Adaptation

CofCA: A STEP-WISE Counterfactual Multi-hop QA benchmark

Learning Molecular Representation in a Cell

MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning

Exact Certification of (Graph) Neural Networks Against Label Poisoning

Learning stochastic dynamics from snapshots through regularized unbalanced optimal transport

Unlocking Point Processes through Point Set Diffusion

Learning Spatial-Semantic Features for Robust Video Object Segmentation

SafeDiffuser: Safe Planning with Diffusion Probabilistic Models

PseDet: Revisiting the Power of Pseudo Label in Incremental Object Detection

The Breakdown of Gaussian Universality in Classification of High-dimensional Linear Factor Mixtures

Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models

Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation

NarrativeBridge: Enhancing Video Captioning with Causal-Temporal Narrative

FedTMOS: Efficient One-Shot Federated Learning with Tsetlin Machine

Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models

Everything is Editable: Extend Knowledge Editing to Unstructured Data in Large Language Models

Learning View-invariant World Models for Visual Robotic Manipulation

How Gradient descent balances features: A dynamical analysis for two-layer neural networks

A Unifying Framework for Representation Learning

Minimax Optimal Two-Stage Algorithm For Moment Estimation Under Covariate Shift

TimeKAN: KAN-based Frequency Decomposition Learning Architecture for Long-term Time Series Forecasting

From Models to Microtheories: Distilling a Model's Topical Knowledge for Grounded Question-Answering

Exploring Local Memorization in Diffusion Models via Bright Ending Attention

ALBAR: Adversarial Learning approach to mitigate Biases in Action Recognition

Analytic DAG Constraints for Differentiable DAG Learning

Artificial Kuramoto Oscillatory Neurons

InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales

Exploiting Structure in Offline Multi-Agent RL: The Benefits of Low Interaction Rank

Towards Generalization Bounds of GCNs for Adversarially Robust Node Classification

Physics-informed Temporal Difference Metric Learning for Robot Motion Planning

Scalable and Certifiable Graph Unlearning: Overcoming the Approximation Error Barrier

Restating the Proof of Linear Convergence for Linear GNNs

TGB-Seq Benchmark: Challenging Temporal GNNs with Complex Sequential Dynamics

Energy-based Backdoor Defense Against Federated Graph Learning

How Two-Layer Neural Networks Learn, One (Giant) Step at a Time

Mechanistic Permutability: Match Features Across Layers

Moral Alignment for LLM Agents

Ask, and it shall be given: On the Turing completeness of prompting

One-for-All Few-Shot Anomaly Detection via Instance-Induced Prompt Learning

From Artificial Needles to Real Haystacks: Improving Retrieval Capabilities in LLMs by Finetuning on Synthetic Data

Process Reward Model with Q-value Rankings

OmniEdit: Building Image Editing Generalist Models Through Specialist Supervision

UniCon: Unidirectional Information Flow for Effective Control of Large-Scale Diffusion Models

Efficient Cross-Episode Meta-RL

Do Vision-Language Models Represent Space and How? Evaluating Spatial Frame of Reference under Ambiguities

COMBO: Compositional World Models for Embodied Multi-Agent Cooperation

Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsification

Learn Your Reference Model for Real Good Alignment

Steering Protein Family Design through Profile Bayesian Flow

C-CLIP: Multimodal Continual Learning for Vision-Language Model

Local-Prompt: Extensible Local Prompts for Few-Shot Out-of-Distribution Detection

Adaptive Batch Size for Privately Finding Second-Order Stationary Points

Straight to Zero: Why Linearly Decaying the Learning Rate to Zero Works Best for LLMs

BRAID: Input-driven Nonlinear Dynamical Modeling of Neural-Behavioral Data

Learning Clustering-based Prototypes for Compositional Zero-Shot Learning

DenseGrounding: Improving Dense Language-Vision Semantics for Ego-centric 3D Visual Grounding

Both Ears Wide Open: Towards Language-Driven Spatial Audio Generation

CR2PQ: Continuous Relative Rotary Positional Query for Dense Visual Representation Learning

Benign Overfitting in Out-of-Distribution Generalization of Linear Models

Captured by Captions: On Memorization and its Mitigation in CLIP Models

Ready-to-React: Online Reaction Policy for Two-Character Interaction Generation

Understanding Fairness Surrogate Functions in Algorithmic Fairness

Neural Eulerian Scene Flow Fields

Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders

Calibrating LLMs with Information-Theoretic Evidential Deep Learning

Diffusion Actor-Critic: Formulating Constrained Policy Iteration as Diffusion Noise Regression for Offline Reinforcement Learning

TIGeR: Unifying Text-to-Image Generation and Retrieval with Large Multimodal Models

Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usage

Effective and Efficient Time-Varying Counterfactual Prediction with State-Space Models

Rethinking Neural Multi-Objective Combinatorial Optimization via Neat Weight Embedding

Neural Multi-Objective Combinatorial Optimization via Graph-Image Multimodal Fusion

Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats

Language Models Learn to Mislead Humans via RLHF

Adversarial Generative Flow Network for Solving Vehicle Routing Problems

DataMan: Data Manager for Pre-training Large Language Models

Graph Assisted Offline-Online Deep Reinforcement Learning for Dynamic Workflow Scheduling

RNNs are not Transformers (Yet): The Key Bottleneck on In-Context Retrieval

Efficient Action-Constrained Reinforcement Learning via Acceptance-Rejection Method and Augmented MDPs

QMP: Q-switch Mixture of Policies for Multi-Task Behavior Sharing

Flow Distillation Sampling: Regularizing 3D Gaussians with Pre-trained Matching Priors

UniCoTT: A Unified Framework for Structural Chain-of-Thought Distillation

DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control Agent

$\text{D}_{2}\text{O}$: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language Models

Can Textual Gradient Work in Federated Learning?

Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMs

Differentially Private Steering for Large Language Model Alignment

Polynomial Composition Activations: Unleashing the Dynamics of Large Language Models

MatryoshkaKV: Adaptive KV Compression via Trainable Orthogonal Projection

Aligning Language Models with Demonstrated Feedback

AugKD: Ingenious Augmentations Empower Knowledge Distillation for Image Super-Resolution

Semantic Image Inversion and Editing using Rectified Stochastic Differential Equations

Uni$^2$Det: Unified and Universal Framework for Prompt-Guided Multi-dataset 3D Detection

Enhancing Learning with Label Differential Privacy by Vector Approximation

RB-Modulation: Training-Free Stylization using Reference-Based Modulation

PAL: Sample-Efficient Personalized Reward Modeling for Pluralistic Alignment

$InterLCM$: Low-Quality Images as Intermediate States of Latent Consistency Models for Effective Blind Face Restoration

HelpSteer2-Preference: Complementing Ratings with Preferences

Single Teacher, Multiple Perspectives: Teacher Knowledge Augmentation for Enhanced Knowledge Distillation

