ICLR 2024 Papers

mini compact topic detail

Robot Fleet Learning via Policy Merging

GNNCert: Deterministic Certification of Graph Neural Networks against Adversarial Perturbations

Eureka: Human-Level Reward Design via Coding Large Language Models

Oracle Efficient Algorithms for Groupwise Regret

Self-Guided Masked Autoencoders for Domain-Agnostic Self-Supervised Learning

Topic Modeling as Multi-Objective Contrastive Optimization

Principled Architecture-aware Scaling of Hyperparameters

Set Learning for Accurate and Calibrated Models

T-MARS: Improving Visual Representations by Circumventing Text Feature Learning

Diffusion Sampling with Momentum for Mitigating Divergence Artifacts

PROGRAM: PROtotype GRAph Model based Pseudo-Label Learning for Test-Time Adaptation

LOQA: Learning with Opponent Q-Learning Awareness

Online Stabilization of Spiking Neural Networks

Meta Continual Learning Revisited: Implicitly Enhancing Online Hessian Approximation via Variance Reduction

Blending Imitation and Reinforcement Learning for Robust Policy Improvement

In-Context Learning Learns Label Relationships but Is Not Conventional Learning

Latent Trajectory Learning for Limited Timestamps under Distribution Shift over Time

ConR: Contrastive Regularizer for Deep Imbalanced Regression

Label-Noise Robust Diffusion Models

Exploring the cloud of feature interaction scores in a Rashomon set

Unveiling the Unseen: Identifiable Clusters in Trained Depthwise Convolutional Kernels

A Simple Romance Between Multi-Exit Vision Transformer and Token Reduction

Sign2GPT: Leveraging Large Language Models for Gloss-Free Sign Language Translation

Learning to Compose: Improving Object Centric Learning by Injecting Compositionality

Equivariant Matrix Function Neural Networks

Sparsistency for inverse optimal transport

Towards Poisoning Fair Representations

Order-Preserving GFlowNets

Zipformer: A faster and better encoder for automatic speech recognition

Looped Transformers are Better at Learning Learning Algorithms

Boosting Graph Anomaly Detection with Adaptive Message Passing

Towards Lossless Dataset Distillation via Difficulty-Aligned Trajectory Matching

MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models

Rethinking the Benefits of Steerable Features in 3D Equivariant Graph Neural Networks

Forward $\chi^2$ Divergence Based Variational Importance Sampling

NoiseDiffusion: Correcting Noise for Image Interpolation with Diffusion Models beyond Spherical Linear Interpolation

Effective Data Augmentation With Diffusion Models

Incremental Randomized Smoothing Certification

Training Graph Transformers via Curriculum-Enhanced Attention Distillation

FITS: Modeling Time Series with $10k$ Parameters

Robust Training of Federated Models with Extremely Label Deficiency

Towards Green AI in Fine-tuning Large Language Models via Adaptive Backpropagation

Continuous Field Reconstruction from Sparse Observations with Implicit Neural Networks

DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion Models

Robust agents learn causal world models

The Effect of Intrinsic Dataset Properties on Generalization: Unraveling Learning Differences Between Natural and Medical Images

Scaling Convex Neural Networks with Burer-Monteiro Factorization

Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach

Robust Model Based Reinforcement Learning Using $\mathcal{L}_1$ Adaptive Control

GeneOH Diffusion: Towards Generalizable Hand-Object Interaction Denoising via Denoising Diffusion

Reward Model Ensembles Help Mitigate Overoptimization

Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks

Near-Optimal Solutions of Constrained Learning Problems

PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback

Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX

Denoising Diffusion via Image-Based Rendering

MMD Graph Kernel: Effective Metric Learning for Graphs via Maximum Mean Discrepancy

On the Hardness of Online Nonconvex Optimization with Single Oracle Feedback

Weaker MVI Condition: Extragradient Methods with Multi-Step Exploration

Domain Randomization via Entropy Maximization

Constraint-Free Structure Learning with Smooth Acyclic Orientations

SEABO: A Simple Search-Based Method for Offline Imitation Learning

Duolando: Follower GPT with Off-Policy Reinforcement Learning for Dance Accompaniment

Consistent4D: Consistent 360° Dynamic Object Generation from Monocular Video

The Reversal Curse: LLMs trained on “A is B” fail to learn “B is A”

Identifying the Risks of LM Agents with an LM-Emulated Sandbox

On Bias-Variance Alignment in Deep Models

InstructDET: Diversifying Referring Object Detection with Generalized Instructions

Patched Denoising Diffusion Models For High-Resolution Image Synthesis

Teach LLMs to Phish: Stealing Private Information from Language Models

Customizable Combination of Parameter-Efficient Modules for Multi-Task Learning

How Do Transformers Learn In-Context Beyond Simple Functions? A Case Study on Learning with Representations

Noise-free Score Distillation

AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning

Efficient Integrators for Diffusion Generative Models

AttEXplore: Attribution for Explanation with model parameters eXploration

Symmetric Basis Convolutions for Learning Lagrangian Fluid Mechanics

You Only Query Once: An Efficient Label-Only Membership Inference Attack

The Marginal Value of Momentum for Small Learning Rate SGD

Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!

CLIP the Bias: How Useful is Balancing Data in Multimodal Learning?

DreamLLM: Synergistic Multimodal Comprehension and Creation

AffineQuant: Affine Transformation Quantization for Large Language Models

On the Power of the Weisfeiler-Leman Test for Graph Motif Parameters

Multisize Dataset Condensation

MVDream: Multi-view Diffusion for 3D Generation

Graph-based Virtual Sensing from Sparse and Partial Multivariate Observations

Point2SSM: Learning Morphological Variations of Anatomies from Point Clouds

Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation

ZeroFlow: Scalable Scene Flow via Distillation

Leftover Lunch: Advantage-based Offline Reinforcement Learning for Language Models

Gradual Optimization Learning for Conformational Energy Minimization

Communication-Efficient Gradient Descent-Accent Methods for Distributed Variational Inequalities: Unified Analysis and Local Updates

Post-hoc bias scoring is optimal for fair classification

Conditional Information Bottleneck Approach for Time Series Imputation

Reasoning with Latent Diffusion in Offline Reinforcement Learning

COSA: Concatenated Sample Pretrained Vision-Language Foundation Model

FedWon: Triumphing Multi-domain Federated Learning Without Normalization

Grokking as the transition from lazy to rich training dynamics

Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo

Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing

QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models

InfoCon: Concept Discovery with Generative and Discriminative Informativeness

Sparse Autoencoders Find Highly Interpretable Features in Language Models

Fixed Non-negative Orthogonal Classifier: Inducing Zero-mean Neural Collapse with Feature Dimension Separation

Self-supervised Representation Learning from Random Data Projectors

Dual-Encoders for Extreme Multi-label Classification

Privileged Sensing Scaffolds Reinforcement Learning

Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation

Neural Auto-designer for Enhanced Quantum Kernels

Fully Hyperbolic Convolutional Neural Networks for Computer Vision

Cameras as Rays: Pose Estimation via Ray Diffusion

Open-ended VQA benchmarking of Vision-Language models by exploiting Classification datasets and their semantic hierarchy

Adversarial Supervision Makes Layout-to-Image Diffusion Models Thrive

ResFields: Residual Neural Fields for Spatiotemporal Signals

AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors

Prompt Gradient Projection for Continual Learning

Vision-by-Language for Training-Free Compositional Image Retrieval

Parallelizing non-linear sequential models over the sequence length

Single Motion Diffusion

Group Preference Optimization: Few-Shot Alignment of Large Language Models

DeepSPF: Spherical SO(3)-Equivariant Patches for Scan-to-CAD Estimation

Cleanba: A Reproducible and Efficient Distributed Reinforcement Learning Platform

SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs

Feature Collapse

WOODS: Benchmarks for Out-of-Distribution Generalization in Time Series

HypeBoy: Generative Self-Supervised Representation Learning on Hypergraphs

Multi-Resolution Diffusion Models for Time Series Forecasting

In-context Exploration-Exploitation for Reinforcement Learning

Non-negative Contrastive Learning

A Plug-and-Play Image Registration Network

Model Merging by Uncertainty-Based Gradient Matching

Idempotence and Perceptual Image Compression

DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation

Does Progress On Object Recognition Benchmarks Improve Generalization on Crowdsourced, Global Data?

Zero-Shot Robustification of Zero-Shot Models

Uncertainty-aware Graph-based Hyperspectral Image Classification

SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents

Towards image compression with perfect realism at ultra-low bitrates

Learning Optimal Contracts: How to Exploit Small Action Spaces

Transferring Labels to Solve Annotation Mismatches Across Object Detection Datasets

Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs

PAC-FNO: Parallel-Structured All-Component Fourier Neural Operators for Recognizing Low-Quality Images

Self-Supervised High Dynamic Range Imaging with Multi-Exposure Images in Dynamic Scenes

An Efficient Membership Inference Attack for the Diffusion Model by Proximal Initialization

FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets

BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inference

Test-Time Training on Nearest Neighbors for Large Language Models

STanHop: Sparse Tandem Hopfield Model for Memory-Enhanced Time Series Prediction

Unified Projection-Free Algorithms for Adversarial DR-Submodular Optimization

Critical Learning Periods Emerge Even in Deep Linear Networks

Understanding the robustness difference between stochastic gradient descent and adaptive gradient methods

OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental Learning

Accelerated Convergence of Stochastic Heavy Ball Method under Anisotropic Gradient Noise

Leveraging Unpaired Data for Vision-Language Generative Models via Cycle Consistency

Mastering Symbolic Operations: Augmenting Language Models with Compiled Neural Networks

InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning

Str2Str: A Score-based Framework for Zero-shot Protein Conformation Sampling

PRES: Toward Scalable Memory-Based Dynamic Graph Neural Networks

The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing

CoRe-GD: A Hierarchical Framework for Scalable Graph Visualization with GNNs

f-FERM: A Scalable Framework for Robust Fair Empirical Risk Minimization

Mitigating the Curse of Dimensionality for Certified Robustness via Dual Randomized Smoothing

Decoupled Marked Temporal Point Process using Neural Ordinary Differential Equations

Elastic Feature Consolidation For Cold Start Exemplar-Free Incremental Learning

BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation

Understanding the Robustness of Multi-modal Contrastive Learning to Distribution Shift

Investigating the Benefits of Projection Head for Representation Learning

LLM-CXR: Instruction-Finetuned LLM for CXR Image Understanding and Generation

Stochastic Modified Equations and Dynamics of Dropout Algorithm

Implicit Neural Representations and the Algebra of Complex Wavelets

Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature

A Benchmark for Learning to Translate a New Language from One Grammar Book

Conformal Inductive Graph Neural Networks

Continual Momentum Filtering on Parameter Space for Online Test-time Adaptation

Consistency Models as a Rich and Efficient Policy Class for Reinforcement Learning

On the Limitations of Temperature Scaling for Distributions with Overlaps

Unveiling and Manipulating Prompt Influence in Large Language Models

FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity

LRM: Large Reconstruction Model for Single Image to 3D

Generative Sliced MMD Flows with Riesz Kernels

Kosmos-G: Generating Images in Context with Multimodal Large Language Models

AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?

BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection

Self-Supervised Dataset Distillation for Transfer Learning

Large-scale Training of Foundation Models for Wearable Biosignals

Provably Robust Conformal Prediction with Improved Efficiency

Accelerating Distributed Stochastic Optimization via Self-Repellent Random Walks

Adaptive Federated Learning with Auto-Tuned Clients

LogicMP: A Neuro-symbolic Approach for Encoding First-order Logic Constraints

DP-SGD Without Clipping: The Lipschitz Neural Network Way

Pre-training Sequence, Structure, and Surface Features for Comprehensive Protein Representation Learning

OmniControl: Control Any Joint at Any Time for Human Motion Generation

Leave-one-out Distinguishability in Machine Learning

In defense of parameter sharing for model-compression

Enhancing One-Shot Federated Learning Through Data and Ensemble Co-Boosting

Accelerating Data Generation for Neural Operators via Krylov Subspace Recycling

How Well Do Supervised 3D Models Transfer to Medical Imaging Tasks?

Revisit and Outstrip Entity Alignment: A Perspective of Generative Models

OMNI: Open-endedness via Models of human Notions of Interestingness

Risk Bounds of Accelerated SGD for Overparameterized Linear Regression

The Hidden Language of Diffusion Models

Distinguished In Uniform: Self-Attention Vs. Virtual Nodes

Task Adaptation from Skills: Information Geometry, Disentanglement, and New Objectives for Unsupervised Reinforcement Learning

Consistent Multi-Class Classification from Multiple Unlabeled Datasets

Enhancing Instance-Level Image Classification with Set-Level Labels

Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources

Coeditor: Leveraging Repo-level Diffs for Code Auto-editing

Unifying Feature and Cost Aggregation with Transformers for Semantic and Visual Correspondence

Causality-Inspired Spatial-Temporal Explanations for Dynamic Graph Neural Networks

Hyper Evidential Deep Learning to Quantify Composite Classification Uncertainty

MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Images

Semantic Flow: Learning Semantic Fields of Dynamic Scenes from Monocular Videos

Leveraging Generative Models for Unsupervised Alignment of Neural Time Series Data

TD-MPC2: Scalable, Robust World Models for Continuous Control

AnyText: Multilingual Visual Text Generation and Editing

LLM Augmented LLMs: Expanding Capabilities through Composition

On the Provable Advantage of Unsupervised Pretraining

Pooling Image Datasets with Multiple Covariate Shift and Imbalance

Provably Efficient Iterated CVaR Reinforcement Learning with Function Approximation and Human Feedback

Domain-Agnostic Molecular Generation with Chemical Feedback

Towards Optimal Feature-Shaping Methods for Out-of-Distribution Detection

Quality-Diversity through AI Feedback

Relaxing the Additivity Constraints in Decentralized No-Regret High-Dimensional Bayesian Optimization

Bayesian Optimization through Gaussian Cox Process Models for Spatio-temporal Data

Safe and Robust Watermark Injection with a Single OoD Image

TOSS: High-quality Text-guided Novel View Synthesis from a Single Image

Elucidating the design space of classifier-guided diffusion generation

Learning Flexible Body Collision Dynamics with Hierarchical Contact Mesh Transformer

Periodicity Decoupling Framework for Long-term Series Forecasting

General Stability Analysis for Zeroth-Order Optimization Algorithms

The Cost of Scaling Down Large Language Models: Reducing Model Size Affects Memory before In-context Learning

Think before you speak: Training Language Models With Pause Tokens

DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer

Context is Environment

Class Incremental Learning via Likelihood Ratio Based Task Prediction

Denoising Diffusion Step-aware Models

Noisy Interpolation Learning with Shallow Univariate ReLU Networks

Initializing Models with Larger Ones

HyperHuman: Hyper-Realistic Human Generation with Latent Structural Diffusion

AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection

Benchmarking and Improving Generator-Validator Consistency of Language Models

Language-Interfaced Tabular Oversampling via Progressive Imputation and Self-Authentication

Counterfactual Density Estimation using Kernel Stein Discrepancies

EQA-MX: Embodied Question Answering using Multimodal Expression

Proper Laplacian Representation Learning

Scaling Autoregressive Models for Content-Rich Text-to-Image Generation

Learning Stackable and Skippable LEGO Bricks for Efficient, Reconfigurable, and Variable-Resolution Diffusion Modeling

DNABERT-2: Efficient Foundation Model and Benchmark For Multi-Species Genomes

Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasets

Adaptive Regularization of Representation Rank as an Implicit Constraint of Bellman Equation

PanoDiffusion: 360-degree Panorama Outpainting via Diffusion

PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts

Making LLaMA SEE and Draw with SEED Tokenizer

Removing Biases from Molecular Representations via Information Maximization

Online Continual Learning for Interactive Instruction Following Agents

Human Motion Diffusion as a Generative Prior

Closing the Curious Case of Neural Text Degeneration

GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformers

Is attention required for ICL? Exploring the Relationship Between Model Architecture and In-Context Learning Ability

Stable Anisotropic Regularization

A Framework for Inference Inspired by Human Memory Mechanisms

SF(DA)$^2$: Source-free Domain Adaptation Through the Lens of Data Augmentation

PBADet: A One-Stage Anchor-Free Approach for Part-Body Association

Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors

A Characterization Theorem for Equivariant Networks with Point-wise Activations

Mirage: Model-agnostic Graph Distillation for Graph Classification

Exploring the Common Appearance-Boundary Adaptation for Nighttime Optical Flow

Faster Approximation of Probabilistic and Distributional Values via Least Squares

Accelerating Sinkhorn algorithm with sparse Newton iterations

Circuit Component Reuse Across Tasks in Transformer Language Models

CORN: Contact-based Object Representation for Nonprehensile Manipulation of General Unseen Objects

Neural-Symbolic Recursive Machine for Systematic Generalization

FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores

Towards Establishing Guaranteed Error for Learned Database Operations

Continuous Invariance Learning

Learning to solve Class-Constrained Bin Packing Problems via Encoder-Decoder Model

EmerDiff: Emerging Pixel-level Semantic Knowledge in Diffusion Models

Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Models

Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking

IceFormer: Accelerated Inference with Long-Sequence Transformers on CPUs

Dynamic Discounted Counterfactual Regret Minimization

Graphical Multioutput Gaussian Process with Attention

RetroBridge: Modeling Retrosynthesis with Markov Bridges

DrS: Learning Reusable Dense Rewards for Multi-Stage Tasks

Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game

Few-Shot Detection of Machine-Generated Text using Style Representations

Improved Analysis of Sparse Linear Regression in Local Differential Privacy Model

Visual Data-Type Understanding does not emerge from scaling Vision-Language Models

Enhancing Tail Performance in Extreme Classifiers by Label Variance Reduction

Reward Design for Justifiable Sequential Decision-Making

Rethinking Complex Queries on Knowledge Graphs with Neural Link Predictors

Generative Pre-training for Speech with Flow Matching

Enhancing Neural Training via a Correlated Dynamics Model

Modeling state-dependent communication between brain regions with switching nonlinear dynamical systems

Some Fundamental Aspects about Lipschitz Continuity of Neural Networks

Structured Video-Language Modeling with Temporal Grouping and Spatial Grounding

Certified Adversarial Robustness for Rate Encoded Spiking Neural Networks

Graph Metanetworks for Processing Diverse Neural Architectures

Structuring Representation Geometry with Rotationally Equivariant Contrastive Learning

TEDDY: Trimming Edges with Degree-based Discrimination Strategy

A differentiable brain simulator bridging brain simulation and brain-inspired computing

From Zero to Turbulence: Generative Modeling for 3D Flow Simulation

RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems

AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model

Physics-Regulated Deep Reinforcement Learning: Invariant Embeddings

FedLoGe: Joint Local and Generic Federated Learning under Long-tailed Data

Efficient Planning with Latent Diffusion

PAC Prediction Sets Under Label Shift

Structural Fairness-aware Active Learning for Graph Neural Networks

Scalable Neural Network Kernels

Language Model Detectors Are Easily Optimized Against

How I Warped Your Noise: a Temporally-Correlated Noise Prior for Diffusion Models

Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning

Zero-Mean Regularized Spectral Contrastive Learning: Implicitly Mitigating Wrong Connections in Positive-Pair Graphs

Neural Field Classifiers via Target Encoding and Classification Loss

Variance-enlarged Poisson Learning for Graph-based Semi-Supervised Learning with Extremely Sparse Labeled Data

Solving Homogeneous and Heterogeneous Cooperative Tasks with Greedy Sequential Execution

Coordinate-Aware Modulation for Neural Fields

Neuroformer: Multimodal and Multitask Generative Pretraining for Brain Data

Do Generated Data Always Help Contrastive Learning?