Contextual Document Embeddings

Matcha: Mitigating Graph Structure Shifts with Test-Time Adaptation

Video In-context Learning: Autoregressive Transformers are Zero-Shot Video Imitators

FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models

SecureGS: Boosting the Security and Fidelity of 3D Gaussian Splatting Steganography

Your Weak LLM is Secretly a Strong Teacher for Alignment

DaWin: Training-free Dynamic Weight Interpolation for Robust Adaptation

CONDA: Adaptive Concept Bottleneck for Foundation Models Under Distribution Shifts

Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Models

LongGenBench: Benchmarking Long-Form Generation in Long Context LLMs

Learning Graph Invariance by Harnessing Spuriosity

Zigzag Diffusion Sampling: Diffusion Models Can Self-Improve via Self-Reflection

Grounding Continuous Representations in Geometry: Equivariant Neural Fields

Shedding Light on Time Series Classification using Interpretability Gated Networks

Measuring And Improving Engagement of Text-to-Image Generation Models

Discriminating image representations with principal distortions

MetaDesigner: Advancing Artistic Typography through AI-Driven, User-Centric, and Multilingual WordArt Synthesis

One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt

LLM-SR: Scientific Equation Discovery via Programming with Large Language Models

Advancing Prompt-Based Methods for Replay-Independent General Continual Learning

FACTS: A Factored State-Space Framework for World Modelling

Wasserstein Distances, Neuronal Entanglement, and Sparsity

Lean-STaR: Learning to Interleave Thinking and Proving

Self-Play Preference Optimization for Language Model Alignment

Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for LLM Problem-Solving

OpenRCA: Can Large Language Models Locate the Root Cause of Software Failures?

Flow Matching with General Discrete Paths: A Kinetic-Optimal Perspective

MP-Mat: A 3D-and-Instance-Aware Human Matting and Editing Framework with Multiplane Representation

Enhancing Zeroth-order Fine-tuning for Language Models with Low-rank Structures

On the Performance Analysis of Momentum Method: A Frequency Domain Perspective

Brain Mapping with Dense Features: Grounding Cortical Semantic Selectivity in Natural Images With Vision Transformers

SaMer: A Scenario-aware Multi-dimensional Evaluator for Large Language Models

Self-supervised Monocular Depth Estimation Robust to Reflective Surface Leveraged by Triplet Mining

InstantSplamp: Fast and Generalizable Stenography Framework for Generative Gaussian Splatting

PFDiff: Training-Free Acceleration of Diffusion Models Combining Past and Future Scores

4K4DGen: Panoramic 4D Generation at 4K Resolution

Fast and Slow Streams for Online Time Series Forecasting Without Information Leakage

FLIP: Flow-Centric Generative Planning as General-Purpose Manipulation World Model

ScImage: How good are multimodal large language models at scientific text-to-image generation?

Binary Losses for Density Ratio Estimation

Data Taggants: Dataset Ownership Verification Via Harmless Targeted Data Poisoning

DICE: End-to-end Deformation Capture of Hand-Face Interactions from a Single Image

BANGS: Game-theoretic Node Selection for Graph Self-Training

CityAnchor: City-scale 3D Visual Grounding with Multi-modality LLMs

Not All Language Model Features Are One-Dimensionally Linear

MVTokenFlow: High-quality 4D Content Generation using Multiview Token Flow

Rapidly Adapting Policies to the Real-World via Simulation-Guided Fine-Tuning

Modality-Specialized Synergizers for Interleaved Vision-Language Generalists

SPARTUN3D: Situated Spatial Understanding of 3D World in Large Language Model

State Space Models are Provably Comparable to Transformers in Dynamic Token Selection

AgentStudio: A Toolkit for Building General Virtual Agents

Unleashing the Power of Task-Specific Directions in Parameter Efficient Fine-tuning

Diffusing to the Top: Boost Graph Neural Networks with Minimal Hyperparameter Tuning

When Graph Neural Networks Meet Dynamic Mode Decomposition

Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want

Linear Transformer Topological Masking with Graph Random Features

Model-based RL as a Minimalist Approach to Horizon-Free and Second-Order Bounds

DINOv2: Learning Robust Visual Features without Supervision

Learning under Temporal Label Noise

Robustness of Quantum Algorithms for Nonconvex Optimization

Uncertainty Herding: One Active Learning Method for All Label Budgets

What Has Been Overlooked in Contrastive Source-Free Domain Adaptation: Leveraging Source-Informed Latent Augmentation within Neighborhood Context

Reducing Hallucinations in Large Vision-Language Models via Latent Space Steering

TorchTitan: One-stop PyTorch native solution for production ready LLM pretraining

HELM: Hierarchical Encoding for mRNA Language Modeling

ShortcutsBench: A Large-Scale Real-world Benchmark for API-based Agents

$q$-exponential family for policy optimization

SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection

Do as We Do, Not as You Think: the Conformity of Large Language Models

Addressing Label Shift in Distributed Learning via Entropy Regularization

LIFe-GoM: Generalizable Human Rendering with Learned Iterative Feedback Over Multi-Resolution Gaussians-on-Mesh

PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs

Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data

The Labyrinth of Links: Navigating the Associative Maze of Multi-modal LLMs

Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions

Let Me Grok for You: Accelerating Grokking via Embedding Transfer from a Weaker Model

Talking Turns: Benchmarking Audio Foundation Models on Turn-Taking Dynamics

TIS-DPO: Token-level Importance Sampling for Direct Preference Optimization With Estimated Weights

ParaSolver: A Hierarchical Parallel Integral Solver for Diffusion Models

NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizer

Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning

Narrowing Information Bottleneck Theory for Multimodal Image-Text Representations Interpretability

Interaction Asymmetry: A General Principle for Learning Composable Abstractions

Cross-Entropy Is All You Need To Invert the Data Generating Process

Let the Code LLM Edit Itself When You Edit the Code

Learning to Generate Diverse Pedestrian Movements from Web Videos with Noisy Labels

In Search of Forgotten Domain Generalization

MetaUrban: An Embodied AI Simulation Platform for Urban Micromobility

FIG: Flow with Interpolant Guidance for Linear Inverse Problems

Towards Hierarchical Rectified Flow

SoundCTM: Unifying Score-based and Consistency Models for Full-band Text-to-Sound Generation

Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learning

Large Language Models are Interpretable Learners

AutoG: Towards automatic graph construction from tabular data

AHA: A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic Manipulation

Demystifying Online Clustering of Bandits: Enhanced Exploration Under Stochastic and Smoothed Adversarial Contexts

Grounding by Trying: LLMs with Reinforcement Learning-Enhanced Retrieval

Scalable Discrete Diffusion Samplers: Combinatorial Optimization and Statistical Physics

Perturbation-Restrained Sequential Model Editing

Not All Prompts Are Made Equal: Prompt-based Pruning of Text-to-Image Diffusion Models