Rigid Protein-Protein Docking via Equivariant Elliptic-Paraboloid Interface Prediction

An improved analysis of per-sample and per-update clipping in federated learning

Evoke: Evoking Critical Thinking Abilities in LLMs via Reviewer-Author Prompt Editing

CoVLM: Composing Visual Entities and Relationships in Large Language Models Via Communicative Decoding

WizardCoder: Empowering Code Large Language Models with Evol-Instruct

Numerical Accounting in the Shuffle Model of Differential Privacy

Language Model Decoding as Direct Metrics Optimization

On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes

Provable Benefits of Multi-task RL under Non-Markovian Decision Making Processes

Like Oil and Water: Group Robustness Methods and Poisoning Defenses May Be at Odds

Geometrically Aligned Transfer Encoder for Inductive Transfer in Regression Tasks

Generative Learning for Solving Non-Convex Problem with Multi-Valued Input-Solution Mapping

Knowledge Fusion of Large Language Models

Learning Multi-Agent Communication from Graph Modeling Perspective

Evaluating Language Model Agency Through Negotiations

SCHEMA: State CHangEs MAtter for Procedure Planning in Instructional Videos

Overthinking the Truth: Understanding how Language Models Process False Demonstrations

BTR: Binary Token Representations for Efficient Retrieval Augmented Language Models

The mechanistic basis of data dependence and abrupt learning in an in-context classification task

A Probabilistic Framework for Modular Continual Learning

Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy Optimization

Universal Backdoor Attacks

DDMI: Domain-agnostic Latent Diffusion Models for Synthesizing High-Quality Implicit Neural Representations

Sentence-level Prompts Benefit Composed Image Retrieval

Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory

Are Human-generated Demonstrations Necessary for In-context Learning?

Enabling Lanuguage Models to Implicitly Learn Self-Improvement

L2MAC: Large Language Model Automatic Computer for Extensive Code Generation

Light-MILPopt: Solving Large-scale Mixed Integer Linear Programs with Lightweight Optimizer and Small-scale Training Dataset

Deep SE(3)-Equivariant Geometric Reasoning for Precise Placement Tasks

A Restoration Network as an Implicit Prior

SineNet: Learning Temporal Dynamics in Time-Dependent Partial Differential Equations

Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restoration

Scaling for Training Time and Post-hoc Out-of-distribution Detection Enhancement

Test-time Adaptation against Multi-modal Reliability Bias

INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection

GOAt: Explaining Graph Neural Networks via Graph Output Attribution

RA-DIT: Retrieval-Augmented Dual Instruction Tuning

A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis

Directly Fine-Tuning Diffusion Models on Differentiable Rewards

OpenNeRF: Open Set 3D Neural Scene Segmentation with Pixel-Wise Features and Rendered Novel Views

Efficiently Computing Similarities to Private Datasets

Domain constraints improve risk prediction when outcome data is missing

Towards Few-Shot Adaptation of Foundation Models via Multitask Finetuning

Multi-granularity Correspondence Learning from Long-term Noisy Videos

LEAP: Liberate Sparse-View 3D Modeling from Camera Poses

Outliers with Opposing Signals Have an Outsized Effect on Neural Network Optimization

Beyond Stationarity: Convergence Analysis of Stochastic Softmax Policy Gradient Methods

Skill or Luck? Return Decomposition via Advantage Functions

Transport meets Variational Inference: Controlled Monte Carlo Diffusions

Unsupervised Order Learning

Enhancing Transferable Adversarial Attacks on Vision Transformers through Gradient Normalization Scaling and High-Frequency Adaptation

Rethinking the symmetry-preserving circuits for constrained variational quantum algorithms

KITAB: Evaluating LLMs on Constraint Satisfaction for Information Retrieval

Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models

Retrieval-Guided Reinforcement Learning for Boolean Circuit Minimization

Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies

Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RL

Compressed Context Memory for Online Language Model Interaction

Revisiting Link Prediction: a data perspective

MINDE: Mutual Information Neural Diffusion Estimation

Realistic Evaluation of Semi-supervised Learning Algorithms in Open Environments

Achieving Human Parity in Content-Grounded Datasets Generation

Contrastive Difference Predictive Coding

Efficient-3Dim: Learning a Generalizable Single-image Novel-view Synthesizer in One Day

Unified Generative Modeling of 3D Molecules with Bayesian Flow Networks

Image2Sentence based Asymmetrical Zero-shot Composed Image Retrieval

Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning with Diverse Tasks

FairerCLIP: Debiasing CLIP's Zero-Shot Predictions using Functions in RKHSs

BarLeRIa: An Efficient Tuning Framework for Referring Image Segmentation

Asymptotically Free Sketched Ridge Ensembles: Risks, Cross-Validation, and Tuning

CADS: Unleashing the Diversity of Diffusion Models through Condition-Annealed Sampling

Provably Efficient CVaR RL in Low-rank MDPs

Symphony: Symmetry-Equivariant Point-Centered Spherical Harmonics for 3D Molecule Generation

Rethinking Channel Dependence for Multivariate Time Series Forecasting: Learning from Leading Indicators

Improved Probabilistic Image-Text Representations

MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use

MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning

Spatio-Temporal Approximation: A Training-Free SNN Conversion for Transformers

Modulated Phase Diffusor: Content-Oriented Feature Synthesis for Detecting Unknown Objects

LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment

MogaNet: Multi-order Gated Aggregation Network

Deep Generative Clustering with Multimodal Diffusion Variational Autoencoders

Towards Category Unification of 3D Single Object Tracking on Point Clouds

SemiReward: A General Reward Model for Semi-supervised Learning

Learning Hierarchical Polynomials with Three-Layer Neural Networks

Graph Neural Networks for Learning Equivariant Representations of Neural Networks

LEAD: Min-Max Optimization from a Physical Perspective

Kalman Filter for Online Classification of Non-Stationary Data

AlpaGasus: Training a Better Alpaca with Fewer Data

RDesign: Hierarchical Data-efficient Representation Learning for Tertiary Structure-based RNA Design

What does automatic differentiation compute for neural networks?

Unbiased Watermark for Large Language Models

Self-Consuming Generative Models Go MAD

Out-of-Distribution Detection with Negative Prompts

STARC: A General Framework For Quantifying Differences Between Reward Functions

Learning from Aggregate responses: Instance Level versus Bag Level Loss Functions

Theoretical Understanding of Learning from Adversarial Perturbations

Time Fairness in Online Knapsack Problems

Attacking Perceptual Similarity Metrics

A ROBUST DIFFERENTIAL NEURAL ODE OPTIMIZER

GPAvatar: Generalizable and Precise Head Avatar from Image(s)

Chain-of-Experts: When LLMs Meet Complex Operations Research Problems

StructComp: Substituting propagation with Structural Compression in Training Graph Contrastive Learning

TopoMLP: A Simple yet Strong Pipeline for Driving Topology Reasoning

Behaviour Distillation

$\infty$-Diff: Infinite Resolution Diffusion with Subsampled Mollified States

Enhancing Human Experience in Human-Agent Collaboration: A Human-Centered Modeling Approach Based on Positive Human Gain

Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Control

Debiasing Algorithm through Model Adaptation

On gauge freedom, conservativity and intrinsic dimensionality estimation in diffusion models

Clifford Group Equivariant Simplicial Message Passing Networks

A Flexible Generative Model for Heterogeneous Tabular EHR with Missing Modality

Don't Play Favorites: Minority Guidance for Diffusion Models

Mitigating Emergent Robustness Degradation while Scaling Graph Learning

Frequency-Aware Transformer for Learned Image Compression

Causally Aligned Curriculum Learning

From Molecules to Materials: Pre-training Large Generalizable Models for Atomic Property Prediction

ED-NeRF: Efficient Text-Guided Editing of 3D Scene With Latent Space NeRF

The Wasserstein Believer: Learning Belief Updates for Partially Observable Environments through Reliable Latent Space Models

FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling

CAMBranch: Contrastive Learning with Augmented MILPs for Branching

Cycle Consistency Driven Object Discovery

YaRN: Efficient Context Window Extension of Large Language Models

CoT3DRef: Chain-of-Thoughts Data-Efficient 3D Visual Grounding

AgentBench: Evaluating LLMs as Agents

Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks

Towards Aligned Layout Generation via Diffusion Model with Aesthetic Constraints

What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning

Leveraging Low-Rank and Sparse Recurrent Connectivity for Robust Closed-Loop Control

Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs

A Multi-Level Framework for Accelerating Training Transformer Models

Supervised Knowledge Makes Large Language Models Better In-context Learners

VQ-TR: Vector Quantized Attention for Time Series Forecasting

Aligning Relational Learning with Lipschitz Fairness

Understanding In-Context Learning from Repetitions

Symmetric Neural-Collapse Representations with Supervised Contrastive Loss: The Impact of ReLU and Batching

Training Unbiased Diffusion Models From Biased Dataset

DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation

Separate and Diffuse: Using a Pretrained Diffusion Model for Better Source Separation

Conversational Drug Editing Using Retrieval and Domain Feedback

Discovering Temporally-Aware Reinforcement Learning Algorithms

A Precise Characterization of SGD Stability Using Loss Surface Geometry

The Expressive Power of Transformers with Chain of Thought

Posterior Sampling Based on Gradient Flows of the MMD with Negative Distance Kernel

ClimODE: Climate and Weather Forecasting with Physics-informed Neural ODEs

Input-gradient space particle inference for neural network ensembles

Towards Reliable and Efficient Backdoor Trigger Inversion via Decoupling Benign Features

Confidence-aware Reward Optimization for Fine-tuning Text-to-Image Models

A Data-Driven Measure of Relative Uncertainty for Misclassification Detection

What Matters to You? Towards Visual Representation Alignment for Robot Learning

MOFI: Learning Image Representations from Noisy Entity Annotated Images

Large Language Models as Automated Aligners for benchmarking Vision-Language Models

Sample-Efficient Linear Representation Learning from Non-IID Non-Isotropic Data

Hypergraph Dynamic System

Elucidating the Exposure Bias in Diffusion Models

SPDER: Semiperiodic Damping-Enabled Object Representation

Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints

MagicDrive: Street View Generation with Diverse 3D Geometry Control

Gaining Wisdom from Setbacks: Aligning Large Language Models via Mistake Analysis

GeoDiffusion: Text-Prompted Geometric Control for Object Detection Data Generation

DATS: Difficulty-Aware Task Sampler for Meta-Learning Physics-Informed Neural Networks

SparseDFF: Sparse-View Feature Distillation for One-Shot Dexterous Manipulation

Leveraging Uncertainty Estimates To Improve Classifier Performance

Learning Planning Abstractions from Language

Experimental Design for Multi-Channel Imaging via Task-Driven Feature Selection

Fast Ensembling with Diffusion Schrödinger Bridge

Benign Overfitting and Grokking in ReLU Networks for XOR Cluster Data

L2P-MIP: Learning to Presolve for Mixed Integer Programming

Neurosymbolic Grounding for Compositional World Models

Momentum Benefits Non-iid Federated Learning Simply and Provably

Making Pre-trained Language Models Great on Tabular Prediction

Multimodal Patient Representation Learning with Missing Modalities and Labels

Feature-aligned N-BEATS with Sinkhorn divergence

Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning

Video Decomposition Prior: Editing Videos Layer by Layer

New Insight of Variance reduce in Zero-Order Hard-Thresholding: Mitigating Gradient Error and Expansivity Contradictions

Subtractive Mixture Models via Squaring: Representation and Learning

AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Bridging Vision and Language Spaces with Assignment Prediction

Modulate Your Spectrum in Self-Supervised Learning

LLM-Assisted Code Cleaning For Training Accurate Code Generators

Implicit bias of SGD in $L_2$-regularized linear DNNs: One-way jumps from high to low rank

Simple Minimax Optimal Byzantine Robust Algorithm for Nonconvex Objectives with Uniform Gradient Heterogeneity

On the Variance of Neural Network Training with respect to Test Sets and Distributions

Graph Parsing Networks

Optimal transport based adversarial patch to leverage large scale attack transferability

SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation

Orbit-Equivariant Graph Neural Networks

Perceptual Group Tokenizer: Building Perception with Iterative Grouping

R-EDL: Relaxing Nonessential Settings of Evidential Deep Learning

Early Neuron Alignment in Two-layer ReLU Networks with Small Initialization

Bootstrapping Variational Information Pursuit with Large Language and Vision Models for Interpretable Image Classification

Dropout-Based Rashomon Set Exploration for Efficient Predictive Multiplicity Estimation

More is Better: when Infinite Overparameterization is Optimal and Overfitting is Obligatory

An Agnostic View on the Cost of Overfitting in (Kernel) Ridge Regression

Attention-Guided Contrastive Role Representations for Multi-agent Reinforcement Learning

Masked Distillation Advances Self-Supervised Transformer Architecture Search

Learning with a Mole: Transferable latent spatial representations for navigation without reconstruction

End-to-End (Instance)-Image Goal Navigation through Correspondence as an Emergent Phenomenon

Don't Judge by the Look: Towards Motion Coherent Video Representation

Submodular Reinforcement Learning

Conserve-Update-Revise to Cure Generalization and Robustness Trade-off in Adversarial Training

Role of Locality and Weight Sharing in Image-Based Tasks: A Sample Complexity Separation between CNNs, LCNs, and FCNs

Noise Map Guidance: Inversion with Spatial Context for Real Image Editing

A Versatile Causal Discovery Framework to Allow Causally-Related Hidden Variables

Inherently Interpretable Time Series Classification via Multiple Instance Learning

Consistent algorithms for multi-label classification with macro-at-$k$ metrics

KW-Design: Pushing the Limit of Protein Design via Knowledge Refinement

MOTOR: A Time-to-Event Foundation Model For Structured Medical Records

Constructing Adversarial Examples for Vertical Federated Learning: Optimal Client Corruption through Multi-Armed Bandit

Mega-TTS 2: Boosting Prompting Mechanisms for Zero-Shot Speech Synthesis

Light Schrödinger Bridge

Learning with Mixture of Prototypes for Out-of-Distribution Detection

Kill Two Birds with One Stone: Rethinking Data Augmentation for Deep Long-tailed Learning

Can We Evaluate Domain Adaptation Models Without Target-Domain Labels?

Efficient Continual Finite-Sum Minimization

Adversarial Training Should Be Cast as a Non-Zero-Sum Game

Advancing the Lower Bounds: an Accelerated, Stochastic, Second-order Method with Optimal Adaptation to Inexactness

MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts

Magnitude Invariant Parametrizations Improve Hypernetwork Learning

Building Cooperative Embodied Agents Modularly with Large Language Models

Towards Robust Multi-Modal Reasoning via Model Selection

The optimality of kernel classifiers in Sobolev space

Proving Test Set Contamination in Black-Box Language Models

SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression

Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled video

CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing

Learning model uncertainty as variance-minimizing instance weights

A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation

Toward effective protection against diffusion-based mimicry through score distillation

Piecewise Linear Parametrization of Policies: Towards Interpretable Deep Reinforcement Learning

Multi-View Representation is What You Need for Point-Cloud Pre-Training

PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization

Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning

Designing Skill-Compatible AI: Methodologies and Frameworks in Chess

Forward Learning with Top-Down Feedback: Empirical and Analytical Characterization

LDReg: Local Dimensionality Regularized Self-Supervised Learning

Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCI

Mixture of LoRA Experts

KoLA: Carefully Benchmarking World Knowledge of Large Language Models

CAMIL: Context-Aware Multiple Instance Learning for Cancer Detection and Subtyping in Whole Slide Images

Knowledge Distillation Based on Transformed Teacher Matching

Foundation Model-oriented Robustness: Robust Image Model Evaluation with Pretrained Models

Pseudo-Generalized Dynamic View Synthesis from a Video

Massively Scalable Inverse Reinforcement Learning in Google Maps

Improved sampling via learned diffusions

Learning Polynomial Problems with $SL(2, \mathbb{R})$-Equivariance

On the hardness of learning under symmetries

Talk like a Graph: Encoding Graphs for Large Language Models

Hybrid Distillation: Connecting Masked Autoencoders with Contrastive Learners

Image Inpainting via Iteratively Decoupled Probabilistic Modeling

Maximum Entropy Heterogeneous-Agent Reinforcement Learning

Nougat: Neural Optical Understanding for Academic Documents

Learning Personalized Causally Invariant Representations for Heterogeneous Federated Clients

ExeDec: Execution Decomposition for Compositional Generalization in Neural Program Synthesis

Tree-Planner: Efficient Close-loop Task Planning with Large Language Models

PINNsFormer: A Transformer-Based Framework For Physics-Informed Neural Networks

Deep Temporal Graph Clustering

DV-3DLane: End-to-end Multi-modal 3D Lane Detection with Dual-view Representation

On the Reliability of Watermarks for Large Language Models

Universal Guidance for Diffusion Models

NEFTune: Noisy Embeddings Improve Instruction Finetuning

Entropy Coding of Unordered Data Structures

A Semantic Invariant Robust Watermark for Large Language Models

Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agents

Long-tailed Diffusion Models with Oriented Calibration

When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations

QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models

Hybrid Internal Model: Learning Agile Legged Locomotion with Simulated Robot Response

Retrieval is Accurate Generation

Illusory Attacks: Information-theoretic detectability matters in adversarial attacks

Consistency-guided Prompt Learning for Vision-Language Models

Differentiable Learning of Generalized Structured Matrices for Efficient Deep Neural Networks

ACRF: Compressing Explicit Neural Radiance Fields via Attribute Compression

Navigating Dataset Documentations in AI: A Large-Scale Analysis of Dataset Cards on HuggingFace

An Analytical Solution to Gauss-Newton Loss for Direct Image Alignment

De novo Protein Design Using Geometric Vector Field Networks

Sample-Efficient Quality-Diversity by Cooperative Coevolution

Weakly-supervised Audio Separation via Bi-modal Semantic Similarity

DecompOpt: Controllable and Decomposed Diffusion Models for Structure-based Molecular Optimization

Adversarial Feature Map Pruning for Backdoor

Toward Student-oriented Teacher Network Training for Knowledge Distillation

Independent-Set Design of Experiments for Estimating Treatment and Spillover Effects under Network Interference

Robust Adversarial Reinforcement Learning via Bounded Rationality Curricula

Plug-and-Play Posterior Sampling under Mismatched Measurement and Prior Models

Backdoor Contrastive Learning via Bi-level Trigger Optimization

Reward-Consistent Dynamics Models are Strongly Generalizable for Offline Reinforcement Learning

Towards Cheaper Inference in Deep Networks with Lower Bit-Width Accumulators

BioBridge: Bridging Biomedical Foundation Models via Knowledge Graphs

Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency

DiLu: A Knowledge-Driven Approach to Autonomous Driving with Large Language Models

DisenBooth: Identity-Preserving Disentangled Tuning for Subject-Driven Text-to-Image Generation

Parsing neural dynamics with infinite recurrent switching linear dynamical systems

Chain of Hindsight aligns Language Models with Feedback

Discovering Failure Modes of Text-guided Diffusion Models via Adversarial Search

Headless Language Models: Learning without Predicting with Contrastive Weight Tying

MAP IT to Visualize Representations

Waxing-and-Waning: a Generic Similarity-based Framework for Efficient Self-Supervised Learning

Revisiting Data Augmentation in Deep Reinforcement Learning

MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback

Doubly Robust Instance-Reweighted Adversarial Training

CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets

Generative Judge for Evaluating Alignment

Demystifying Linear MDPs and Novel Dynamics Aggregation Framework

Language Modeling Is Compression

The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding of the Open World

Progressive3D: Progressively Local Editing for Text-to-3D Content Creation with Complex Semantic Prompts

An Extensible Framework for Open Heterogeneous Collaborative Perception

On the Joint Interaction of Models, Data, and Features

SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

Accurate and Scalable Estimation of Epistemic Uncertainty for Graph Neural Networks

Interventional Fairness on Partially Known Causal Graphs: A Constrained Optimization Approach

Replay across Experiments: A Natural Extension of Off-Policy RL

FeatUp: A Model-Agnostic Framework for Features at Any Resolution

COCO-Periph: Bridging the Gap Between Human and Machine Perception in the Periphery

Training Socially Aligned Language Models on Simulated Social Interactions

Diverse Projection Ensembles for Distributional Reinforcement Learning

CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction

SafeDreamer: Safe Reinforcement Learning with World Models

Optimal Sample Complexity of Contrastive Learning

CLaM-TTS: Improving Neural Codec Language Model for Zero-Shot Text-to-Speech

Where We Have Arrived in Proving the Emergence of Sparse Interaction Primitives in DNNs

Enhanced Face Recognition using Intra-class Incoherence Constraint

Global Optimality for Non-linear Constrained Restoration Problems via Invexity

Towards Energy Efficient Spiking Neural Networks: An Unstructured Pruning Framework

ADDP: Learning General Representations for Image Recognition and Generation with Alternating Denoising Diffusion Process

GNeRP: Gaussian-guided Neural Reconstruction of Reflective Objects with Noisy Polarization Priors

CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity

Mask-Based Modeling for Neural Radiance Fields

MixSup: Mixed-grained Supervision for Label-efficient LiDAR-based 3D Object Detection

Towards Understanding Sycophancy in Language Models

Algorithms for Caching and MTS with reduced number of predictions

Learning to reconstruct signals from binary measurements alone

Multi-Source Diffusion Models for Simultaneous Music Generation and Separation

$\pi$2vec: Policy Representation with Successor Features

SWAP: Sparse Entropic Wasserstein Regression for Robust Network Pruning

Towards Identifiable Unsupervised Domain Translation: A Diversified Distribution Matching Approach

Conditional Variational Diffusion Models

Can LLM-Generated Misinformation Be Detected?

Pre-training LiDAR-based 3D Object Detectors through Colorization

On the Markov Property of Neural Algorithmic Reasoning: Analyses and Methods

Matrix Manifold Neural Networks++

Neural Atoms: Propagating Long-range Interaction in Molecular Graphs through Efficient Communication Channel

Sum-Product-Set Networks: Deep Tractable Models for Tree-Structured Graphs

Optimistic Bayesian Optimization with Unknown Constraints

Less is More: One-shot Subgraph Reasoning on Large-scale Knowledge Graphs

Plan-Seq-Learn: Language Model Guided RL for Solving Long Horizon Robotics Tasks

Personalize Segment Anything Model with One Shot

On the generalization capacity of neural networks during generic multimodal reasoning

Rethinking and Extending the Probabilistic Inference Capacity of GNNs

The Expressive Power of Low-Rank Adaptation

Multi-Scale Representations by Varying Window Attention for Semantic Segmentation

Retrieval meets Long Context Large Language Models

Dynamic Layer Tying for Parameter-Efficient Transformers

Simplifying Transformer Blocks

Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learning

A Branching Decoder for Set Generation

Enhancing High-Resolution 3D Generation through Pixel-wise Gradient Clipping

3D Feature Prediction for Masked-AutoEncoder-Based Point Cloud Pretraining

A Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural Networks

Deep Reinforcement Learning Guided Improvement Heuristic for Job Shop Scheduling

Path Choice Matters for Clear Attributions in Path Methods

Instructive Decoding: Instruction-Tuned Large Language Models are Self-Refiner from Noisy Instructions

Estimating Shape Distances on Neural Representations with Limited Samples

DIAGNOSIS: Detecting Unauthorized Data Usages in Text-to-image Diffusion Models

Object centric architectures enable efficient causal representation learning

Pre-Training and Fine-Tuning Generative Flow Networks

Topological data analysis on noisy quantum computers

LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection

Variational Inference for SDEs Driven by Fractional Noise

VCR-Graphormer: A Mini-batch Graph Transformer via Virtual Connections

LaneSegNet: Map Learning with Lane Segment Perception for Autonomous Driving

Soft Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample Complexity

Debiased Collaborative Filtering with Kernel-Based Causal Balancing

Towards Non-Asymptotic Convergence for Diffusion-Based Generative Models

Reverse Forward Curriculum Learning for Extreme Sample and Demo Efficiency

Langevin Monte Carlo for strongly log-concave distributions: Randomized midpoint revisited

S$2$AC: Energy-Based Reinforcement Learning with Stein Soft Actor Critic

FedHyper: A Universal and Robust Learning Rate Scheduler for Federated Learning with Hypergradient Descent

A Symmetry-Aware Exploration of Bayesian Neural Network Posteriors

SEA: Sparse Linear Attention with Estimated Attention Mask

Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling Limit

Goodhart's Law in Reinforcement Learning

ReFusion: Improving Natural Language Understanding with Computation-Efficient Retrieval Representation Fusion

An Emulator for Fine-tuning Large Language Models using Small Language Models

Neural Optimal Transport with General Cost Functionals

Bounding the Expected Robustness of Graph Neural Networks Subject to Node Feature Attacks

COLLIE: Systematic Construction of Constrained Text Generation Tasks

SWE-bench: Can Language Models Resolve Real-world Github Issues?

Cross-Modal Contextualized Diffusion Models for Text-Guided Visual Generation and Editing

At Which Training Stage Does Code Data Help LLMs Reasoning?

VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs

Expressive Losses for Verified Robustness via Convex Combinations

Language Model Cascades: Token-Level Uncertainty And Beyond

A Linear Algebraic Framework for Counterfactual Generation

Learning to Reject Meets Long-tail Learning

Faithful Rule Extraction for Differentiable Rule Learning Models

Quantifying Network Similarity using Graph Cumulants

Grokking as a First Order Phase Transition in Two Layer Networks

Feature emergence via margin maximization: case studies in algebraic tasks

JointNet: Extending Text-to-Image Diffusion for Dense Distribution Modeling

HyperAttention: Long-context Attention in Near-Linear Time

An operator preconditioning perspective on training in physics-informed machine learning

Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection

Confidential-DPproof: Confidential Proof of Differentially Private Training

Hindsight PRIORs for Reward Learning from Human Preferences

A Hierarchical Bayesian Model for Few-Shot Meta Learning

The Alignment Problem from a Deep Learning Perspective

Neural Fine-Tuning Search for Few-Shot Learning

FairTune: Optimizing Parameter Efficient Fine Tuning for Fairness in Medical Image Analysis

Align With Purpose: Optimize Desired Properties in CTC Models with a General Plug-and-Play Framework

DIG In: Evaluating Disparities in Image Generations with Indicators for Geographic Diversity

Memorization in Self-Supervised Learning Improves Downstream Generalization

Neural Active Learning Beyond Bandits

SPADE: Semi-supervised Anomaly Detection under Distribution Mismatch

CARD: Channel Aligned Robust Blend Transformer for Time Series Forecasting

Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecasting

EasyTPP: Towards Open Benchmarking Temporal Point Processes

Explaining Time Series via Contrastive and Locally Sparse Perturbations

Pathologies of Predictive Diversity in Deep Ensembles

Detecting Pretraining Data from Large Language Models

In-Context Pretraining: Language Modeling Beyond Document Boundaries

RECOMP: Improving Retrieval-Augmented LMs with Context Compression and Selective Augmentation

A Fast and Provable Algorithm for Sparse Phase Retrieval

SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore

Multilingual Jailbreak Challenges in Large Language Models

Lemur: Harmonizing Natural Language and Code for Language Agents

One-shot Active Learning Based on Lewis Weight Sampling for Multiple Deep Models

The Blessing of Randomness: SDE Beats ODE in General Diffusion-based Image Editing

Window Attention is Bugged: How not to Interpolate Position Embeddings

Sharpness-Aware Data Poisoning Attack

NetInfoF Framework: Measuring and Exploiting Network Usable Information

Faster Sampling from Log-Concave Densities over Polytopes via Efficient Linear Solvers

Learning to Reject with a Fixed Predictor: Application to Decontextualization

Demystifying Poisoning Backdoor Attacks from a Statistical Perspective

A 2-Dimensional State Space Layer for Spatial Inductive Bias

High-dimensional SGD aligns with emerging outlier eigenspaces

A Unified and General Framework for Continual Learning

Dynamic Neural Response Tuning

Det-CGD: Compressed Gradient Descent with Matrix Stepsizes for Non-Convex Optimization

BatchPrompt: Accomplish more with less

CODE REPRESENTATION LEARNING AT SCALE

Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors

Forward Learning of Graph Neural Networks

Towards Cross Domain Generalization of Hamiltonian Representation via Meta Learning

AutoChunk: Automated Activation Chunk for Memory-Efficient Deep Learning Inference

One Forward is Enough for Neural Network Training via Likelihood Ratio Method

TorchRL: A data-driven decision-making library for PyTorch

SweetDreamer: Aligning Geometric Priors in 2D diffusion for Consistent Text-to-3D

CellPLM: Pre-training of Cell Language Model Beyond Single Cells

MetaPhysiCa: Improving OOD Robustness in Physics-informed Machine Learning

EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations

Counting Graph Substructures with Graph Neural Networks

Meta-VBO: Utilizing Prior Tasks in Optimizing Risk Measures with Gaussian Processes

Beyond Accuracy: Evaluating Self-Consistency of Code Large Language Models with IdentityChain

Beyond Imitation: Leveraging Fine-grained Quality Signals for Alignment

In-Context Learning through the Bayesian Prism

Improving Domain Generalization with Domain Relations

Analyzing and Mitigating Object Hallucination in Large Vision-Language Models

Zoology: Measuring and Improving Recall in Efficient Language Models

Protein-Ligand Interaction Prior for Binding-aware 3D Molecule Diffusion Models

TRAM: Bridging Trust Regions and Sharpness Aware Minimization

Holistic Evaluation of Language Models

MOFDiff: Coarse-grained Diffusion for Metal-Organic Framework Design

Temporal Generalization Estimation in Evolving Graphs

The Curse of Diversity in Ensemble-Based Exploration

Beam Enumeration: Probabilistic Explainability For Sample Efficient Self-conditioned Molecular Design

DynaVol: Unsupervised Learning for Dynamic Scenes through Object-Centric Voxelization

Self-Alignment with Instruction Backtranslation

Denoising Task Routing for Diffusion Models

Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps

DreamTime: An Improved Optimization Strategy for Diffusion-Guided 3D Generation

"What Data Benefits My Classifier?" Enhancing Model Performance and Interpretability through Influence-Based Data Selection

TapMo: Shape-aware Motion Generation of Skeleton-free Characters

Embarrassingly Simple Dataset Distillation

Pose Modulated Avatars from Video

SaProt: Protein Language Modeling with Structure-aware Vocabulary

DMV3D: Denoising Multi-view Diffusion Using 3D Large Reconstruction Model

MovingParts: Motion-based 3D Part Discovery in Dynamic Radiance Field

CausalTime: Realistically Generated Time-series for Benchmarking of Causal Discovery

Two-timescale Extragradient for Finding Local Minimax Points

Near-Optimal Quantum Algorithm for Minimizing the Maximal Loss

Contextual Bandits with Online Neural Regression

Predictive auxiliary objectives in deep RL mimic learning in the brain

Mathematical Justification of Hard Negative Mining via Isometric Approximation Theorem

Score Regularized Policy Optimization through Diffusion Behavior

Amortizing intractable inference in large language models

WildChat: 1M ChatGPT Interaction Logs in the Wild

Real-Fake: Effective Training Data Synthesis Through Distribution Matching

Be Aware of the Neighborhood Effect: Modeling Selection Bias under Interference

DAM: Towards a Foundation Model for Forecasting

CPPO: Continual Learning for Reinforcement Learning with Human Feedback

Understanding the Robustness of Randomized Feature Defense Against Query-Based Adversarial Attacks

Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation

Tuning LayerNorm in Attention: Towards Efficient Multi-Modal LLM Finetuning

Grounded Object-Centric Learning

Generalization in diffusion models arises from geometry-adaptive harmonic representations

Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis

Robust NAS under adversarial training: benchmark, theory, and beyond

SE(3)-Stochastic Flow Matching for Protein Backbone Generation

Future Language Modeling from Temporal Document History

AutoCast++: Enhancing World Event Prediction with Zero-shot Ranking-based Context Retrieval

SGD Finds then Tunes Features in Two-Layer Neural Networks with near-Optimal Sample Complexity: A Case Study in the XOR problem

Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL

ODE Discovery for Longitudinal Heterogeneous Treatment Effects Inference

InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation

One-shot Empirical Privacy Estimation for Federated Learning

Learning to Act from Actionless Videos through Dense Correspondences

The False Promise of Imitating Proprietary Language Models

Offline RL with Observation Histories: Analyzing and Improving Sample Complexity

Learning From Simplicial Data Based on Random Walks and 1D Convolutions

Strategic Preys Make Acute Predators: Enhancing Camouflaged Object Detectors by Generating Camouflaged Objects

Revisiting the Last-Iterate Convergence of Stochastic Gradient Methods

Large Language Models to Enhance Bayesian Optimization

PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Prediction

Approximating Nash Equilibria in Normal-Form Games via Stochastic Optimization

Towards Transparent Time Series Forecasting

Seeking Neural Nuggets: Knowledge Transfer in Large Language Models from a Parametric Perspective