Quality Measures for Dynamic Graph Generative Models

Injecting Universal Jailbreak Backdoors into LLMs in Minutes

VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesis

Reward Guided Latent Consistency Distillation

On Bits and Bandits: Quantifying the Regret-Information Trade-off

HD-Painter: High-Resolution and Prompt-Faithful Text-Guided Image Inpainting with Diffusion Models

Relax and Merge: A Simple Yet Effective Framework for Solving Fair $k$-Means and $k$-sparse Wasserstein Barycenter Problems

JudgeBench: A Benchmark for Evaluating LLM-Based Judges

SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models

To Tackle Adversarial Transferability: A Novel Ensemble Training Method with Fourier Transformation

Boosting Methods for Interval-censored Data with Regression and Classification

Multi-level Certified Defense Against Poisoning Attacks in Offline Reinforcement Learning

GridMix: Exploring Spatial Modulation for Neural Fields in PDE Modeling

Breaking Neural Network Scaling Laws with Modularity

Tractable Multi-Agent Reinforcement Learning through Behavioral Economics

ElasticTok: Adaptive Tokenization for Image and Video

World Model on Million-Length Video And Language With Blockwise RingAttention

RocketEval: Efficient automated LLM evaluation via grading checklist

Look Before You Leap: Universal Emergent Mechanism for Retrieval in Language Models

The Hidden Cost of Waiting for Accurate Predictions

Boosting Latent Diffusion with Perceptual Objectives

Do LLMs ``know'' internally when they follow instructions?

RelCon: Relative Contrastive Learning for a Motion Foundation Model for Wearable Data

EFFICIENT JAILBREAK ATTACK SEQUENCES ON LARGE LANGUAGE MODELS VIA MULTI-ARMED BANDIT-BASED CONTEXT SWITCHING

Diff3DS: Generating View-Consistent 3D Sketch via Differentiable Curve Rendering

Adaptive Length Image Tokenization via Recurrent Allocation

Diffusing States and Matching Scores: A New Framework for Imitation Learning

Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking

Positional Embeddings in Transformer Models: Evolution from Text to Vision Domains

Natural Language Inference Improves Compositionality in Vision-Language Models

Language models scale reliably with over-training and on downstream tasks

MMR: A Large-scale Benchmark Dataset for Multi-target and Multi-granularity Reasoning Segmentation

Diffusion-based Decoupled Deterministic and Uncertain Framework for Probabilistic Multivariate Time Series Forecasting

Episodic Novelty Through Temporal Distance

Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN

VICtoR: Learning Hierarchical Vision-Instruction Correlation Rewards for Long-horizon Manipulation

Fewer May Be Better: Enhancing Offline Reinforcement Learning with Reduced Dataset

Context-Alignment: Activating and Enhancing LLMs Capabilities in Time Series

ECD: A Machine Learning Benchmark for Predicting Enhanced-Precision Electronic Charge Density in Crystalline Inorganic Materials

Harnessing Diversity for Important Data Selection in Pretraining Large Language Models

Global Well-posedness and Convergence Analysis of Score-based Generative Models via Sharp Lipschitz Estimates

Domain Guidance: A Simple Transfer Approach for a Pre-trained Diffusion Model

VisualPredicator: Learning Abstract World Models with Neuro-Symbolic Predicates for Robot Planning

Linear Multistep Solver Distillation for Fast Sampling of Diffusion Models

BodyGen: Advancing Towards Efficient Embodiment Co-Design

ProtoSnap: Prototype Alignment For Cuneiform Signs

Weighted-Reward Preference Optimization for Implicit Model Fusion

BBCaL: Black-box Backdoor Detection under the Causality Lens

Reward Dimension Reduction for Scalable Multi-Objective Reinforcement Learning

Mind Control through Causal Inference: Predicting Clean Images from Poisoned Data

Equivariant Masked Position Prediction for Efficient Molecular Representation

Tree of Attributes Prompt Learning for Vision-Language Models

Decision Information Meets Large Language Models: The Future of Explainable Operations Research

Streaming Video Question-Answering with In-context Video KV-Cache Retrieval

Sitcom-Crafter: A Plot-Driven Human Motion Generation System in 3D Scenes

Explain Yourself, Briefly! Self-Explaining Neural Networks with Concise Sufficient Reasons

GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-Time Alignment

Out-of-distribution Generalization for Total Variation based Invariant Risk Minimization

SPD Attack - Prevention of AI Powered Image Editing by Image Immunization

CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion

Loopy: Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependency

Towards Bridging Generalization and Expressivity of Graph Neural Networks

Shared-AE: Automatic Identification of Shared Subspaces in High-dimensional Neural and Behavioral Activity

Medium-Difficulty Samples Constitute Smoothed Decision Boundary for Knowledge Distillation on Pruned Datasets

Value-aligned Behavior Cloning for Offline Reinforcement Learning via Bi-level Optimization

Physics-aligned field reconstruction with diffusion bridge

How to Find the Exact Pareto Front for Multi-Objective MDPs?

Hybrid Regularization Improves Diffusion-based Inverse Problem Solving

Broadening Target Distributions for Accelerated Diffusion Models via a Novel Analysis Approach

Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers

PEARL: Towards Permutation-Resilient LLMs

SymmetricDiffusers: Learning Discrete Diffusion on Finite Symmetric Groups

CaPo: Cooperative Plan Optimization for Efficient Embodied Multi-Agent Cooperation

OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data

HGM³: Hierarchical Generative Masked Motion Modeling with Hard Token Mining

G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model

MTU-Bench: A Multi-granularity Tool-Use Benchmark for Large Language Models

Logic-Logit: A Logic-Based Approach to Choice Modeling

Learning Evolving Tools for Large Language Models

Enhancing Compositional Text-to-Image Generation with Reliable Random Seeds

WorkflowLLM: Enhancing Workflow Orchestration Capability of Large Language Models

Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance

Robust Representation Consistency Model via Contrastive Denoising

Frequency-Guided Masking for Enhanced Vision Self-Supervised Learning

Tracing Representation Progression: Analyzing and Enhancing Layer-Wise Similarity

Robustness Reprogramming for Representation Learning

On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations

Understanding Constraint Inference in Safety-Critical Inverse Reinforcement Learning

Alchemy: Amplifying Theorem-Proving Capability Through Symbolic Mutation

Multi-Accurate CATE is Robust to Unknown Covariate Shifts

OpenPRM: Building Open-domain Process-based Reward Models with Preference Trees

Advancing LLM Reasoning Generalists with Preference Trees

NeuralPlane: Structured 3D Reconstruction in Planar Primitives with Neural Fields

Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models

Accelerating Inference of Retrieval-Augmented Generation via Sparse Context Selection

{$\tau$}-bench: A Benchmark for \underline{T}ool-\underline{A}gent-\underline{U}ser Interaction in Real-World Domains

QuaDiM: A Conditional Diffusion Model For Quantum State Property Estimation

Learning Interleaved Image-Text Comprehension in Vision-Language Large Models

ADIFF: Explaining audio difference using natural language

Taming Transformer Without Using Learning Rate Warmup

Towards a learning theory of representation alignment

Preference Diffusion for Recommendation

Fair Submodular Cover

Biologically Plausible Brain Graph Transformer

Real2Code: Reconstruct Articulated Objects via Code Generation

CertainlyUncertain: A Benchmark and Metric for Multimodal Epistemic and Aleatoric Awareness

BLEND: Behavior-guided Neural Population Dynamics Modeling via Privileged Knowledge Distillation

AI as Humanity’s Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text

$F^3Set$: Towards Analyzing Fast, Frequent, and Fine-grained Events from Videos

RecFlow: An Industrial Full Flow Recommendation Dataset

Towards a General Time Series Anomaly Detector with Adaptive Bottlenecks and Dual Adversarial Decoders

LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models

How Far Are We from True Unlearnability?

Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation

GaussianBlock: Building Part-Aware Compositional and Editable 3D Scene by Primitives and Gaussians

Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo

MoDeGPT: Modular Decomposition for Large Language Model Compression

Synthesizing Programmatic Reinforcement Learning Policies with Large Language Model Guided Search

Reflexive Guidance: Improving OoDD in Vision-Language Models via Self-Guided Image-Adaptive Concept Generation

W-PCA Based Gradient-Free Proxy for Efficient Search of Lightweight Language Models

CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL

A CLIP-Powered Framework for Robust and Generalizable Data Selection

Flat Reward in Policy Parameter Space Implies Robust Reinforcement Learning

Revisiting Convolution Architecture in the Realm of DNA Foundation Models

Can One Modality Model Synergize Training of Other Modality Models?

BiGR: Harnessing Binary Latent Codes for Image Generation and Improved Visual Representation Capabilities

Integral Performance Approximation for Continuous-Time Reinforcement Learning Control

Does Safety Training of LLMs Generalize to Semantically Related Natural Prompts?

SymmCD: Symmetry-Preserving Crystal Generation with Diffusion Models

A Formal Framework for Understanding Length Generalization in Transformers

How Much is a Noisy Image Worth? Data Scaling Laws for Ambient Diffusion.

Efficient Automated Circuit Discovery in Transformers using Contextual Decomposition

A Theoretically-Principled Sparse, Connected, and Rigid Graph Representation of Molecules

Learning Generalizable Skills from Offline Multi-Task Data for Multi-Agent Cooperation

Efficient Perplexity Bound and Ratio Matching in Discrete Diffusion Language Models

Iterative Substructure Extraction for Molecular Relational Learning with Interactive Graph Information Bottleneck

VideoGLUE: Video General Understanding Evaluation of Foundation Models

Utility-Directed Conformal Prediction: A Decision-Aware Framework for Actionable Uncertainty Quantification

Bridging the Semantic Gap Between Text and Table: A Case Study on NL2SQL

TIPS: Text-Image Pretraining with Spatial awareness

GPromptShield: Elevating Resilience in Graph Prompt Tuning Against Adversarial Attacks

Uncovering Overfitting in Large Language Model Editing

UniDrive: Towards Universal Driving Perception Across Camera Configurations

Context-aware Dynamic Pruning for Speech Foundation Models

ParetoFlow: Guided Flows in Multi-Objective Optimization

High-Dimensional Bayesian Optimisation with Gaussian Process Prior Variational Autoencoders

Autonomous Evaluation of LLMs for Truth Maintenance and Reasoning Tasks

TimeMixer++: A General Time Series Pattern Machine for Universal Predictive Analysis

Ambient Diffusion Posterior Sampling: Solving Inverse Problems with Diffusion Models Trained on Corrupted Data

HyperDAS: Towards Automating Mechanistic Interpretability with Hypernetworks

Beyond Model Collapse: Scaling Up with Synthesized Data Requires Verification

Online Reinforcement Learning in Non-Stationary Context-Driven Environments

Strong Model Collapse

Optimal Brain Apoptosis

Node-Time Conditional Prompt Learning in Dynamic Graphs

Autoregressive Video Generation without Vector Quantization

A Stochastic Approach to the Subset Selection Problem via Mirror Descent

GReaTer: Gradients Over Reasoning Makes Smaller Language Models Strong Prompt Optimizers

Masked Temporal Interpolation Diffusion for Procedure Planning in Instructional Videos

DEPT: Decoupled Embeddings for Pre-training Language Models

Agent-to-Sim: Learning Interactive Behavior Models from Casual Longitudinal Videos

MAPS: Advancing Multi-Modal Reasoning in Expert-Level Physical Science

Automated Proof Generation for Rust Code via Self-Evolution

Century: A Framework and Dataset for Evaluating Historical Contextualisation of Sensitive Images

Bridging Compressed Image Latents and Multimodal Large Language Models

Fast Feedforward 3D Gaussian Splatting Compression

Selective Label Enhancement Learning for Test-Time Adaptation

SANER: Annotation-free Societal Attribute Neutralizer for Debiasing CLIP

Towards Calibrated Deep Clustering Network

ConMix: Contrastive Mixup at Representation Level for Long-tailed Deep Clustering

ProAdvPrompter: A Two-Stage Journey to Effective Adversarial Prompting for LLMs

Growth Inhibitors for Suppressing Inappropriate Image Concepts in Diffusion Models

The OMG dataset: An Open MetaGenomic corpus for mixed-modality genomic language modeling

CATCH: Channel-Aware Multivariate Time Series Anomaly Detection via Frequency Patching

Exposure Bracketing Is All You Need For A High-Quality Image

GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning

BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks

Scaling Long Context Training Data by Long-Distance Referrals

Sample then Identify: A General Framework for Risk Control and Assessment in Multimodal Large Language Models

FedLWS: Federated Learning with Adaptive Layer-wise Weight Shrinking

DRL: Decomposed Representation Learning for Tabular Anomaly Detection

Gaussian-Based Instance-Adaptive Intensity Modeling for Point-Supervised Facial Expression Spotting

FlowDec: A flow-based full-band general audio codec with high perceptual quality

MuseGNN: Forming Scalable, Convergent GNN Layers that Minimize a Sampling-Based Energy

Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Design

AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents

AutoBencher: Towards Declarative Benchmark Construction

Avoid Overclaims: Summary of Complexity Bounds for Algorithms in Minimization and Minimax Optimization

On the Identification of Temporal Causal Representation with Instantaneous Dependence

Poison-splat: Computation Cost Attack on 3D Gaussian Splatting

FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"

Robots Pre-train Robots: Manipulation-Centric Robotic Representation from Large-Scale Robot Datasets

Multi-Label Node Classification with Label Influence Propagation

StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization

Generalizing Weisfeiler-Lehman Kernels to Subgraphs

Digi-Q: Learning VLM Q-Value Functions for Training Device-Control Agents

CtrLoRA: An Extensible and Efficient Framework for Controllable Image Generation

ELFS: Label-Free Coreset Selection with Proxy Training Dynamics

Dreamweaver: Learning Compositional World Models from Pixels

On LLM Knowledge Distillation - A Comparison between Forward KL and Reverse KL

Longhorn: State Space Models are Amortized Online Learners

On the Hölder Stability of Multiset and Graph Neural Networks

Uncertainty and Influence aware Reward Model Refinement for Reinforcement Learning from Human Feedback