REValueD: Regularised Ensemble Value-Decomposition for Factorisable Markov Decision Processes

Traveling Waves Encode The Recent Past and Enhance Sequence Learning

Adaptive Sharpness-Aware Pruning for Robust Sparse Networks

TACTiS-2: Better, Faster, Simpler Attentional Copulas for Multivariate Time Series

LLaMA-Adapter: Efficient Fine-tuning of Large Language Models with Zero-initialized Attention

GROOT: Learning to Follow Instructions by Watching Gameplay Videos

Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse Problems

DreamFlow: High-quality text-to-3D generation by Approximating Probability Flow

Unpaired Image-to-Image Translation via Neural Schrödinger Bridge

Exploring Diffusion Time-steps for Unsupervised Representation Learning

DiffAR: Denoising Diffusion Autoregressive Model for Raw Speech Waveform Generation

FROSTER: Frozen CLIP is A Strong Teacher for Open-Vocabulary Action Recognition

Understanding Catastrophic Forgetting in Language Models via Implicit Inference

Training Diffusion Models with Reinforcement Learning

Shadow Cones: A Generalized Framework for Partial Order Embeddings

Curriculum reinforcement learning for quantum architecture search under hardware errors

Continual Learning in the Presence of Spurious Correlations: Analyses and a Simple Baseline

A Lightweight Method for Tackling Unknown Participation Statistics in Federated Averaging

Data Debugging with Shapley Importance over Machine Learning Pipelines

Probabilistically Rewired Message-Passing Neural Networks

Motif: Intrinsic Motivation from Artificial Intelligence Feedback

Empirical Likelihood for Fair Classification

SAFLEX: Self-Adaptive Augmentation via Feature Label Extrapolation

Deep Reinforcement Learning for Modelling Protein Complexes

Hypothesis Search: Inductive Reasoning with Language Models

LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attacks

Unbalancedness in Neural Monge Maps Improves Unpaired Domain Translation

Learning to Embed Time Series Patches Independently

Horizon-Free Regret for Linear Markov Decision Processes

Soft Contrastive Learning for Time Series

Towards Faithful XAI Evaluation via Generalization-Limited Backdoor Watermark

Mixture of Weak and Strong Experts on Graphs

Learning Energy-Based Models by Cooperative Diffusion Recovery Likelihood

Balancing Act: Constraining Disparate Impact in Sparse Models

Machine Unlearning for Image-to-Image Generative Models

Flow Matching on General Geometries

LipVoicer: Generating Speech from Silent Videos Guided by Lip Reading

Emu: Generative Pretraining in Multimodality

Bespoke Solvers for Generative Flow Models

Candidate Label Set Pruning: A Data-centric Perspective for Deep Partial-label Learning

Kernelised Normalising Flows

Quick-Tune: Quickly Learning Which Pretrained Model to Finetune and How

Workflow Discovery from Dialogues in the Low Data Regime

Stabilizing Backpropagation Through Time to Learn Complex Physics

DittoGym: Learning to Control Soft Shape-Shifting Robots

Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models

Zero-Shot Robotic Manipulation with Pre-Trained Image-Editing Diffusion Models

Dictionary Contrastive Learning for Efficient Local Supervision without Auxiliary Networks

VersVideo: Leveraging Enhanced Temporal Diffusion Models for Versatile Video Generation

SEPT: Towards Efficient Scene Representation Learning for Motion Prediction

Selective Visual Representations Improve Convergence and Generalization for Embodied AI

Generalization of Scaled Deep ResNets in the Mean-Field Regime

BrainLM: A foundation model for brain activity recordings

MgNO: Efficient Parameterization of Linear Operators via Multigrid

The Generalization Gap in Offline Reinforcement Learning

Principled Federated Domain Adaptation: Gradient Projection and Auto-Weighting

Teaching Language Models to Hallucinate Less with Synthetic Tasks

Fourier Transporter: Bi-Equivariant Robotic Manipulation in 3D

TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Series

Neural Polynomial Gabor Fields for Macro Motion Analysis

To Grok or not to Grok: Disentangling Generalization and Memorization on Corrupted Algorithmic Datasets

Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals

Teaching Large Language Models to Self-Debug

SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction

Decentralized Riemannian Conjugate Gradient Method on the Stiefel Manifold

Energy-Based Concept Bottleneck Models: Unifying Prediction, Concept Intervention, and Probabilistic Interpretations

What's in a Prior? Learned Proximal Networks for Inverse Problems

Large Language Models as Optimizers

Enhancing Contrastive Learning for Ordinal Regression via Ordinal Content Preserved Data Augmentation

SequenceMatch: Imitation Learning for Autoregressive Sequence Modelling with Backtracking

One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention

Large Language Models Cannot Self-Correct Reasoning Yet

Incentivized Truthful Communication for Federated Bandits

Identifying Policy Gradient Subspaces

H-GAP: Humanoid Control with a Generalist Planner

Biased Temporal Convolution Graph Network for Time Series Forecasting with Missing Values

Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models

Mixture-of-Experts Meets Instruction Tuning: A Winning Combination for Large Language Models

IRAD: Implicit Representation-driven Image Resampling against Adversarial Attacks

Long-Short-Range Message-Passing: A Physics-Informed Framework to Capture Non-Local Interaction for Scalable Molecular Dynamics Simulation

Decoding Natural Images from EEG for Object Recognition

On the Analysis of GAN-based Image-to-Image Translation with Gaussian Noise Injection

Explaining Kernel Clustering via Decision Trees

CAS: A Probability-Based Approach for Universal Condition Alignment Score

$\alpha$TC-VAE: On the relationship between Disentanglement and Diversity

Select to Perfect: Imitating desired behavior from large multi-agent data

Unleashing the Potential of Fractional Calculus in Graph Neural Networks with FROND

Understanding Expressivity of GNN in Rule Learning

When Semantic Segmentation Meets Frequency Aliasing

Follow-Up Differential Descriptions: Language Models Resolve Ambiguities for Image Classification

Idempotent Generative Network

ReTaSA: A Nonparametric Functional Estimation Approach for Addressing Continuous Target Shift

DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning

Integrating Planning and Deep Reinforcement Learning via Automatic Induction of Task Substructures

On the Learnability of Watermarks for Language Models

Achieving Fairness in Multi-Agent MDP Using Reinforcement Learning

Stochastic Gradient Descent for Gaussian Processes Done Right

Achieving Sample and Computational Efficient Reinforcement Learning by Action Space Reduction via Grouping

Tractable Probabilistic Graph Representation Learning with Graph-Induced Sum-Product Networks

Image Inpainting via Tractable Steering of Diffusion Models

Multimarginal Generative Modeling with Stochastic Interpolants

Generalized Neural Sorting Networks with Error-Free Differentiable Swap Functions

Meaning Representations from Trajectories in Autoregressive Models

GIO: Gradient Information Optimization for Training Dataset Selection

Parameter-Efficient Multi-Task Model Fusion with Partial Linearization

SLiMe: Segment Like Me

Language Models Represent Space and Time

M3C: A Framework towards Convergent, Flexible, and Unsupervised Learning of Mixture Graph Matching and Clustering

MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning

BadEdit: Backdooring Large Language Models by Model Editing

One For All: Towards Training One Graph Model For All Classification Tasks

Neural Monge Map estimation and its applications

Rethinking the Power of Graph Canonization in Graph Representation Learning with Stability

Symmetric Mean-field Langevin Dynamics for Distributional Minimax Problems

$t^3$-Variational Autoencoder: Learning Heavy-tailed Data with Student's t and Power Divergence

Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion

On the Sample Complexity of Lipschitz Constant Estimation

Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-tuning

Image Background Serves as Good Proxy for Out-of-distribution Data

FedTrans: Client-Transparent Utility Estimation for Robust Federated Learning

CLEX: Continuous Length Extrapolation for Large Language Models

Combining Axes Preconditioners through Kronecker Approximation for Deep Learning

The Update-Equivalence Framework for Decision-Time Planning

MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning

Inverse Approximation Theory for Nonlinear Recurrent Neural Networks

Less is More: Fewer Interpretable Region via Submodular Subset Selection

LEMON: Lossless model expansion

Sparse Model Soups: A Recipe for Improved Pruning via Model Averaging

Understanding Addition in Transformers

Deceptive Fairness Attacks on Graphs via Meta Learning

Fair and Efficient Contribution Valuation for Vertical Federated Learning

Federated Text-driven Prompt Generation for Vision-Language Models

Improved Active Learning via Dependent Leverage Score Sampling

Optimal Sketching for Residual Error Estimation for Matrix and Vector Norms

Crystalformer: Infinitely Connected Attention for Periodic Structure Encoding

Large Language Model Cascades with Mixture of Thought Representations for Cost-Efficient Reasoning

PAE: Reinforcement Learning from External Knowledge for Efficient Exploration

CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules

Image Clustering Conditioned on Text Criteria

How to Fine-Tune Vision Models with SGD

Towards 3D Molecule-Text Interpretation in Language Models

CompA: Addressing the Gap in Compositional Reasoning in Audio-Language Models

How Over-Parameterization Slows Down Gradient Descent in Matrix Sensing: The Curses of Symmetry and Initialization

MT-Ranker: Reference-free machine translation evaluation by inter-system ranking

Parametric Augmentation for Time Series Contrastive Learning

UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition

Towards Robust Out-of-Distribution Generalization Bounds via Sharpness

A Unified Sampling Framework for Solver Searching of Diffusion Probabilistic Models

On the Effect of Batch Size in Byzantine-Robust Distributed Learning

Expressivity of ReLU-Networks under Convex Relaxations

DiffusionSat: A Generative Foundation Model for Satellite Imagery

Denoising Diffusion Bridge Models

Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning

ASMR: Activation-Sharing Multi-Resolution Coordinate Networks for Efficient Inference

Causal Inference with Conditional Front-Door Adjustment and Identifiable Variational Autoencoder

From Bricks to Bridges: Product of Invariances to Enhance Latent Space Communication

Batched Low-Rank Adaptation of Foundation Models

GRAPH-CONSTRAINED DIFFUSION FOR END-TO-END PATH PLANNING

Leveraging Hyperbolic Embeddings for Coarse-to-Fine Robot Design

Impact of Computation in Integral Reinforcement Learning for Continuous-Time Control

Weakly Supervised Virus Capsid Detection with Image-Level Annotations in Electron Microscopy Images

Generalized Schrödinger Bridge Matching

Repeated Random Sampling for Minimizing the Time-to-Accuracy of Learning

Patches Are All You Need?

Navigating the Design Space of Equivariant Diffusion-Based Generative Models for De Novo 3D Molecule Generation

Breaking Physical and Linguistic Borders: Multilingual Federated Prompt Tuning for Low-Resource Languages

Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching

How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression?

Ferret: Refer and Ground Anything Anywhere at Any Granularity

Demonstration-Regularized RL

Manifold Diffusion Fields

Language Control Diffusion: Efficiently Scaling through Space, Time, and Tasks

PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization

How do Language Models Bind Entities in Context?

Emergent mechanisms for long timescales depend on training curriculum and affect performance in memory tasks

Structural Estimation of Partially Observed Linear Non-Gaussian Acyclic Model: A Practical Approach with Identifiability

Score-based generative models break the curse of dimensionality in learning a family of sub-Gaussian distributions

FairSeg: A Large-Scale Medical Image Segmentation Dataset for Fairness Learning Using Segment Anything Model with Fair Error-Bound Scaling

Learning Performance-Improving Code Edits

Tensor Programs VI: Feature Learning in Infinite Depth Neural Networks

Privately Aligning Language Models with Reinforcement Learning

Dual RL: Unification and New Methods for Reinforcement and Imitation Learning

Let's Verify Step by Step

Complete and Efficient Graph Transformers for Crystal Material Property Prediction

Uncertainty Quantification via Stable Distribution Propagation

Exploring the Promise and Limits of Real-Time Recurrent Learning

Understanding Convergence and Generalization in Federated Learning through Feature Learning Theory

LLMs Meet VLMs: Boost Open Vocabulary Object Detection with Fine-grained Descriptors

HiGen: Hierarchical Graph Generative Networks

BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models

Human Feedback is not Gold Standard

Bellman Optimal Stepsize Straightening of Flow-Matching Models

Embodied Active Defense: Leveraging Recurrent Feedback to Counter Adversarial Patches

Learning Implicit Representation for Reconstructing Articulated Objects

$\texttt{NAISR}$: A 3D Neural Additive Model for Interpretable Shape Representation

Towards Offline Opponent Modeling with In-context Learning

MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereo

SKILL-MIX: a Flexible and Expandable Family of Evaluations for AI Models

LoTa-Bench: Benchmarking Language-oriented Task Planners for Embodied Agents

Hybrid Directional Graph Neural Network for Molecules

DAFA: Distance-Aware Fair Adversarial Training

Fast-ELECTRA for Efficient Pre-training

Course Correcting Koopman Representations

Generating Pragmatic Examples to Train Neural Program Synthesizers

Data Filtering Networks

Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization

Learning with Language-Guided State Abstractions

On Harmonizing Implicit Subpopulations

On Error Propagation of Diffusion Models

R&B: Region and Boundary Aware Zero-shot Grounded Text-to-image Generation

ScaleCrafter: Tuning-free Higher-Resolution Visual Generation with Diffusion Models

Out-Of-Domain Unlabeled Data Improves Generalization

Poly-View Contrastive Learning

Successor Heads: Recurring, Interpretable Attention Heads In The Wild

Image Clustering via the Principle of Rate Reduction in the Age of Pretrained Models

On the Expressivity of Objective-Specification Formalisms in Reinforcement Learning

Latent Representation and Simulation of Markov Processes via Time-Lagged Information Bottleneck

DreamClean: Restoring Clean Image Using Deep Diffusion Prior

Enhancing Neural Subset Selection: Integrating Background Information into Set Representations

Probabilistic Adaptation of Black-Box Text-to-Video Models

DREAM: Dual Structured Exploration with Mixup for Open-set Graph Domain Adaption

Partitioning Message Passing for Graph Fraud Detection

Meta-Evolve: Continuous Robot Evolution for One-to-many Policy Transfer

Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding

TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models

Learning Interactive Real-World Simulators

Learning from Sparse Offline Datasets via Conservative Density Estimation

From Graphs to Hypergraphs: Hypergraph Projection and its Reconstruction

Concept Bottleneck Generative Models

Safe Collaborative Filtering

Object-Centric Learning with Slot Mixture Module

Spatio-Temporal Few-Shot Learning via Diffusive Neural Network Generation

Skip-Attention: Improving Vision Transformers by Paying Less Attention

Linear Log-Normal Attention with Unbiased Concentration

Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning

Koopman-based generalization bound: New aspect for full-rank weights

Robust Model-Based Optimization for Challenging Fitness Landscapes

Analytically Tractable Hidden-States Inference in Bayesian Neural Networks

An interpretable error correction method for enhancing code-to-code translation

Random Feature Amplification: Feature Learning and Generalization in Neural Networks

Fiber Monte Carlo

NeRM: Learning Neural Representations for High-Framerate Human Motion Synthesis

A Unified Experiment Design Approach for Cyclic and Acyclic Causal Models

A Framework and Benchmark for Deep Batch Active Learning for Regression

Tackling the Data Heterogeneity in Asynchronous Federated Learning with Cached Update Calibration

ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation

TextField3D: Towards Enhancing Open-Vocabulary 3D Generation with Noisy Text Fields

Automatic Functional Differentiation in JAX

Manipulating dropout reveals an optimal balance of efficiency and robustness in biological and machine visual systems

$\mathcal{B}$-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis

Transformer-VQ: Linear-Time Transformers via Vector Quantization

What does the Knowledge Neuron Thesis Have to do with Knowledge?

Ghost on the Shell: An Expressive Representation of General 3D Shapes

Intriguing Properties of Generative Classifiers

Octavius: Mitigating Task Interference in MLLMs via LoRA-MoE

Learning semilinear neural operators: A unified recursive framework for prediction and data assimilation.

ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving

Sample-efficient Learning of Infinite-horizon Average-reward MDPs with General Function Approximation

Towards Robust Offline Reinforcement Learning under Diverse Data Corruption

Fine-tuning Multimodal LLMs to Follow Zero-shot Demonstrative Instructions

Towards domain-invariant Self-Supervised Learning with Batch Styles Standardization

Towards Diverse Behaviors: A Benchmark for Imitation Learning with Human Demonstrations

SNIP: Bridging Mathematical Symbolic and Numeric Realms with Unified Pre-training

Learning from Label Proportions: Bootstrapping Supervised Learners via Belief Propagation

Transformer-Modulated Diffusion Models for Probabilistic Multivariate Time Series Forecasting

Smooth ECE: Principled Reliability Diagrams via Kernel Smoothing

LiDAR: Sensing Linear Probing Performance in Joint Embedding SSL Architectures

Vanishing Gradients in Reinforcement Finetuning of Language Models

What Algorithms can Transformers Learn? A Study in Length Generalization

Neural Network-Based Score Estimation in Diffusion Models: Optimization and Generalization

Enhancing Small Medical Learners with Privacy-preserving Contextual Prompting

Optimal criterion for feature learning of two-layer linear neural network in high dimensional interpolation regime

On the Scalability and Memory Efficiency of Semidefinite Programs for Lipschitz Constant Estimation of Neural Networks

Learning to Act without Actions

Intelligent Switching for Reset-Free RL

PINNACLE: PINN Adaptive ColLocation and Experimental points selection

Quantifying the Sensitivity of Inverse Reinforcement Learning to Misspecification

Effective and Efficient Federated Tree Learning on Hybrid Data

Neural Processing of Tri-Plane Hybrid Neural Fields

Boosting the Adversarial Robustness of Graph Neural Networks: An OOD Perspective

Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Models

Byzantine Robust Cooperative Multi-Agent Reinforcement Learning as a Bayesian Game

SetCSE: Set Operations using Contrastive Learning of Sentence Embeddings

#InsTag: Instruction Tagging for Analyzing Supervised Fine-tuning of Large Language Models

Harnessing Joint Rain-/Detail-aware Representations to Eliminate Intricate Rains

Pre-training with Random Orthogonal Projection Image Modeling

Debiasing Attention Mechanism in Transformer without Demographics

Unsupervised Pretraining for Fact Verification by Language Model Distillation

Empirical Analysis of Model Selection for Heterogeneous Causal Effect Estimation

Image Translation as Diffusion Visual Programmers

Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation

Adversarial Imitation Learning via Boosting

Bayes Conditional Distribution Estimation for Knowledge Distillation Based on Conditional Mutual Information

ValUES: A Framework for Systematic Validation of Uncertainty Estimation in Semantic Segmentation

Provable Reward-Agnostic Preference-Based Reinforcement Learning

Bidirectional Temporal Diffusion Model for Temporally Consistent Human Animation

Copula Conformal prediction for multi-step time series prediction

Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining

Adapting Large Language Models via Reading Comprehension

Improving Convergence and Generalization Using Parameter Symmetries

COLEP: Certifiably Robust Learning-Reasoning Conformal Prediction via Probabilistic Circuits

PolyGCL: GRAPH CONTRASTIVE LEARNING via Learnable Spectral Polynomial Filters

Manifold Preserving Guided Diffusion

Motion Guidance: Diffusion-Based Image Editing with Differentiable Motion Estimators

Threaten Spiking Neural Networks through Combining Rate and Temporal Information

FLD: Fourier Latent Dynamics for Structured Motion Representation and Learning

Exploring Target Representations for Masked Autoencoders

Federated Recommendation with Additive Personalization

Neural Language of Thought Models

Text2Reward: Reward Shaping with Language Models for Reinforcement Learning

Towards Training Without Depth Limits: Batch Normalization Without Gradient Explosion

Statistical Rejection Sampling Improves Preference Optimization

Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs

Privacy Amplification for Matrix Mechanisms

Negative Label Guided OOD Detection with Pretrained Vision-Language Models

PTaRL: Prototype-based Tabular Representation Learning via Space Calibration

Improved baselines for vision-language pre-training

Constrained Bi-Level Optimization: Proximal Lagrangian Value Function Approach and Hessian-free Algorithm

Error Feedback Reloaded: From Quadratic to Arithmetic Mean of Smoothness Constants

Correlated Noise Provably Beats Independent Noise for Differentially Private Learning

ModuLoRA: Finetuning 2-Bit LLMs on Consumer GPUs by Integrating with Modular Quantizers

On the Stability of Expressive Positional Encodings for Graphs

PolyVoice: Language Models for Speech to Speech Translation

Benchmarking Algorithms for Federated Domain Generalization

Compositional Generative Inverse Design

Evaluating Representation Learning on the Protein Structure Universe

AutoVP: An Automated Visual Prompting Framework and Benchmark

On the Hardness of Constrained Cooperative Multi-Agent Reinforcement Learning

Linearity of Relation Decoding in Transformer Language Models

Causal Structure Recovery with Latent Variables under Milder Distributional and Graphical Assumptions

Information Retention via Learning Supplemental Features

Geometry-Aware Projective Mapping for Unbounded Neural Radiance Fields

Off-Policy Primal-Dual Safe Reinforcement Learning

Can Large Language Models Infer Causation from Correlation?

When should we prefer Decision Transformers for Offline Reinforcement Learning?

ARM: Refining Multivariate Forecasting with Adaptive Temporal-Contextual Learning

SAS: Structured Activation Sparsification

Learning Multi-Agent Communication with Contrastive Learning

Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages

Xformer: Hybrid X-Shaped Transformer for Image Denoising

Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios

Dynamics-Informed Protein Design with Structure Conditioning

Identifiable Latent Polynomial Causal Models through the Lens of Change

SYMBOL: Generating Flexible Black-Box Optimizers through Symbolic Equation Learning

Graph Lottery Ticket Automated

Threshold-Consistent Margin Loss for Open-World Deep Metric Learning

The Expressive Leaky Memory Neuron: an Efficient and Expressive Phenomenological Neuron Model Can Solve Long-Horizon Tasks.

DreamSmooth: Improving Model-based Reinforcement Learning via Reward Smoothing

Encoding Unitig-level Assembly Graphs with Heterophilous Constraints for Metagenomic Contigs Binning

Adaptive Regret for Bandits Made Possible: Two Queries Suffice

AdaMerging: Adaptive Model Merging for Multi-Task Learning

Statistically Optimal $K$-means Clustering via Nonnegative Low-rank Semidefinite Programming

AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ

Improved statistical and computational complexity of the mean-field Langevin dynamics under structured data

Zero Bubble (Almost) Pipeline Parallelism

Bridging Neural and Symbolic Representations with Transitional Dictionary Learning

Towards Characterizing Domain Counterfactuals for Invertible Latent Causal Models

Thin-Shell Object Manipulations With Differentiable Physics Simulations

Bayesian Coreset Optimization for Personalized Federated Learning

Beyond Spatio-Temporal Representations: Evolving Fourier Transform for Temporal Graphs

MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models

Towards Robust Fidelity for Evaluating Explainability of Graph Neural Networks

Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs

Towards Best Practices of Activation Patching in Language Models: Metrics and Methods

Scale-Adaptive Diffusion Model for Complex Sketch Synthesis

Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs

On the Over-Memorization During Natural, Robust and Catastrophic Overfitting

Mastering Memory Tasks with World Models

Towards Principled Representation Learning from Videos for Reinforcement Learning

Expected flow networks in stochastic environments and two-player zero-sum games

Towards Unified Multi-Modal Personalization: Large Vision-Language Models for Generative Recommendation and Beyond

DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models

Energy-conserving equivariant GNN for elasticity of lattice architected metamaterials

SALMON: Self-Alignment with Instructable Reward Models

Get more for less: Principled Data Selection for Warming Up Fine-Tuning in LLMs

Augmenting Transformers with Recursively Composed Multi-grained Representations

Adversarial Training on Purification (AToP): Advancing Both Robustness and Generalization

Large Language Models as Generalizable Policies for Embodied Tasks

The Joint Effect of Task Similarity and Overparameterization on Catastrophic Forgetting — An Analytical Model

Fast Equilibrium of SGD in Generic Situations

Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data

Compositional Preference Models for Aligning LMs

Diffusion Posterior Sampling for Linear Inverse Problem Solving: A Filtering Perspective

Demystifying Local & Global Fairness Trade-offs in Federated Learning Using Partial Information Decomposition

Provable Offline Preference-Based Reinforcement Learning

Learning Conditional Invariances through Non-Commutativity

Generative Modeling with Phase Stochastic Bridge

Bandits Meet Mechanism Design to Combat Clickbait in Online Recommendation

RobustTSF: Towards Theory and Design of Robust Time Series Forecasting with Anomalies

Tailoring Self-Rationalizers with Multi-Reward Distillation

Controlling Vision-Language Models for Multi-Task Image Restoration

Frozen Transformers in Language Models Are Effective Visual Encoder Layers

VFLAIR: A Research Library and Benchmark for Vertical Federated Learning

Measuring Vision-Language STEM Skills of Neural Models

Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers

Whole-Song Hierarchical Generation of Symbolic Music Using Cascaded Diffusion Models

MCM: Masked Cell Modeling for Anomaly Detection in Tabular Data

GAIA: Zero-shot Talking Avatar Generation

NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers

CLIP-MUSED: CLIP-Guided Multi-Subject Visual Neural Information Semantic Decoding

How connectivity structure shapes rich and lazy learning in neural circuits

ARGS: Alignment as Reward-Guided Search

PromptTTS 2: Describing and Generating Voices with Text Prompt

Let Models Speak Ciphers: Multiagent Debate through Embeddings

NeuroBack: Improving CDCL SAT Solving using Graph Neural Networks

Understanding when Dynamics-Invariant Data Augmentations Benefit Model-free Reinforcement Learning Updates

Selective Mixup Fine-Tuning for Optimizing Non-Decomposable Objectives

Revisiting Deep Audio-Text Retrieval Through the Lens of Transportation

Text-to-3D with Classifier Score Distillation

Transformers can optimally learn regression mixture models

Dirichlet-based Per-Sample Weighting by Transition Matrix for Noisy Label Learning

Branch-GAN: Improving Text Generation with (not so) Large Language Models

SocioDojo: Building Lifelong Analytical Agents with Real-world Text and Time Series

ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language Models

Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization

A unique M-pattern for micro-expression spotting in long videos

Progressive Fourier Neural Representation for Sequential Video Compilation

Internal Cross-layer Gradients for Extending Homogeneity to Heterogeneity in Federated Learning

iTransformer: Inverted Transformers Are Effective for Time Series Forecasting

Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations

A Mutual Information Perspective on Federated Contrastive Learning

Local Graph Clustering with Noisy Labels

DistillSpec: Improving Speculative Decoding via Knowledge Distillation

Faithful Vision-Language Interpretation via Concept Bottleneck Models

AuG-KD: Anchor-Based Mixup Generation for Out-of-Domain Knowledge Distillation

Stylized Offline Reinforcement Learning: Extracting Diverse High-Quality Behaviors from Heterogeneous Datasets

Variance-aware Regret Bounds for Stochastic Contextual Dueling Bandits

Demystifying Embedding Spaces using Large Language Models

A Newborn Embodied Turing Test for Comparing Object Segmentation Across Animals and Machines

DeepZero: Scaling Up Zeroth-Order Optimization for Deep Model Training

Closing the Gap between TD Learning and Supervised Learning - A Generalisation Point of View.

Unveiling the Pitfalls of Knowledge Editing for Large Language Models

Learning Thresholds with Latent Values and Censored Feedback

Extending Power of Nature from Binary to Real-Valued Graph Learning in Real World

Robustifying and Boosting Training-Free Neural Architecture Search

Guess & Sketch: Language Model Guided Transpilation

Zero and Few-shot Semantic Parsing with Ambiguous Inputs

Boosting of Thoughts: Trial-and-Error Problem Solving with Large Language Models

Large-Vocabulary 3D Diffusion Model with Transformer

An Investigation of Representation and Allocation Harms in Contrastive Learning

Channel Vision Transformers: An Image Is Worth 1 x 16 x 16 Words

Solving High Frequency and Multi-Scale PDEs with Gaussian Processes

Adversarial Attacks on Fairness of Graph Neural Networks

Task structure and nonlinearity jointly determine learned representational geometry

Locality Sensitive Sparse Encoding for Learning World Models Online

ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models

Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph

Tractable MCMC for Private Learning with Pure and Gaussian Differential Privacy

Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

Graph Transformers on EHRs: Better Representation Improves Downstream Performance

SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning

Stable Neural Stochastic Differential Equations in Analyzing Irregular Time Series Data

Scalable Modular Network: A Framework for Adaptive Learning via Agreement Routing

Improved Regret Bounds for Non-Convex Online-Within-Online Meta Learning

Compose and Conquer: Diffusion-Based 3D Depth Aware Composable Image Synthesis

Recursive Generalization Transformer for Image Super-Resolution

Reconciling Spatial and Temporal Abstractions for Goal Representation

Magnushammer: A Transformer-Based Approach to Premise Selection

Score Models for Offline Goal-Conditioned Reinforcement Learning

Treatment Effects Estimation By Uniform Transformer

Scaling Laws for Associative Memories

Entropy-MCMC: Sampling from Flat Basins with Ease

LMUFormer: Low Complexity Yet Powerful Spiking Model With Legendre Memory Units

Representation Deficiency in Masked Language Modeling

Sampling Multimodal Distributions with the Vanilla Score: Benefits of Data-Based Initialization

MaGIC: Multi-modality Guided Image Completion

CO2: Efficient Distributed Training with Full Communication-Computation Overlap

Learning Robust Generalizable Radiance Field with Visibility and Feature Augmented Point Representation

Alice Benchmarks: Connecting Real World Re-Identification with the Synthetic

HoloNets: Spectral Convolutions do extend to Directed Graphs

Searching for High-Value Molecules Using Reinforcement Learning and Transformers

Interpretable Meta-Learning of Physical Systems

An Image Is Worth 1000 Lies: Transferability of Adversarial Images across Prompts on Vision-Language Models

Fast Value Tracking for Deep Reinforcement Learning

Interpretable Sparse System Identification: Beyond Recent Deep Learning Techniques on Time-Series Prediction

FedInverse: Evaluating Privacy Leakage in Federated Learning

CircuitNet 2.0: An Advanced Dataset for Promoting Machine Learning Innovations in Realistic Chip Design Environment

Are Transformers with One Layer Self-Attention Using Low-Rank Weight Matrices Universal Approximators?

Self-Supervised Contrastive Learning for Long-term Forecasting

Federated Orthogonal Training: Mitigating Global Catastrophic Forgetting in Continual Federated Learning

Neuron Activation Coverage: Rethinking Out-of-distribution Detection and Generalization

OctoPack: Instruction Tuning Code Large Language Models

Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation

Open the Black Box: Step-based Policy Updates for Temporally-Correlated Episodic Reinforcement Learning

Rethinking CNN’s Generalization to Backdoor Attack from Frequency Domain

Variance Reduced Halpern Iteration for Finite-Sum Monotone Inclusions

Flow to Better: Offline Preference-based Reinforcement Learning via Preferred Trajectory Generation

LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed Prompts

VBH-GNN: Variational Bayesian Heterogeneous Graph Neural Networks for Cross-subject Emotion Recognition

Neural Rate Control for Learned Video Compression

PnP Inversion: Boosting Diffusion-based Editing with 3 Lines of Code

Harnessing Density Ratios for Online Reinforcement Learning

Sliced Denoising: A Physics-Informed Molecular Pre-Training Method

Is Self-Repair a Silver Bullet for Code Generation?

Unified Human-Scene Interaction via Prompted Chain-of-Contacts

Improved Efficiency Based on Learned Saccade and Continuous Scene Reconstruction From Foveated Visual Sampling

Grounding Multimodal Large Language Models to the World

Context-Aware Meta-Learning

A Poincaré Inequality and Consistency Results for Signal Sampling on Large Graphs

Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection

MetaCoCo: A New Few-Shot Classification Benchmark with Spurious Correlation

Negatively Correlated Ensemble Reinforcement Learning for Online Diverse Game Level Generation

Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised Learning

Causal Fairness under Unobserved Confounding: A Neural Sensitivity Framework

Local Composite Saddle Point Optimization

ASID: Active Exploration for System Identification in Robotic Manipulation

Simple Hierarchical Planning with Diffusion

sRGB Real Noise Modeling via Noise-Aware Sampling with Normalizing Flows

BatteryML: An Open-source Platform for Machine Learning on Battery Degradation

Improving Generalization of Alignment with Human Preferences through Group Invariant Learning

Dynamic Sparse Training with Structured Sparsity

DENEVIL: TOWARDS DECIPHERING AND NAVIGATING THE ETHICAL VALUES OF LARGE LANGUAGE MODELS VIA INSTRUCTION LEARNING

Robustifying State-space Models for Long Sequences via Approximate Diagonalization

Generative Adversarial Equilibrium Solvers

Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models

FedImpro: Measuring and Improving Client Update in Federated Learning

What Makes a Good Prune? Maximal Unstructured Pruning for Maximal Cosine Similarity

Improving LoRA in Privacy-preserving Federated Learning

Efficient Inverse Multiagent Learning

Neural Neighborhood Search for Multi-agent Path Finding

Nemesis: Normalizing the Soft-prompt Vectors of Vision-Language Models

FasterViT: Fast Vision Transformers with Hierarchical Attention

C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersion

DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior

Plugin estimators for selective classification with out-of-distribution detection

P$^2$OT: Progressive Partial Optimal Transport for Deep Imbalanced Clustering

Unprocessing Seven Years of Algorithmic Fairness

Adaptive Stochastic Gradient Algorithm for Black-box Multi-Objective Learning

Intriguing Properties of Data Attribution on Diffusion Models

SpaCE: The Spatial Confounding Environment

How Does Unlabeled Data Provably Help Out-of-Distribution Detection?