3D StreetUnveiler with Semantic-aware 2DGS - a simple baseline

PivotMesh: Generic 3D Mesh Generation via Pivot Vertices Guidance

EMOS: Embodiment-aware Heterogeneous Multi-robot Operating System with LLM Agents

Scaling Stick-Breaking Attention: An Efficient Implementation and In-depth Study

Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models

Free Hunch: Denoiser Covariance Estimation for Diffusion Models Without Extra Costs

Scale-Aware Contrastive Reverse Distillation for Unsupervised Medical Anomaly Detection

Generalized Principal-Agent Problem with a Learning Agent

Innovative Thinking, Infinite Humor: Humor Research of Large Language Models through Structured Thought Leaps

Near-optimal Active Regression of Single-Index Models

Few for Many: Tchebycheff Set Scalarization for Many-Objective Optimization

Let Your Features Tell The Differences: Understanding Graph Convolution By Feature Splitting

Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains

AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark

Planning Anything with Rigor: General-Purpose Zero-Shot Planning with LLM-based Formalized Programming

Truncated Consistency Models

Heavy-Tailed Diffusion Models

Energy-Based Diffusion Language Models for Text Generation

Think while You Generate: Discrete Diffusion with Planned Denoising

LocoVR: Multiuser Indoor Locomotion Dataset in Virtual Reality

Quantized Spike-driven Transformer

Can Watermarked LLMs be Identified by Users via Crafted Prompts?

Persistent Pre-training Poisoning of LLMs

Backtracking Improves Generation Safety

Human-Aligned Chess With a Bit of Search

What Are Good Positional Encodings for Directed Graphs?

Consistent Flow Distillation for Text-to-3D Generation

3D-AffordanceLLM: Harnessing Large Language Models for Open-Vocabulary Affordance Detection in 3D Worlds

From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions

Step-by-Step Reasoning for Math Problems via Twisted Sequential Monte Carlo

Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation Models

DisEnvisioner: Disentangled and Enriched Visual Prompt for Customized Image Generation

Looped Transformers for Length Generalization

A Theoretical Perspective: How to Prevent Model Collapse in Self-consuming Training Loops

Efficient Reward Poisoning Attacks on Online Deep Reinforcement Learning

Language Models Need Inductive Biases to Count Inductively

CLDyB: Towards Dynamic Benchmarking for Continual Learning with Pre-trained Models

Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuning

SD-LoRA: Scalable Decoupled Low-Rank Adaptation for Class Incremental Learning

VideoWebArena: Evaluating Long Context Multimodal Agents with Video Understanding Web Tasks

Learning-Guided Rolling Horizon Optimization for Long-Horizon Flexible Job-Shop Scheduling

GravMAD: Grounded Spatial Value Maps Guided Action Diffusion for Generalized 3D Manipulation

MADGEN: Mass-Spec attends to De Novo Molecular generation

Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models

MELODI: Exploring Memory Compression for Long Contexts

How Discrete and Continuous Diffusion Meet: Comprehensive Analysis of Discrete Diffusion Models via a Stochastic Integral Framework

Better autoregressive regression with LLMs via regression-aware fine-tuning

A Simple Approach to Unifying Diffusion-based Conditional Generation

PT-T2I/V: An Efficient Proxy-Tokenized Diffusion Transformer for Text-to-Image/Video-Task

ODE-based Smoothing Neural Network for Reinforcement Learning Tasks

Efficient Learning with Sine-Activated Low-Rank Matrices

Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity

Group Distributionally Robust Dataset Distillation with Risk Minimization

Proactive Privacy Amnesia for Large Language Models: Safeguarding PII with Negligible Impact on Model Utility

Can In-context Learning Really Generalize to Out-of-distribution Tasks?

Rethinking Invariance in In-context Learning

What is Wrong with Perplexity for Long-context Language Modeling?

Scaling Offline Model-Based RL via Jointly-Optimized World-Action Model Pretraining

Conformal Prediction Sets Can Cause Disparate Impact

TFG-Flow: Training-free Guidance in Multimodal Generative Flow

Infinite-Resolution Integral Noise Warping for Diffusion Models

Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-Faithfulness

MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers

RazorAttention: Efficient KV Cache Compression Through Retrieval Heads

Residual Kernel Policy Network: Enhancing Stability and Robustness in RKHS-Based Reinforcement Learning

Unposed Sparse Views Room Layout Reconstruction in the Age of Pretrain Model

Unifying Unsupervised Graph-Level Anomaly Detection and Out-of-Distribution Detection: A Benchmark

Doubly robust identification of treatment effects from multiple environments

Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-Based Decision-Making Systems

Enhancing Federated Domain Adaptation with Multi-Domain Prototype-Based Federated Fine-Tuning

Re-Imagining Multimodal Instruction Tuning: A Representation View

Graph-Guided Scene Reconstruction from Images with 3D Gaussian Splatting

Dynamic Diffusion Transformer

Bridging the Gap between Database Search and \emph{De Novo} Peptide Sequencing with SearchNovo

ReNovo: Retrieval-Based \emph{De Novo} Mass Spectrometry Peptide Sequencing

Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction

Factor Graph-based Interpretable Neural Networks

The adaptive complexity of parallelized log-concave sampling

Improved Approximation Algorithms for $k$-Submodular Maximization via Multilinear Extension

Progressive Parameter Efficient Transfer Learning for Semantic Segmentation

The Crucial Role of Samplers in Online Direct Preference Optimization

I2VControl-Camera: Precise Video Camera Control with Adjustable Motion Strength

Reinforcement Learning from Imperfect Corrective Actions and Proxy Rewards

The Crystal Ball Hypothesis in diffusion models: Anticipating object positions from initial noise

BenTo: Benchmark Reduction with In-Context Transferability

Is Your Multimodal Language Model Oversensitive to Safe Queries?

Many-Objective Multi-Solution Transport

Earlier Tokens Contribute More: Learning Direct Preference Optimization From Temporal Decay Perspective

Integrating Protein Dynamics into Structure-Based Drug Design via Full-Atom Stochastic Flows

Group Ligands Docking to Protein Pockets

ProteinBench: A Holistic Evaluation of Protein Foundation Models

Enhancing Prediction Performance through Influence Measure

Point Cluster: A Compact Message Unit for Communication-Efficient Collaborative Perception

Dense Video Object Captioning from Disjoint Supervision

A Robust Method to Discover Causal or Anticausal Relation

N-ForGOT: Towards Not-forgetting and Generalization of Open Temporal Graph Learning

HiSplat: Hierarchical 3D Gaussian Splatting for Generalizable Sparse-View Reconstruction

UniGS: Unified Language-Image-3D Pretraining with Gaussian Splatting

CryoFM: A Flow-based Foundation Model for Cryo-EM Densities

Anyprefer: An Agentic Framework for Preference Data Synthesis

Fine-Grained Verifiers: Preference Modeling as Next-token Prediction in Vision-Language Alignment

MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models

Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models

Routing Experts: Learning to Route Dynamic Experts in Existing Multi-modal Large Language Models

$\gamma-$MoD: Exploring Mixture-of-Depth Adaptation for Multimodal Large Language Models

DiffPC: Diffusion-based High Perceptual Fidelity Image Compression with Semantic Refinement

UniMatch: Universal Matching from Atom to Task for Few-Shot Drug Discovery

Learning LLM-as-a-Judge for Preference Alignment

BitStack: Any-Size Compression of Large Language Models in Variable Memory Environments

Data Mixing Laws: Optimizing Data Mixtures by Predicting Language Modeling Performance

Towards Universality: Studying Mechanistic Similarity Across Language Model Architectures

HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing

MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine

Reliable and Diverse Evaluation of LLM Medical Knowledge Mastery

On the Role of Attention Heads in Large Language Model Safety

WeatherGFM: Learning a Weather Generalist Foundation Model via In-context Learning

CARTS: Advancing Neural Theorem Proving with Diversified Tactic Calibration and Bias-Resistant Tree Search

Circuit Representation Learning with Masked Gate Modeling and Verilog-AIG Alignment

The Lottery LLM Hypothesis, Rethinking What Abilities Should LLM Compression Preserve?

STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs

Learning Graph Quantized Tokenizers

Motion Control of High-Dimensional Musculoskeletal Systems with Hierarchical Model-Based Planning

Stealthy Shield Defense: A Conditional Mutual Information-Based Approach against Black-Box Model Inversion Attacks

PathGen-1.6M: 1.6 Million Pathology Image-text Pairs Generation through Multi-agent Collaboration

BadRobot: Jailbreaking Embodied LLM Agents in the Physical World

Hyper-Connections

Ultra-Sparse Memory Network

Re-Aligning Language to Visual Objects with an Agentic Workflow

DSPO: Direct Score Preference Optimization for Diffusion Model Alignment

On Quantizing Neural Representation for Variable-Rate Video Coding

From Decoupling to Adaptive Transformation: a Wider Optimization Space for PTQ

Towards Effective Evaluations and Comparisons for LLM Unlearning Methods

Inverse Rendering using Multi-Bounce Path Tracing and Reservoir Sampling

An Intelligent Agentic System for Complex Image Restoration Problems

Scaling Large Language Model-based Multi-Agent Collaboration

Toward Efficient Multi-Agent Exploration With Trajectory Entropy Maximization

VideoGrain: Modulating Space-Time Attention for Multi-Grained Video Editing

Long-horizon Visual Instruction Generation with Logic and Attribute Self-reflection

Less is More: Masking Elements in Image Condition Features Avoids Content Leakages in Style Transfer Diffusion Models

Noisy Test-Time Adaptation in Vision-Language Models

When Prompt Engineering Meets Software Engineering: CNL-P as Natural and Robust "APIs'' for Human-AI Interaction

An Empirical Analysis of Uncertainty in Large Language Model Evaluations

Towards Out-of-Modal Generalization without Instance-level Modal Correspondence

Quantifying Generalization Complexity for Large Language Models

PixWizard: Versatile Image-to-Image Visual Assistant with Open-Language Instructions

LLaVA-MoD: Making LLaVA Tiny via MoE-Knowledge Distillation

AgentRefine: Enhancing Agent Generalization through Refinement Tuning

CS-Bench: A Comprehensive Benchmark for Large Language Models towards Computer Science Mastery

MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detection

Vision Language Models are In-Context Value Learners

DynFrs: An Efficient Framework for Machine Unlearning in Random Forest

SigDiffusions: Score-Based Diffusion Models for Time Series via Log-Signature Embeddings

TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data

Asymmetric Factorized Bilinear Operation for Vision Transformer

Efficient Masked AutoEncoder for Video Object Counting and A Large-Scale Benchmark

DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search

DUET: Decentralized Bilevel Optimization without Lower-Level Strong Convexity

Multi-Reward as Condition for Instruction-based Image Editing

A Tight Convergence Analysis of Inexact Stochastic Proximal Point Algorithm for Stochastic Composite Optimization Problems

LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs

A Benchmark for Semantic Sensitive Information in LLMs Outputs

Evaluating Semantic Variation in Text-to-Image Synthesis: A Causal Perspective

Data Center Cooling System Optimization Using Offline Reinforcement Learning

ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation

Lipschitz Bandits in Optimal Space

TEASER: Token Enhanced Spatial Modeling for Expressions Reconstruction

INFER: A Neural-symbolic Model For Extrapolation Reasoning on Temporal Knowledge Graph

Generalizability of Neural Networks Minimizing Empirical Risk Based on Expressive Power

Provable Robust Overfitting Mitigation in Wasserstein Distributionally Robust Optimization

Complementary Label Learning with Positive Label Guessing and Negative Label Enhancement

InstaRevive: One-Step Image Enhancement via Dynamic Score Matching

Physics of Language Models: Part 3.2, Knowledge Manipulation

Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws

Unhackable Temporal Reward for Scalable Video MLLMs

GROOT-2: Weakly Supervised Multimodal Instruction Following Agents

Knowledge Graph Finetuning Enhances Knowledge Manipulation in Large Language Models

Computing Circuits Optimization via Model-Based Circuit Genetic Evolution

A Graph Enhanced Symbolic Discovery Framework For Efficient Logic Optimization

Beyond Content Relevance: Evaluating Instruction Following in Retrieval Models

Uni-Sign: Toward Unified Sign Language Understanding at Scale

RMB: Comprehensively benchmarking reward models in LLM alignment

Proving Olympiad Inequalities by Synergizing LLMs and Symbolic Reasoning

Jailbreaking as a Reward Misspecification Problem

Vevo: Controllable Zero-Shot Voice Imitation with Self-Supervised Disentanglement

MagicPIG: LSH Sampling for Efficient LLM Generation

D-FINE: Redefine Regression Task of DETRs as Fine-grained Distribution Refinement

Incremental Causal Effect for Time to Treatment Initialization

Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent

Graph Neural Ricci Flow: Evolving Feature from a Curvature Perspective

On Designing General and Expressive Quantum Graph Neural Networks with Applications to MILP Instance Representation

OmniBind: Large-scale Omni Multimodal Representation via Binding Spaces

OmniSep: Unified Omni-Modality Sound Separation with Query-Mixup

On the Completeness of Invariant Geometric Deep Learning Models

MixEval-X: Any-to-any Evaluations from Real-world Data Mixture

RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction

Entropy-based Activation Function Optimization: A Method on Searching Better Activation Functions

BigDocs: An Open Dataset for Training Multimodal Models on Document and Code Tasks