AdjointDPM: Adjoint Sensitivity Method for Gradient Backpropagation of Diffusion Probabilistic Models

GlucoBench: Curated List of Continuous Glucose Monitoring Datasets with Prediction Benchmarks

Finite-Time Analysis of On-Policy Heterogeneous Federated Reinforcement Learning

Look, Remember and Reason: Grounded Reasoning in Videos with Language Models

It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition

MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning

Pushing Boundaries: Mixup's Influence on Neural Collapse

Analyzing and Improving Optimal-Transport-based Adversarial Networks

Two-stage LLM Fine-tuning with Less Specialization and More Generalization

LLCP: Learning Latent Causal Processes for Reasoning-based Video Question Answer

Implicit regularization of deep residual networks towards neural ODEs

Provably Efficient UCB-type Algorithms For Learning Predictive State Representations

Inner Classifier-Free Guidance and Its Taylor Expansion for Diffusion Models

Protein Multimer Structure Prediction via Prompt Learning

Symbol as Points: Panoptic Symbol Spotting via Point-based Representation

Compressing Latent Space via Least Volume

CoLiDE: Concomitant Linear DAG Estimation

EBMDock: Neural Probabilistic Protein-Protein Docking via a Differentiable Energy Model

Going Beyond Neural Network Feature Similarity: The Network Feature Complexity and Its Interpretation Using Category Theory

Habitat 3.0: A Co-Habitat for Humans, Avatars, and Robots

A Unified Framework for Bayesian Optimization under Contextual Uncertainty

Learning Large DAGs is Harder than you Think: Many Losses are Minimal for the Wrong DAG

Nearly $d$-Linear Convergence Bounds for Diffusion Models via Stochastic Localization

Active Retrosynthetic Planning Aware of Route Quality

Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency

Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model

Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy

Non-Exchangeable Conformal Risk Control

Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLM

USB-NeRF: Unrolling Shutter Bundle Adjusted Neural Radiance Fields

Are Bert Family Good Instruction Followers? A Study on Their Potential And Limitations

Synergistic Patch Pruning for Vision Transformer: Unifying Intra- & Inter-Layer Patch Importance

Dissecting Sample Hardness: A Fine-Grained Analysis of Hardness Characterization Methods for Data-Centric AI

Epitopological learning and Cannistraci-Hebb network shape intelligence brain-inspired theory for ultra-sparse advantage in deep learning

Early Stopping Against Label Noise Without Validation Data

Contrastive Preference Learning: Learning from Human Feedback without Reinforcement Learning

Unknown Domain Inconsistency Minimization for Domain Generalization

Enhancing Transfer Learning with Flexible Nonparametric Posterior Sampling

Finite Scalar Quantization: VQ-VAE Made Simple

Fixed-Budget Differentially Private Best Arm Identification

Rethinking Backdoor Attacks on Dataset Distillation: A Kernel Method Perspective

Neural Contractive Dynamical Systems

Energy-based Automated Model Evaluation

Unraveling the Enigma of Double Descent: An In-depth Analysis through the Lens of Learned Feature Space

FreeDyG: Frequency Enhanced Continuous-Time Dynamic Graph Model for Link Prediction

Structural Inference with Dynamics Encoding and Partial Correlation Coefficients

SEAL: A Framework for Systematic Evaluation of Real-World Super-Resolution

Toward Optimal Policy Population Growth in Two-Player Zero-Sum Games

Towards Robust and Efficient Cloud-Edge Elastic Model Adaptation via Selective Entropy Distillation

Polynormer: Polynomial-Expressive Graph Transformer in Linear Time

Beyond task performance: evaluating and reducing the flaws of large multimodal models with in-context-learning

A Differentially Private Clustering Algorithm for Well-Clustered Graphs

The Trickle-down Impact of Reward Inconsistency on RLHF

Contrastive Learning is Spectral Clustering on Similarity Graph

Better Neural PDE Solvers Through Data-Free Mesh Movers

Weatherproofing Retrieval for Localization with Generative AI and Geometric Consistency

Memorization Capacity of Multi-Head Attention in Transformers

LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models

Domain-Inspired Sharpness-Aware Minimization Under Domain Shifts

Adaptive Retrieval and Scalable Indexing for k-NN Search with Cross-Encoders

Enhancing Group Fairness in Online Settings Using Oblique Decision Forests

True Knowledge Comes from Practice: Aligning Large Language Models with Embodied Environments via Reinforcement Learning

Maximum Likelihood Estimation is All You Need for Well-Specified Covariate Shift

A Sublinear Adversarial Training Algorithm

PhyloGFN: Phylogenetic inference with generative flow networks

Understanding Certified Training with Interval Bound Propagation

Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images

Performance Gaps in Multi-view Clustering under the Nested Matrix-Tensor Model

Language Model Beats Diffusion - Tokenizer is key to visual generation

ZeRO++: Extremely Efficient Collective Communication for Large Model Training

Multimodal Learning Without Labeled Multimodal Data: Guarantees and Applications

Dual Associated Encoder for Face Restoration

CausalLM is not optimal for in-context learning

An Unforgeable Publicly Verifiable Watermark for Large Language Models

Deep Orthogonal Hypersphere Compression for Anomaly Detection

IMPUS: Image Morphing with Perceptually-Uniform Sampling Using Diffusion Models

Evaluating the Zero-shot Robustness of Instruction-tuned Language Models

Does Writing with Language Models Reduce Content Diversity?

Class Probability Matching with Calibrated Networks for Label Shift Adaption

Few-shot Hybrid Domain Adaptation of Image Generator

Entity-Centric Reinforcement Learning for Object Manipulation from Pixels

Compositional Conservatism: A Transductive Approach in Offline Reinforcement Learning

Adaptive Rational Activations to Boost Deep Reinforcement Learning

InterpGNN: Understand and Improve Generalization Ability of Transdutive GNNs through the Lens of Interplay between Train and Test Nodes

A Progressive Training Framework for Spiking Neural Networks with Learnable Multi-hierarchical Model

Memory-Assisted Sub-Prototype Mining for Universal Domain Adaptation

Bounding Box Stability against Feature Dropout Reflects Detector Generalization across Environments

CIFAR-10-Warehouse: Broad and More Realistic Testbeds in Model Generalization Analysis

Ito Diffusion Approximation of Universal Ito Chains for Sampling, Optimization and Boosting

OWL: A Large Language Model for IT Operations

Towards Meta-Pruning via Optimal Transport

Würstchen: An Efficient Architecture for Large-Scale Text-to-Image Diffusion Models

REFACTOR: Learning to Extract Theorems from Proofs

From Posterior Sampling to Meaningful Diversity in Image Restoration

Federated Q-Learning: Linear Regret Speedup with Low Communication Cost

Transformer Fusion with Optimal Transport

A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models

Dynamic Neighborhood Construction for Structured Large Discrete Action Spaces

LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset

A Recipe for Improved Certifiable Robustness

Sparse MoE with Language Guided Routing for Multilingual Machine Translation

Neural Architecture Retrieval

Neural SDF Flow for 3D Reconstruction of Dynamic Scenes

Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedback

Convolution Meets LoRA: Parameter Efficient Finetuning for Segment Anything Model

Teaching Arithmetic to Small Transformers

ADOPD: A Large-Scale Document Page Decomposition Dataset

Sample-Efficiency in Multi-Batch Reinforcement Learning: The Need for Dimension-Dependent Adaptivity

Compressing LLMs: The Truth is Rarely Pure and Never Simple

To the Cutoff... and Beyond? A Longitudinal Perspective on LLM Data Contamination

ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search

Large Language Models as Tool Makers

LayoutNUWA: Revealing the Hidden Layout Expertise of Large Language Models

Delphic Offline Reinforcement Learning under Nonidentifiable Hidden Confounding

Learning Mean Field Games on Sparse Graphs: A Hybrid Graphex Approach

P2Seg: Pointly-supervised Segmentation via Mutual Distillation

SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores

Efficient Subgraph GNNs by Learning Effective Selection Policies

Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning

Label-free Node Classification on Graphs with Large Language Models (LLMs)

LLM-grounded Video Diffusion Models

Understanding In-Context Learning in Transformers and LLMs by Learning to Learn Discrete Functions

Multimodal Web Navigation with Instruction-Finetuned Foundation Models

Function-space Parameterization of Neural Networks for Sequential Learning

One-hot Generalized Linear Model for Switching Brain State Discovery

Large Language Models as Analogical Reasoners

Generative Modeling of Regular and Irregular Time Series Data via Koopman VAEs

Annealing Self-Distillation Rectification Improves Adversarial Training

H2O-SDF: Two-phase Learning for 3D Indoor Reconstruction using Object Surface Fields

Boundary Denoising for Video Activity Localization

Out-of-Distribution Detection by Leveraging Between-Layer Transformation Smoothness

RLIF: Interactive Imitation Learning as Reinforcement Learning

Diffusion in Diffusion: Cyclic One-Way Diffusion for Text-Vision-Conditioned Generation

On Trajectory Augmentations for Off-Policy Evaluation

How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions

Alt-Text with Context: Improving Accessibility for Images on Twitter

Combinatorial Bandits for Maximum Value Reward Function under Value-Index Feedback

Reward-Free Curricula for Training Robust World Models

Yet Another ICU Benchmark: A Flexible Multi-Center Framework for Clinical ML

PORF: POSE RESIDUAL FIELD FOR ACCURATE NEURAL SURFACE RECONSTRUCTION

PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation

Convergence of Bayesian Bilevel Optimization

Functional Interpolation for Relative Positions improves Long Context Transformers

Consistency Training with Learnable Data Augmentation for Graph Anomaly Detection with Limited Supervision

Rotation Has Two Sides: Evaluating Data Augmentation for Deep One-class Classification

Small-scale proxies for large-scale Transformer training instabilities

Lion Secretly Solves a Constrained Optimization: As Lyapunov Predicts

Improving equilibrium propagation without weight symmetry through Jacobian homeostasis

Symmetric Single Index Learning

Tight Rates in Supervised Outlier Transfer Learning

Node2ket: Efficient High-Dimensional Network Embedding in Quantum Hilbert Space

Towards LLM4QPE: Unsupervised Pretraining of Quantum Property Estimation and A Benchmark

Object-Aware Inversion and Reassembly for Image Editing

Analysis of Learning a Flow-based Generative Model from Limited Sample Complexity

What's In My Big Data?

Learning Over Molecular Conformer Ensembles: Datasets and Benchmarks

Minimum width for universal approximation using ReLU networks on compact domain

Provable Memory Efficient Self-Play Algorithm for Model-free Reinforcement Learning

Retro-fallback: retrosynthetic planning in an uncertain world

Generative Human Motion Stylization in Latent Space

TUVF: Learning Generalizable Texture UV Radiance Fields

Achieving the Pareto Frontier of Regret Minimization and Best Arm Identification in Multi-Armed Bandits

Monte Carlo guided Denoising Diffusion models for Bayesian linear inverse problems.

Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks

Fast Imitation via Behavior Foundation Models

Peering Through Preferences: Unraveling Feedback Acquisition for Aligning Large Language Models

MEND: Meta Demonstration Distillation for Efficient and Effective In-Context Learning

Ins-DetCLIP: Aligning Detection Model to Follow Human-Language Instruction

ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs

Only Pay for What Is Uncertain: Variance-Adaptive Thompson Sampling

The Consensus Game: Language Model Generation via Equilibrium Search

Tool-Augmented Reward Modeling

Procedural Fairness Through Decoupling Objectionable Data Generating Components

Generalized Policy Iteration using Tensor Approximation for Hybrid Control

Scaling Supervised Local Learning with Augmented Auxiliary Networks

Decongestion by Representation: Learning to Improve Economic Welfare in Marketplaces

Diffusion Models for Multi-Task Generative Modeling

OpenChat: Advancing Open-source Language Models with Mixed-Quality Data

Causal Modelling Agents: Causal Graph Discovery through Synergising Metadata- and Data-driven Reasoning

FedCompass: Efficient Cross-Silo Federated Learning on Heterogeneous Client Devices Using a Computing Power-Aware Scheduler

Bandits with Replenishable Knapsacks: the Best of both Worlds

Bridging State and History Representations: Understanding Self-Predictive RL

Latent 3D Graph Diffusion

State Representation Learning Using an Unbalanced Atlas

Scalable Monotonic Neural Networks

Towards a statistical theory of data selection under weak supervision

Multilinear Operator Networks

BayesPrompt: Prompting Large-Scale Pre-Trained Language Models on Few-shot Inference via Debiased Domain Abstraction

A Stable, Fast, and Fully Automatic Learning Algorithm for Predictive Coding Networks

Bongard-OpenWorld: Few-Shot Reasoning for Free-form Visual Concepts in the Real World

NuwaDynamics: Discovering and Updating in Causal Spatio-Temporal Modeling

Rethinking Information-theoretic Generalization: Loss Entropy Induced PAC Bounds

Decoupling Weighing and Selecting for Integrating Multiple Graph Pre-training Tasks

Democratizing Fine-grained Visual Recognition with Large Language Models

Analyzing Feed-Forward Blocks in Transformers through the Lens of Attention Maps

GAFormer: Enhancing Timeseries Transformers Through Group-Aware Embeddings

DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Text

SpeechTokenizer: Unified Speech Tokenizer for Speech Language Models

Prompt Learning with Quaternion Networks

Prioritized Soft Q-Decomposition for Lexicographic Reinforcement Learning

A Simple Interpretable Transformer for Fine-Grained Image Classification and Analysis

MBR and QE Finetuning: Training-time Distillation of the Best and Most Expensive Decoding Methods

Generalizability of Adversarial Robustness Under Distribution Shifts

UC-NERF: Neural Radiance Field for Under-Calibrated Multi-View Cameras in Autonomous Driving

LUM-ViT: Learnable Under-sampling Mask Vision Transformer for Bandwidth Limited Optical Signal Acquisition

Facing the Elephant in the Room: Visual Prompt Tuning or Full finetuning?

Accelerated Sampling with Stacked Restricted Boltzmann Machines

BECLR: Batch Enhanced Contrastive Few-Shot Learning

DyST: Towards Dynamic Neural Scene Representations on Real-World Videos

Logical Languages Accepted by Transformer Encoders with Hard Attention

Meta-Learning Priors Using Unrolled Proximal Networks

NfgTransformer: Equivariant Representation Learning for Normal-form Games

A Topological Perspective on Demystifying GNN-Based Link Prediction Performance

Self-Supervised Speech Quality Estimation and Enhancement Using Only Clean Speech

Circumventing Concept Erasure Methods For Text-To-Image Generative Models

Continual Learning on a Diet: Learning from Sparsely Labeled Streams Under Constrained Computation

Energy-guided Entropic Neural Optimal Transport

On the Posterior Distribution in Denoising: Application to Uncertainty Quantification

Towards Eliminating Hard Label Constraints in Gradient Inversion Attacks

Soft Mixture Denoising: Beyond the Expressive Bottleneck of Diffusion Models

Horizon-free Reinforcement Learning in Adversarial Linear Mixture MDPs

Ensemble Distillation for Unsupervised Constituency Parsing

MAPE-PPI: Towards Effective and Efficient Protein-Protein Interaction Prediction via Microenvironment-Aware Protein Embedding

Approximately Piecewise E(3) Equivariant Point Networks

EventRPG: Event Data Augmentation with Relevance Propagation Guidance

LLMCarbon: Modeling the End-to-End Carbon Footprint of Large Language Models

Implicit Maximum a Posteriori Filtering via Adaptive Optimization

Multi-modal Gaussian Process Variational Autoencoders for Neural and Behavioral Data

ContextRef: Evaluating Referenceless Metrics for Image Description Generation

Diffusion Model for Dense Matching

BENO: Boundary-embedded Neural Operators for Elliptic PDEs

Kernel Metric Learning for In-Sample Off-Policy Evaluation of Deterministic RL Policies

On Double Descent in Reinforcement Learning with LSTD and Random Features

Bayesian Bi-clustering of Neural Spiking Activity with Latent Structures

Functional Bayesian Tucker Decomposition for Continuous-indexed Tensor Data

Doubly Robust Proximal Causal Learning for Continuous Treatments

SaNN: Simple Yet Powerful Simplicial-aware Neural Networks

DMBP: Diffusion model-based predictor for robust offline reinforcement learning against state observation perturbations

Bounds on Representation-Induced Confounding Bias for Treatment Effect Estimation

Making Retrieval-Augmented Language Models Robust to Irrelevant Context

GAIA: a benchmark for General AI Assistants

Polynomial Width is Sufficient for Set Representation with High-dimensional Features

AUC-CL: A Batchsize-Robust Framework for Self-Supervised Contrastive Representation Learning

Adversarial Causal Bayesian Optimization

A Neural Framework for Generalized Causal Sensitivity Analysis

Fast, Expressive $\mathrm{SE}(n)$ Equivariant Networks through Weight-Sharing in Position-Orientation Space

Most discriminative stimuli for functional cell type clustering

Efficient Backpropagation with Variance Controlled Adaptive Sampling

Improving Intrinsic Exploration by Creating Stationary Objectives

A Dynamical View of the Question of Why

SPTNet: An Efficient Alternative Framework for Generalized Category Discovery with Spatial Prompt Tuning

CoBIT: A Contrastive Bi-directional Image-Text Generation Model

Retrieval-based Disentangled Representation Learning with Natural Language Supervision

Large Language Models are Efficient Learners of Noise-Robust Speech Recognition

Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularization

Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning

Leveraging augmented-Lagrangian techniques for differentiating over infeasible quadratic programs in machine learning

FedDA: Faster Adaptive Gradient Methods for Federated Constrained Optimization

Conformal Language Modeling

GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction

Space Group Constrained Crystal Generation

SliceGPT: Compress Large Language Models by Deleting Rows and Columns

Generating Images with 3D Annotations Using Diffusion Models

The importance of feature preprocessing for differentially private linear optimization

Conditional Instrumental Variable Regression with Representation Learning for Causal Inference

Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Data

Improving the Convergence of Dynamic NeRFs via Optimal Transport

Mean Field Theory in Deep Metric Learning

Prompt Risk Control: A Rigorous Framework for Responsible Deployment of Large Language Models

Abstractors and relational cross-attention: An inductive bias for explicit relational reasoning in Transformers

Ground-A-Video: Zero-shot Grounded Video Editing using Text-to-image Diffusion Models

Get What You Want, Not What You Don't: Image Content Suppression for Text-to-Image Diffusion Models

Confronting Reward Model Overoptimization with Constrained RLHF

Un-Mixing Test-Time Normalization Statistics: Combatting Label Temporal Correlation

InstructPix2NeRF: Instructed 3D Portrait Editing from a Single Image

Interpretable Diffusion via Information Decomposition

LQ-LoRA: Low-rank plus Quantized Matrix Decomposition for Efficient Language Model Finetuning