From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMs

Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning Process

Physics of Language Models: Part 2.2, How to Learn From Mistakes on Grade-School Math Problems

Retrieval Augmented Diffusion Model for Structure-informed Antibody Design and Optimization

Humanizing the Machine: Proxy Attacks to Mislead LLM Detectors

Montessori-Instruct: Generate Influential Training Data Tailored for Student Learning

Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimization

Episodic Memories Generation and Evaluation Benchmark for Large Language Models

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners

Sort-free Gaussian Splatting via Weighted Sum Rendering

Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling

STAR: Stability-Inducing Weight Perturbation for Continual Learning

OmnixR: Evaluating Omni-modality Language Models on Reasoning across Modalities

Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language Models

OMG: Opacity Matters in Material Modeling with Gaussian Splatting

Preble: Efficient Distributed Prompt Scheduling for LLM Serving

Learning Hierarchical Polynomials of Multiple Nonlinear Features

Is Your Model Really A Good Math Reasoner? Evaluating Mathematical Reasoning with Checklist

Understanding Matrix Function Normalizations in Covariance Pooling through the Lens of Riemannian Geometry

Gyrogroup Batch Normalization

Convergence of Distributed Adaptive Optimization with Local Updates

Do Egocentric Video-Language Models Truly Understand Hand-Object Interactions?

ZeroDiff: Solidified Visual-semantic Correlation in Zero-Shot Learning

Rodimus*: Breaking the Accuracy-Efficiency Trade-Off with Efficient Attentions

GrabS: Generative Embodied Agent for 3D Object Segmentation without Scene Supervision

Hymba: A Hybrid-head Architecture for Small Language Models

OBI-Bench: Can LMMs Aid in Study of Ancient Script on Oracle Bones?

QP-SNN: Quantized and Pruned Spiking Neural Networks

LaMPlace: Learning to Optimize Cross-Stage Metrics in Macro Placement

Differentiable Integer Linear Programming

Accelerating Neural ODEs: A Variational Formulation-based Approach

Text2PDE: Latent Diffusion Models for Accessible Physics Simulation

Self-Evolving Multi-Agent Collaboration Networks for Software Development

Monte Carlo Planning with Large Language Model for Text-Based Game Agents

Why RoPE Struggles to Maintain Long-Term Decay in Long Sequences?

TidalDecode: Fast and Accurate LLM Decoding with Position Persistent Sparse Attention

Solving New Tasks by Adapting Internet Video Knowledge

Have the VLMs Lost Confidence? A Study of Sycophancy in VLMs

Intervening Anchor Token: Decoding Strategy in Alleviating Hallucinations for MLLMs

Neuralized Markov Random Field for Interaction-Aware Stochastic Human Trajectory Prediction

Post-hoc Reward Calibration: A Case Study on Length Bias

Layerwise Recurrent Router for Mixture-of-Experts

Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation

DeciMamba: Exploring the Length Extrapolation Potential of Mamba

Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence

On the Byzantine-Resilience of Distillation-Based Federated Learning

Preserving Diversity in Supervised Fine-Tuning of Large Language Models

Understanding and Mitigating Hallucination in Large Vision-Language Models via Modular Attribution and Intervention

Adam-mini: Use Fewer Learning Rates To Gain More

Learning to Adapt Frozen CLIP for Few-Shot Test-Time Domain Adaptation

As Simple as Fine-tuning: LLM Alignment via Bidirectional Negative Feedback Loss

Multiple Heads are Better than One: Mixture of Modality Knowledge Experts for Entity Representation Learning

LoRA3D: Low-Rank Self-Calibration of 3D Geometric Foundation models

Combatting Dimensional Collapse in LLM Pre-Training Data via Submodular File Selection

Aligning Generative Denoising with Discriminative Objectives Unleashes Diffusion for Visual Perception

Eliminating Position Bias of Language Models: A Mechanistic Approach

Query-based Knowledge Transfer for Heterogeneous Learning Environments

SEBRA : Debiasing through Self-Guided Bias Ranking

STAMP: Scalable Task- And Model-agnostic Collaborative Perception

A Statistical Approach for Controlled Training Data Detection

GS-CPR: Efficient Camera Pose Refinement via 3D Gaussian Splatting

Automatic Curriculum Expert Iteration for Reliable LLM Reasoning

Advancing Mathematical Reasoning in Language Models: The Impact of Problem-Solving Data, Data Synthesis Methods, and Training Stages

Synthetic continued pretraining

ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery

Kronecker Mask and Interpretive Prompts are Language-Action Video Learners

Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting

Rethinking Light Decoder-based Solvers for Vehicle Routing Problems

Relaxed Recursive Transformers: Effective Parameter Sharing with Layer-wise LoRA

ThinkBot: Embodied Instruction Following with Thought Chain Reasoning

EmbodiedSAM: Online Segment Any 3D Thing in Real Time

Strong Preferences Affect the Robustness of Preference Models and Value Alignment

Breach By A Thousand Leaks: Unsafe Information Leakage in 'Safe' AI Responses

Teaching LLMs How to Learn with Contextual Fine-Tuning

Planning in Natural Language Improves LLM Search for Code Generation

BinaryDM: Accurate Weight Binarization for Efficient Diffusion Models

A Theoretical Analysis of Self-Supervised Learning for Vision Transformers

Open-Vocabulary Customization from CLIP via Data-Free Knowledge Distillation

Bayesian WeakS-to-Strong from Text Classification to Generation

Debiasing Federated Learning with Correlated Client Participation

TOMATO: Assessing Visual Temporal Reasoning Capabilities in Multimodal Foundation Models

Towards counterfactual fairness through auxiliary variables

SG-I2V: Self-Guided Trajectory Control in Image-to-Video Generation

WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling

Improving Neural Optimal Transport via Displacement Interpolation

Towards Continuous Reuse of Graph Models via Holistic Memory Diversification

SleepSMC: Ubiquitous Sleep Staging via Supervised Multimodal Coordination

EqNIO: Subequivariant Neural Inertial Odometry

OmniRe: Omni Urban Scene Reconstruction

EG4D: Explicit Generation of 4D Object without Score Distillation

Unsupervised Disentanglement of Content and Style via Variance-Invariance Constraints

DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search

Cauchy-Schwarz Regularizers

Hypothetical Minds: Scaffolding Theory of Mind for Multi-Agent Tasks with Large Language Models

T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching

PaRa: Personalizing Text-to-Image Diffusion via Parameter Rank Reduction

mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models

INS: Interaction-aware Synthesis to Enhance Offline Multi-agent Reinforcement Learning

A Periodic Bayesian Flow for Material Generation

MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer

SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration

FlexCAD: Unified and Versatile Controllable CAD Generation with Fine-tuned Large Language Models

Don't Take Things Out of Context: Attention Intervention for Enhancing Chain-of-Thought Reasoning in Large Language Models

Improving Complex Reasoning with Dynamic Prompt Corruption: A Soft Prompt Optimization Approach

Constraint-Conditioned Actor-Critic for Offline Safe Reinforcement Learning

Language Model Alignment in Multilingual Trolley Problems

Visual Description Grounding Reduces Hallucinations and Boosts Reasoning in LVLMs

Structural-Entropy-Based Sample Selection for Efficient and Effective Learning

Diffusion$^2$: Dynamic 3D Content Generation via Score Composition of Video and Multi-view Diffusion Models

Discriminator-Guided Embodied Planning for LLM Agent

Controllable Unlearning for Image-to-Image Generative Models via $\epsilon$-Constrained Optimization

Cyclic Contrastive Knowledge Transfer for Open-Vocabulary Object Detection

Multi-Resolution Decomposable Diffusion Model for Non-Stationary Time Series Anomaly Detection

DisPose: Disentangling Pose Guidance for Controllable Human Image Animation

LaMP: Language-Motion Pretraining for Motion Generation, Retrieval, and Captioning

VoxDialogue: Can Spoken Dialogue Systems Understand Information Beyond Words?

Mixture-of-Agents Enhances Large Language Model Capabilities

Scaling Instruction-tuned LLMs to Million-token Contexts via Hierarchical Synthetic Data Generation

Train Small, Infer Large: Memory-Efficient LoRA Training for Large Language Models

CLIPDrag: Combining Text-based and Drag-based Instructions for Image Editing

CollabEdit: Towards Non-destructive Collaborative Knowledge Editing

Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understanding

Tool-Planner: Task Planning with Clusters across Multiple Tools

Small Models are LLM Knowledge Triggers for Medical Tabular Prediction

Greener GRASS: Enhancing GNNs with Encoding, Rewiring, and Attention

Graph Transformers Dream of Electric Flow

On Statistical Rates of Conditional Diffusion Transformers: Approximation, Estimation and Minimax Optimality

Learning Equivariant Non-Local Electron Density Functionals

Can Transformers Do Enumerative Geometry?

No Equations Needed: Learning System Dynamics Without Relying on Closed-Form ODEs

Zero-shot forecasting of chaotic systems

Associative memory and dead neurons

Foundation Models Secretly Understand Neural Network Weights: Enhancing Hypernetwork Architectures with Foundation Models

Generation and Comprehension Hand-in-Hand: Vision-guided Expression Diffusion for Boosting Referring Expression Generation and Comprehension

3DGS-Drag: Dragging Gaussians for Intuitive Point-Based 3D Editing

Sketch2Diagram: Generating Vector Diagrams from Hand-Drawn Sketches

Latent Radiance Fields with 3D-aware 2D Representations

Learning Color Equivariant Representations

CHAMP: Conformalized 3D Human Multi-Hypothesis Pose Estimators

RESfM: Robust Deep Equivariant Structure from Motion

Empowering Users in Digital Privacy Management through Interactive LLM-Based Agents

Smoothing the Shift: Towards Stable Test-Time Adaptation under Complex Multimodal Noises

BP-Modified Local Loss for Efficient Training of Deep Neural Networks

Basis Sharing: Cross-Layer Parameter Sharing for Large Language Model Compression

Are Large Vision Language Models Good Game Players?

Neural Phylogeny: Fine-Tuning Relationship Detection among Neural Networks

Your Mixture-of-Experts LLM Is Secretly an Embedding Model for Free

DOCS: Quantifying Weight Similarity for Deeper Insights into Large Language Models

BadJudge: Backdoor Vulnerabilities of LLM-As-A-Judge

Improving Neural Network Accuracy by Concurrently Training with a Twin Network

Democratic Training Against Universal Adversarial Perturbations

Severing Spurious Correlations with Data Pruning

Provably Reliable Conformal Prediction Sets in the Presence of Data Poisoning

The "Law'' of the Unconscious Contrastive Learner: Probabilistic Alignment of Unpaired Modalities

Bayesian Treatment of the Spectrum of the Empirical Kernel in (Sub)Linear-Width Neural Networks

Oscillatory State-Space Models

Two Sparse Matrices are Better than One: Sparsifying Neural Networks with Double Sparse Factorization

Designing Concise ConvNets with Columnar Stages

Sharpness-Aware Minimization: General Analysis and Improved Rates

Local convergence of simultaneous min-max algorithms to differential equilibrium on Riemannian manifold

Policy Optimization under Imperfect Human Interactions with Agent-Gated Shared Autonomy

Simple, Good, Fast: Self-Supervised World Models Free of Baggage

CBMA: Improving Conformal Prediction through Bayesian Model Averaging

End-to-end Learning of Gaussian Mixture Priors for Diffusion Sampler

Connecting Federated ADMM to Bayes

Training One-Dimensional Graph Neural Networks is NP-Hard

On the Optimal Memorization Capacity of Transformers

Efficient Online Pruning and Abstraction for Imperfect Information Extensive-Form Games

Strategic Classification With Externalities

Bounds on $L_p$ Errors in Density Ratio Estimation via $f$-Divergence Loss Functions

Conservative Contextual Bandits: Beyond Linear Representations

Linear Bandits with Memory

Do Stochastic, Feel Noiseless: Stable Stochastic Optimization via a Double Momentum Mechanism

Reexamining the Aleatoric and Epistemic Uncertainty Dichotomy

Generalizable Motion Planning via Operator Learning

ADAM: An Embodied Causal Agent in Open-World Environments

Euler Characteristic Tools for Topological Data Analysis

Neural networks on Symmetric Spaces of Noncompact Type

Exact Community Recovery under Side Information: Optimality of Spectral Algorithms

Content-Style Learning from Unaligned Domains: Identifiability under Unknown Latent Dimensions

Let SSMs be ConvNets: State-space Modeling with Optimal Tensor Contractions

Learning from End User Data with Shuffled Differential Privacy over Kernel Densities

How to Verify Any (Reasonable) Distribution Property: Computationally Sound Argument Systems for Distributions

ConceptPrune: Concept Editing in Diffusion Models via Skilled Neuron Pruning

Deep MMD Gradient Flow without adversarial training

How Feature Learning Can Improve Neural Scaling Laws

Understanding Factual Recall in Transformers via Associative Memories

ViBiDSampler: Enhancing Video Interpolation Using Bidirectional Diffusion Sampler

Multi-LLM-Agents Debate - Performance, Efficiency, and Scaling Challenges

RTDiff: Reverse Trajectory Synthesis via Diffusion for Offline Reinforcement Learning

Small-to-Large Generalization: Training Data Influences Models Consistently Across Scale

Exploring The Forgetting in Adversarial Training: A Novel Method for Enhancing Robustness

Do LLM Agents Have Regret? A Case Study in Online Learning and Games

Can LLM Simulations Truly Reflect Humanity? A Deep Dive

Compute-Constrained Data Selection

Multi-objective antibody design with constrained preference optimization

Linear SCM Identification in the Presence of Confounders and Gaussian Noise

No Location Left Behind: Measuring and Improving the Fairness of Implicit Representations for Earth Data