Adaptive Self-training Framework for Fine-grained Scene Graph Generation

Video Language Planning

Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting

Sparse Weight Averaging with Multiple Particles for Iterative Magnitude Pruning

Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts

Grounding Language Plans in Demonstrations Through Counterfactual Perturbations

Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Models

Learning Decentralized Partially Observable Mean Field Control for Artificial Collective Behavior

Less or More From Teacher: Exploiting Trilateral Geometry For Knowledge Distillation

COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL

Neuron-Enhanced AutoEncoder Matrix Completion and Collaborative Filtering: Theory and Practice

Efficient ConvBN Blocks for Transfer Learning and Beyond

Mind Your Augmentation: The Key to Decoupling Dense Self-Supervised Learning

RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval

Lipschitz Singularities in Diffusion Models

AUGCAL: Improving Sim2Real Adaptation by Uncertainty Calibration on Augmented Synthetic Images

RECOMBINER: Robust and Enhanced Compression with Bayesian Implicit Neural Representations

Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression

Adversarial Adaptive Sampling: Unify PINN and Optimal Transport for the Approximation of PDEs

Vision-Language Foundation Models as Effective Robot Imitators

Learning Nash Equilibria in Rank-1 Games

GTMGC: Using Graph Transformer to Predict Molecule’s Ground-State Conformation

FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimators

Fake It Till Make It: Federated Learning with Consensus-Oriented Generation

Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models

STREAM: Spatio-TempoRal Evaluation and Analysis Metric for Video Generative Models

METRA: Scalable Unsupervised RL with Metric-Aware Abstraction

Transferring Learning Trajectories of Neural Networks

Scalable and Effective Implicit Graph Neural Networks on Large Graphs

Rethinking Branching on Exact Combinatorial Optimization Solver: The First Deep Symbolic Discovery Framework

GraphPulse: Topological representations for temporal graph property prediction

Lewis's Signaling Game as beta-VAE For Natural Word Lengths and Segments

MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training

Mediator Interpretation and Faster Learning Algorithms for Linear Correlated Equilibria in General Sequential Games

R-MAE: Regions Meet Masked Autoencoders

Label-Focused Inductive Bias over Latent Object Features in Visual Classification

Dissecting learning and forgetting in language model finetuning

Prediction without Preclusion: Recourse Verification with Reachable Sets

Gene Regulatory Network Inference in the Presence of Dropouts: a Causal View

Federated Causal Discovery from Heterogeneous Data

Amortized Network Intervention to Steer the Excitatory Point Processes

Decodable and Sample Invariant Continuous Object Encoder

Tangent Transformers for Composition,Privacy and Removal

Beyond Memorization: Violating Privacy via Inference with Large Language Models

Time Travel in LLMs: Tracing Data Contamination in Large Language Models

How Realistic Is Your Synthetic Data? Constraining Deep Generative Models for Tabular Data

CivRealm: A Learning and Reasoning Odyssey in Civilization for Decision-Making Agents

Masked Audio Generation using a Single Non-Autoregressive Transformer

Unconstrained Stochastic CCA: Unifying Multiview and Self-Supervised Learning

lpNTK: Better Generalisation with Less Data via Sample Interaction During Learning

Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs

Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization

Sliced Wasserstein Estimation with Control Variates

VONet: Unsupervised Video Object Learning With Parallel U-Net Attention and Object-wise Sequential VAE

Relay Diffusion: Unifying diffusion process across resolutions for image synthesis

A representation-learning game for classes of prediction tasks

Query-Policy Misalignment in Preference-Based Reinforcement Learning

SparseFormer: Sparse Visual Recognition via Limited Latent Tokens

NECO: NEural Collapse Based Out-of-distribution detection

EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision

Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning

Time-LLM: Time Series Forecasting by Reprogramming Large Language Models

Accurate Forgetting for Heterogeneous Federated Continual Learning

EControl: Fast Distributed Optimization with Compression and Error Control

Divide and not forget: Ensemble of selectively trained experts in Continual Learning

UniAdapter: Unified Parameter-Efficient Transfer Learning for Cross-modal Modeling

Learning No-Regret Sparse Generalized Linear Models with Varying Observation(s)

Nevis'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research

Protein-ligand binding representation learning from fine-grained interactions

Universal Jailbreak Backdoors from Poisoned Human Feedback

VDT: General-purpose Video Diffusion Transformers via Mask Modeling

EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models

GraphCare: Enhancing Healthcare Predictions with Personalized Knowledge Graphs

Grokking in Linear Estimators -- A Solvable Model that Groks without Understanding

Constrained Decoding for Cross-lingual Label Projection

Efficient Heterogeneous Meta-Learning via Channel Shuffling Modulation

Tag2Text: Guiding Vision-Language Model via Image Tagging

Masked Autoencoders with Multi-Window Local-Global Attention Are Better Audio Learners

Multi-task Learning with 3D-Aware Regularization

Latent Intuitive Physics: Learning to Transfer Hidden Physics from A 3D Video

MixSATGEN: Learning Graph Mixing for SAT Instance Generation

On the Parameterization of Second-Order Optimization Effective towards the Infinite Width

Pareto Deep Long-Tailed Recognition: A Conflict-Averse Solution

Gradual Domain Adaptation via Gradient Flow

Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks

Layer-wise linear mode connectivity

Guiding Masked Representation Learning to Capture Spatio-Temporal Relationship of Electrocardiogram

Decoupling regularization from the action space

Source-Free and Image-Only Unsupervised Domain Adaptation for Category Level Object Pose Estimation

Learning in reverse causal strategic environments with ramifications on two sided markets

Learning to design protein-protein interactions with enhanced generalization

CLAP: Collaborative Adaptation for Patchwork Learning

Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification

Towards Understanding Factual Knowledge of Large Language Models

Social Reward: Evaluating and Enhancing Generative AI through Million-User Feedback from an Online Creative Community

Invariance-based Learning of Latent Dynamics

Addressing Signal Delay in Deep Reinforcement Learning

GRANDE: Gradient-Based Decision Tree Ensembles for Tabular Data

ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate

Differentially Private Synthetic Data via Foundation Model APIs 1: Images

On Differentially Private Federated Linear Contextual Bandits

Federated Wasserstein Distance

Win-Win: Training High-Resolution Vision Transformers from Two Windows

Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning

Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation

Trajeglish: Traffic Modeling as Next-Token Prediction

Bayesian Low-rank Adaptation for Large Language Models

Detecting, Explaining, and Mitigating Memorization in Diffusion Models

An Intuitive Multi-Frequency Feature Representation for SO(3)-Equivariant Networks

CrossLoco: Human Motion Driven Control of Legged Robots via Guided Unsupervised Reinforcement Learning

Brain decoding: toward real-time reconstruction of visual perception

Cauchy-Schwarz Divergence Information Bottleneck for Regression

Adaptive Window Pruning for Efficient Local Motion Deblurring

Heterogeneous Personalized Federated Learning by Local-Global Updates Mixing via Convergence Rate

ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models

TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting

Continuous-Multiple Image Outpainting in One-Step via Positional Query and A Diffusion-based Approach

Pre-Training Goal-based Models for Sample-Efficient Reinforcement Learning

A Primal-Dual Approach to Solving Variational Inequalities with General Constraints

Assessing Uncertainty in Similarity Scoring: Performance & Fairness in Face Recognition

CALICO: Self-Supervised Camera-LiDAR Contrastive Pre-training for BEV Perception

Robust Classification via Regression for Learning with Noisy Labels

Does CLIP’s generalization performance mainly stem from high train-test similarity?

GNNBoundary: Towards Explaining Graph Neural Networks through the Lens of Decision Boundaries

Flag Aggregator: Scalable Distributed Training under Failures and Augmented Losses using Convex Optimization

Understanding prompt engineering may not require rethinking generalization

Backdoor Federated Learning by Poisoning Backdoor-Critical Layers

Reverse Diffusion Monte Carlo

Spurious Feature Diversification Improves Out-of-distribution Generalization

Interpreting Robustness Proofs of Deep Neural Networks

OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text

Incentive-Aware Federated Learning with Training-Time Model Rewards

SWAP-NAS: Sample-Wise Activation Patterns for Ultra-fast NAS

Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning

Communication-Efficient Federated Non-Linear Bandit Optimization

Provable Robust Watermarking for AI-Generated Text

Respect the model: Fine-grained and Robust Explanation with Sharing Ratio Decomposition

Exploring Effective Stimulus Encoding via Vision System Modeling for Visual Prostheses

An LLM can Fool Itself: A Prompt-Based Adversarial Attack

WildFusion: Learning 3D-Aware Latent Diffusion Models in View Space

Prometheus: Inducing Fine-Grained Evaluation Capability in Language Models

Enhancing Human-AI Collaboration Through Logic-Guided Reasoning

Synaptic Weight Distributions Depend on the Geometry of Plasticity

ArchLock: Locking DNN Transferability at the Architecture Level with a Zero-Cost Binary Predictor

3D-Aware Hypothesis & Verification for Generalizable Relative Object Pose Estimation

Outlier-Robust Subsampling Techniques for Persistent Homology

On Penalty Methods for Nonconvex Bilevel Optimization and First-Order Stochastic Approximation

ODEFormer: Symbolic Regression of Dynamical Systems with Transformers

VertiBench: Advancing Feature Distribution Diversity in Vertical Federated Learning Benchmarks

Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition

Neuro-Inspired Information-Theoretic Hierarchical Perception for Multimodal Learning

Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression

Efficient Sharpness-Aware Minimization for Molecular Graph Transformer Models

When can transformers reason with abstract symbols?

Novel Quadratic Constraints for Extending LipSDP beyond Slope-Restricted Activations

DOS: Diverse Outlier Sampling for Out-of-Distribution Detection

Safe RLHF: Safe Reinforcement Learning from Human Feedback

Mayfly: a Neural Data Structure for Graph Stream Summarization

Steve-Eye: Equipping LLM-based Embodied Agents with Visual Perception in Open Worlds

Towards Faithful Explanations: Boosting Rationalization with Shortcuts Discovery

On Adversarial Training without Perturbing all Examples

ReLoRA: High-Rank Training Through Low-Rank Updates

VDC: Versatile Data Cleanser based on Visual-Linguistic Inconsistency by Multimodal Large Language Models

Provable Compositional Generalization for Object-Centric Learning

Neural Common Neighbor with Completion for Link Prediction

Stack Attention: Improving the Ability of Transformers to Model Hierarchical Patterns

DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models

Masked Completion via Structured Diffusion with White-Box Transformers

PubDef: Defending Against Transfer Attacks From Public Models

Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation Patching

Efficient Streaming Language Models with Attention Sinks

Defining and extracting generalizable interaction primitives from DNNs

LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models

Fine-Tuning Language Models for Factuality

Minimax optimality of convolutional neural networks for infinite dimensional input-output problems and separation from kernel methods

Training Bayesian Neural Networks with Sparse Subspace Variational Inference

Spatially-Aware Transformers for Embodied Agents

DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified Robustness

Seer: Language Instructed Video Prediction with Latent Diffusion Models

Let's do the time-warp-attend: Learning topological invariants of dynamical systems

Querying Easily Flip-flopped Samples for Deep Active Learning

Quasi-Monte Carlo for 3D Sliced Wasserstein

TAB: Temporal Accumulated Batch Normalization in Spiking Neural Networks

Large Content And Behavior Models To Understand, Simulate, And Optimize Content And Behavior

Improved algorithm and bounds for successive projection

Statistical Perspective of Top-K Sparse Softmax Gating Mixture of Experts

Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models

GeoLLM: Extracting Geospatial Knowledge from Large Language Models

LILO: Learning Interpretable Libraries by Compressing and Documenting Code

NOLA: Compressing LoRA using Linear Combination of Random Basis

Learning Hierarchical World Models with Adaptive Temporal Abstractions from Discrete Latent Dynamics

Beyond Vanilla Variational Autoencoders: Detecting Posterior Collapse in Conditional and Hierarchical Variational Autoencoders

Faithful and Efficient Explanations for Neural Networks via Neural Tangent Kernel Surrogate Models

On Characterizing the Trade-off in Invariant Representation Learning

Diffeomorphic Mesh Deformation via Efficient Optimal Transport for Cortical Surface Reconstruction

Learning Semantic Proxies from Visual Prompts for Parameter-Efficient Fine-Tuning in Deep Metric Learning

Llemma: An Open Language Model for Mathematics

Zeroth-Order Optimization Meets Human Feedback: Provable Learning via Ranking Oracles

Distributionally Robust Optimization with Bias and Variance Reduction

Adapting and Evaluating Influence-Estimation Methods for Gradient-Boosted Decision Trees

Fast Hyperboloid Decision Tree Algorithms

TiC-CLIP: Continual Training of CLIP Models

Neural Ordinary Differential Equations for Modeling Epidemic Spreading

Tree Cross Attention

Proximal Policy Gradient Arborescence for Quality Diversity Reinforcement Learning

Understanding Reconstruction Attacks with the Neural Tangent Kernel and Dataset Distillation

Multi-resolution HuBERT: Multi-resolution Speech Self-Supervised Learning with Masked Unit Prediction

Neur2RO: Neural Two-Stage Robust Optimization

Variational Bayesian Last Layers

Finetuning Text-to-Image Diffusion Models for Fairness

IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Models

Improving Non-Transferable Representation Learning by Harnessing Content and Style

AmortizedPeriod: Attention-based Amortized Inference for Periodicity Identification

Decision ConvFormer: Local Filtering in MetaFormer is Sufficient for Decision Making

CABINET: Content Relevance-based Noise Reduction for Table Question Answering

Efficient local linearity regularization to overcome catastrophic overfitting

TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting

Social-Transmotion: Promptable Human Trajectory Prediction

The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Language Models

Controlled Text Generation via Language Model Arithmetic

Neural Fourier Transform: A General Approach to Equivariant Representation Learning

Hybrid Sharing for Multi-Label Image Classification

Learning invariant representations of time-homogeneous stochastic dynamical systems

Label-Agnostic Forgetting: A Supervision-Free Unlearning in Deep Models

On the Fairness ROAD: Robust Optimization for Adversarial Debiasing

Understanding Transferable Representation Learning and Zero-shot Transfer in CLIP

Complex priors and flexible inference in recurrent circuits with dendritic nonlinearities

A Variational Framework for Estimating Continuous Treatment Effects with Measurement Error

SolidGen: An Autoregressive Model for Direct B-rep Synthesis

DEEP NEURAL NETWORK INITIALIZATION WITH SPARSITY INDUCING ACTIVATIONS

Guiding Instruction-based Image Editing via Multimodal Large Language Models

A Foundation Model for Error Correction Codes

Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space

Learning to Make Adherence-aware Advice

Tree Search-Based Policy Optimization under Stochastic Execution Delay

High Fidelity Neural Audio Compression

Sufficient conditions for offline reactivation in recurrent neural networks

A Generalist Agent

Scalable Real-Time Recurrent Learning Using Columnar-Constructive Networks

Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis

Offline Data Enhanced On-Policy Policy Gradient with Provable Guarantees

InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modules

Towards Optimal Regret in Adversarial Linear MDPs with Bandit Feedback

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Graph Generation with $K^2$-trees

Memory-Consistent Neural Networks for Imitation Learning

PRIME: Prioritizing Interpretability in Failure Mode Extraction

Bayesian Neural Controlled Differential Equations for Treatment Effect Estimation

OpenTab: Advancing Large Language Models as Open-domain Table Reasoners

Lemur: Integrating Large Language Models in Automated Program Verification

A Simple and Effective Pruning Approach for Large Language Models

Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions

Quadratic models for understanding catapult dynamics of neural networks

Geographic Location Encoding with Spherical Harmonics and Sinusoidal Representation Networks

Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion

Learning to Solve Bilevel Programs with Binary Tender

PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Training

Fusing Models with Complementary Expertise

Making RL with Preference-based Feedback Efficient via Randomization

Local Search GFlowNets

Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priors

Data-independent Module-aware Pruning for Hierarchical Vision Transformers

Matryoshka Diffusion Models

Pre-training with Synthetic Data Helps Offline Reinforcement Learning

SOHES: Self-supervised Open-world Hierarchical Entity Segmentation

Understanding the Effects of RLHF on LLM Generalisation and Diversity

Overcoming the Pitfalls of Vision-Language Model Finetuning for OOD Generalization

Addressing Loss of Plasticity and Catastrophic Forgetting in Continual Learning

Reinforcement Symbolic Regression Machine

RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation

BRUSLEATTACK: A QUERY-EFFICIENT SCORE- BASED BLACK-BOX SPARSE ADVERSARIAL ATTACK

Learning Energy Decompositions for Partial Inference in GFlowNets

Unlocking the Power of Representations in Long-term Novelty-based Exploration

Augmented Bayesian Policy Search

ImagenHub: Standardizing the evaluation of conditional image generation models

Universal Humanoid Motion Representations for Physics-Based Control

PILOT: An $\mathcal{O}(1/K)$-Convergent Approach for Policy Evaluation with Nonlinear Function Approximation

Estimating Conditional Mutual Information for Dynamic Feature Selection

ALAM: Averaged Low-Precision Activation for Memory-Efficient Training of Transformer Models

Spectrally Transformed Kernel Regression

Adversarial AutoMixup

First-order ANIL provably learns representations despite overparametrisation

Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization

GenSim: Generating Robotic Simulation Tasks via Large Language Models

Multi-View Causal Representation Learning with Partial Observability

Long-Term Typhoon Trajectory Prediction: A Physics-Conditioned Approach Without Reanalysis Data

DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Models

Leveraging Optimization for Adaptive Attacks on Image Watermarks

CNN Kernels Can Be the Best Shapelets

A Lie Group Approach to Riemannian Batch Normalization

Modelling complex vector drawings with stroke-clouds

WizardLM: Empowering Large Pre-Trained Language Models to Follow Complex Instructions

Exposing Text-Image Inconsistency Using Diffusion Models

Task Planning for Visual Room Rearrangement under Partial Observability

FOSI: Hybrid First and Second Order Optimization

InstructCV: Instruction-Tuned Text-to-Image Diffusion Models as Vision Generalists

3D Reconstruction with Generalizable Neural Fields using Scene Priors

Lagrangian Flow Networks for Conservation Laws

fairret: a Framework for Differentiable Fairness Regularization Terms

LitCab: Lightweight Language Model Calibration over Short- and Long-form Responses

Massive Editing for Large Language Models via Meta Learning

Fantastic Generalization Measures are Nowhere to be Found

VeRA: Vector-based Random Matrix Adaptation

Towards Imitation Learning to Branch for MIP: A Hybrid Reinforcement Learning based Sample Augmentation Approach

Implicit Gaussian process representation of vector fields over arbitrary latent manifolds

Reclaiming the Source of Programmatic Policies: Programmatic versus Latent Spaces

V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection

TESTAM: A Time-Enhanced Spatio-Temporal Attention Model with Mixture of Experts

Learning Multi-Faceted Prototypical User Interests

PeFLL: Personalized Federated Learning by Learning to Learn

Hebbian Learning based Orthogonal Projection for Continual Learning of Spiking Neural Networks

Delta-AI: Local objectives for amortized inference in sparse graphical models

DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization

Effective Structural Encodings via Local Curvature Profiles

Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering

SyncDreamer: Generating Multiview-consistent Images from a Single-view Image

InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation

Improving Offline RL by Blending Heuristics

Learning dynamic representations of the functional connectome in neurobiological networks

RAPPER: Reinforced Rationale-Prompted Paradigm for Natural Language Explanation in Visual Question Answering

Learning interpretable control inputs and dynamics underlying animal locomotion

The Effectiveness of Random Forgetting for Robust Generalization

AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents

Unraveling the Key Components of OOD Generalization via Diversification

Bilevel Optimization under Unbounded Smoothness: A New Algorithm and Convergence Analysis

JoMA: Demystifying Multilayer Transformers via Joint Dynamics of MLP and Attention

ODICE: Revealing the Mystery of Distribution Correction Estimation via Orthogonal-gradient Update

Online GNN Evaluation Under Test-time Graph Distribution Shifts

Particle Guidance: non-I.I.D. Diverse Sampling with Diffusion Models

Cascading Reinforcement Learning

CCIL: Continuity-Based Data Augmentation for Corrective Imitation Learning

A Black-box Approach for Non-stationary Multi-agent Reinforcement Learning

Disentangling Time Series Representations via Contrastive Independence-of-Support on l-Variational Inference

LoftQ: LoRA-Fine-Tuning-aware Quantization for Large Language Models

ReMasker: Imputing Tabular Data with Masked Autoencoding

A Cognitive Model for Learning Abstract Relational Structures from Memory-based Decision-Making Tasks

Diving Segmentation Model into Pixels

Robust Similarity Learning with Difference Alignment Regularization

Exploring Weight Balancing on Long-Tailed Recognition Problem

Towards Enhancing Time Series Contrastive Learning: A Dynamic Bad Pair Mining Approach

GENOME: Generative Neuro-Symbolic Visual Reasoning by Growing and Reusing Modules

Plug-and-Play: An Efficient Post-training Pruning Method for Large Language Models

Rethinking Channel Dimensions to Isolate Outliers for Low-bit Weight Quantization of Large Language Models

LabelDP-Pro: Learning with Label Differential Privacy via Projections

FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing

Navigating Text-To-Image Customization: From LyCORIS Fine-Tuning to Model Evaluation

Learning to Jointly Understand Visual and Tactile Signals

AirPhyNet: Harnessing Physics-Guided Neural Networks for Air Quality Prediction

A path-norm toolkit for modern networks: consequences, promises and challenges

Deep Confident Steps to New Pockets: Strategies for Docking Generalization

Training-free Multi-objective Diffusion Model for 3D Molecule Generation

Towards Codable Watermarking for Injecting Multi-Bits Information to LLMs

Scaling Laws of RoPE-based Extrapolation

UniTabE: A Universal Pretraining Protocol for Tabular Foundation Model in Data Science

Rethinking Label Poisoning for GNNs: Pitfalls and Attacks

Efficient Score Matching with Deep Equilibrium Layers

Jointly-Learned Exit and Inference for a Dynamic Neural Network

Private Zeroth-Order Nonsmooth Nonconvex Optimization

Can we get the best of both Binary Neural Networks and Spiking Neural Networks for Efficient Computer Vision?

Deep Neural Networks Tend To Extrapolate Predictably

On the Vulnerability of Adversarially Trained Models Against Two-faced Attacks

Scalable Language Model with Generalized Continual Learning

FedCDA: Federated Learning with Cross-rounds Divergence-aware Aggregation

WebArena: A Realistic Web Environment for Building Autonomous Agents

Fantastic Gains and Where to Find Them: On the Existence and Prospect of General Knowledge Transfer between Any Pretrained Model

Language Model Inversion

A Good Learner can Teach Better: Teacher-Student Collaborative Knowledge Distillation

Consistent Video-to-Video Transfer Using Synthetic Dataset

GraphChef: Decision-Tree Recipes to Explain Graph Neural Networks

Benign Oscillation of Stochastic Gradient Descent with Large Learning Rate

Towards Generative Abstract Reasoning: Completing Raven’s Progressive Matrix via Rule Abstraction and Selection

Adaptive deep spiking neural network with global-local learning via balanced excitatory and inhibitory mechanism

Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generation

Learning Hierarchical Image Segmentation For Recognition and By Recognition

Uncertainty-aware Constraint Inference in Inverse Constrained Reinforcement Learning

DIFFTACTILE: A Physics-based Differentiable Tactile Simulator for Contact-rich Robotic Manipulation

On the Role of Discrete Tokenization in Visual Representation Learning

In-Context Learning Dynamics with Random Binary Sequences

Influencer Backdoor Attack on Semantic Segmentation

NeurRev: Train Better Sparse Neural Network Practically via Neuron Revitalization

Low Rank Matrix Completion via Robust Alternating Minimization in Nearly Linear Time

Whittle Index with Multiple Actions and State Constraint for Inventory Management

ControlVideo: Training-free Controllable Text-to-video Generation

Jointly Training Large Autoregressive Multimodal Models

Time-Efficient Reinforcement Learning with Stochastic Stateful Policies

MiniLLM: Knowledge Distillation of Large Language Models

Learning Adaptive Multiresolution Transforms via Meta-Framelet-based Graph Convolutional Network

Multiscale Positive-Unlabeled Detection of AI-Generated Texts

Implicit Neural Representation Inference for Low-Dimensional Bayesian Deep Learning

When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method

The Effective Horizon Explains Deep RL Performance in Stochastic Environments

Interpreting CLIP's Image Representation via Text-Based Decomposition

Demystifying CLIP Data

Optimal Sample Complexity for Average Reward Markov Decision Processes

Space and time continuous physics simulation from partial observations

Learning 3D Particle-based Simulators from RGB-D Videos

Pessimistic Nonlinear Least-Squares Value Iteration for Offline Reinforcement Learning

The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry

EMO: EARTH MOVER DISTANCE OPTIMIZATION FOR AUTO-REGRESSIVE LANGUAGE MODELING

Adaptive Instrument Design for Indirect Experiments

Towards Foundation Models for Knowledge Graph Reasoning

Locality-Aware Graph Rewiring in GNNs

Curiosity-driven Red-teaming for Large Language Models

The Devil is in the Object Boundary: Towards Annotation-free Instance Segmentation using Foundation Models

Chameleon: Increasing Label-Only Membership Leakage with Adaptive Poisoning

LCOT: Linear Circular Optimal Transport

OPTIMAL ROBUST MEMORIZATION WITH RELU NEURAL NETWORKS

Stochastic Controlled Averaging for Federated Learning with Communication Compression

DORSal: Diffusion for Object-centric Representations of Scenes $\textit{et al.}$

REBAR: Retrieval-Based Reconstruction for Time-series Contrastive Learning

T-Rep: Representation Learning for Time Series using Time-Embeddings

Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training

Sharpness-Aware Minimization Enhances Feature Quality via Balanced Learning

Boosting Vanilla Lightweight Vision Transformers via Re-parameterization

Rethinking the Uniformity Metric in Self-Supervised Learning

Detecting Machine-Generated Texts by Multi-Population Aware Optimization for Maximum Mean Discrepancy

SEGNO: Generalizing Equivariant Graph Neural Networks with Physical Inductive Biases

Identifying Representations for Intervention Extrapolation

Fusion Is Not Enough: Single Modal Attacks on Fusion Models for 3D Object Detection

Generalization error of spectral algorithms

CrIBo: Self-Supervised Learning via Cross-Image Object-Level Bootstrapping

The Reasonableness Behind Unreasonable Translation Capability of Large Language Model

On Representation Complexity of Model-based and Model-free Reinforcement Learning

EX-Graph: A Pioneering Dataset Bridging Ethereum and X

Self-Supervised Heterogeneous Graph Learning: a Homophily and Heterogeneity View

Chain of Thought Empowers Transformers to Solve Inherently Serial Problems

Beating Price of Anarchy and Gradient Descent without Regret in Potential Games

Conformal Risk Control

Fair Classifiers that Abstain without Harm

Repelling Random Walks

Separating common from salient patterns with Contrastive Representation Learning

Instant3D: Fast Text-to-3D with Sparse-view Generation and Large Reconstruction Model

Learning the greatest common divisor: explaining transformer predictions

BroGNet: Momentum-Conserving Graph Neural Stochastic Differential Equation for Learning Brownian Dynamics

Diagnosing Transformers: Illuminating Feature Spaces for Clinical Decision-Making

Vision Transformers Need Registers

Efficient and Scalable Graph Generation through Iterative Local Expansion

PlaSma: Procedural Knowledge Models for Language-based Planning and Re-Planning

Lipsum-FT: Robust Fine-Tuning of Zero-Shot Models Using Random Text Guidance

Neural Spectral Methods: Self-supervised learning in the spectral domain

Zero-Shot Continuous Prompt Transfer: Generalizing Task Semantics Across Language Models

RETSim: Resilient and Efficient Text Similarity

MUFFIN: Curating Multi-Faceted Instructions for Improving Instruction Following

ConjNorm: Tractable Density Estimation for Out-of-Distribution Detection

Convolutional Deep Kernel Machines

Theoretical Analysis of Robust Overfitting for Wide DNNs: An NTK Approach

ReSimAD: Zero-Shot 3D Domain Transfer for Autonomous Driving with Source Reconstruction and Target Simulation

I-PHYRE: Interactive Physical Reasoning

Defining Expertise: Applications to Treatment Effect Estimation

A Variational Perspective on Solving Inverse Problems with Diffusion Models

Beyond IID weights: sparse and low-rank deep Neural Networks are also Gaussian Processes

Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks

Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chips

Network Memory Footprint Compression Through Jointly Learnable Codebooks and Mappings

MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning

Data Distillation Can Be Like Vodka: Distilling More Times For Better Quality

LipSim: A Provably Robust Perceptual Similarity Metric

SALMONN: Towards Generic Hearing Abilities for Large Language Models

Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF

Project and Probe: Sample-Efficient Adaptation by Interpolating Orthogonal Features

UNR-Explainer: Counterfactual Explanations for Unsupervised Node Representation Learning Models

On Accelerating Diffusion-Based Sampling Processes via Improved Integration Approximation

Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision

From Latent Graph to Latent Topology Inference: Differentiable Cell Complex Module

AutoLoRa: An Automated Robust Fine-Tuning Framework

Dropout Enhanced Bilevel Training

Predicting Emergent Abilities with Infinite Resolution Evaluation

LightHGNN: Distilling Hypergraph Neural Networks into MLPs for 100x Faster Inference

On Diffusion Modeling for Anomaly Detection

Efficient Modulation for Vision Networks

Finite-State Autoregressive Entropy Coding for Efficient Learned Lossless Compression

G$^2$N$^2$ : Weisfeiler and Lehman go grammatical

Time-Varying Propensity Score to Bridge the Gap between the Past and Present

Discovering modular solutions that generalize compositionally

Be More Active! Understanding the Differences Between Mean and Sampled Representations of Variational Autoencoders

Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time Steps

Meta Inverse Constrained Reinforcement Learning: Convergence Guarantee and Generalization Analysis

Masked Structural Growth for 2x Faster Language Model Pre-training

On the Generalization and Approximation Capacities of Neural Controlled Differential Equations

Robust Angular Synchronization via Directed Graph Neural Networks

Maximum Entropy Model Correction in Reinforcement Learning

Improving protein optimization with smoothed fitness landscapes

Sample-Efficient Learning of POMDPs with Multiple Observations In Hindsight

Quantifying the Plausibility of Context Reliance in Neural Machine Translation

BrainSCUBA: Fine-Grained Natural Language Captions of Visual Cortex Selectivity

Enabling Efficient Equivariant Operations in the Fourier Basis via Gaunt Tensor Products

Views Can Be Deceiving: Improved SSL Through Feature Space Augmentation

Flat Minima in Linear Estimation and an Extended Gauss Markov Theorem

Sample-Efficient Multi-Agent RL: An Optimization Perspective

Multimodal Molecular Pretraining via Modality Blending

Online Information Acquisition: Hiring Multiple Agents

RAIN: Your Language Models Can Align Themselves without Finetuning

Lie Group Decompositions for Equivariant Neural Networks

Masks, Signs, And Learning Rate Rewinding

Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation

Random Sparse Lifts: Construction, Analysis and Convergence of finite sparse networks

TabR: Tabular Deep Learning Meets Nearest Neighbors

Conformal Prediction via Regression-as-Classification

The Human-AI Substitution game: active learning from a strategic labeler

Probabilistic Self-supervised Representation Learning via Scoring Rules Minimization

Classification with Conceptual Safeguards

$\mathbb{D}^2$ Pruning: Message Passing for Balancing Diversity & Difficulty in Data Pruning

Scaling physics-informed hard constraints with mixture-of-experts

On Stationary Point Convergence of PPO-Clip

How to Capture Higher-order Correlations? Generalizing Matrix Softmax Attention to Kronecker Computation

General Graph Random Features

Are Models Biased on Text without Gender-related Language?

Uni3D: Exploring Unified 3D Representation at Scale

Privacy-Preserving In-Context Learning for Large Language Models

A Discretization Framework for Robust Contextual Stochastic Optimization

Chain of Log-Concave Markov Chains

A Quadratic Synchronization Rule for Distributed Deep Learning

Perceptual Scales Predicted by Fisher Information Metrics

Protein Discovery with Discrete Walk-Jump Sampling

Fast and unified path gradient estimators for normalizing flows

Out-of-Variable Generalisation for Discriminative Models

A Simple and Scalable Representation for Graph Generation

Listen, Think, and Understand

FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning

TokenFlow: Consistent Diffusion Features for Consistent Video Editing

Language-Informed Visual Concept Learning

Turning large language models into cognitive models

Neural Snowflakes: Universal Latent Graph Inference via Trainable Latent Geometries

Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts

Unveiling Options with Neural Network Decomposition

Towards the Fundamental Limits of Knowledge Transfer over Finite Domains

Active Test-Time Adaptation: Theoretical Analyses and An Algorithm

Quantifying and Enhancing Multi-modal Robustness with Modality Preference

RingAttention with Blockwise Transformers for Near-Infinite Context

A Statistical Analysis of Wasserstein Autoencoders for Intrinsically Low-dimensional Data

Improved Techniques for Training Consistency Models

Modeling Boundedly Rational Agents with Latent Inference Budgets

HYPO: Hyperspherical Out-Of-Distribution Generalization

On the Foundations of Shortcut Learning

Emergent Communication with Conversational Repair

SmartPlay : A Benchmark for LLMs as Intelligent Agents

A General Framework for User-Guided Bayesian Optimization

InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior

HIFA: High-fidelity Text-to-3D Generation with Advanced Diffusion Guidance

Understanding Domain Generalization: A Noise Robustness Perspective

Can Transformers Capture Spatial Relations between Objects?

The LLM Surgeon

Causal-StoNet: Causal Inference for High-Dimensional Complex Data

Equivariant Scalar Fields for Molecular Docking with Fast Fourier Transforms

Belief-Enriched Pessimistic Q-Learning against Adversarial State Perturbations

Diffusion-TS: Interpretable Diffusion for General Time Series Generation

Why is SAM Robust to Label Noise?

An Efficient Tester-Learner for Halfspaces

Batch normalization is sufficient for universal function approximation in CNNs

Neural structure learning with stochastic differential equations

Predictive, scalable and interpretable knowledge tracing on structured domains

Imitation Learning from Observation with Automatic Discount Scheduling

Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognition

ImageNet-OOD: Deciphering Modern Out-of-Distribution Detection Algorithms

Gen-Z: Generative Zero-Shot Text Classification with Contextualized Label Descriptions

GNNX-BENCH: Unravelling the Utility of Perturbation-based GNN Explainers through In-depth Benchmarking

A Benchmark Study on Calibration

BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks

Guaranteed Approximation Bounds for Mixed-Precision Neural Operators

Lifting Architectural Constraints of Injective Flows

Aux-NAS: Exploiting Auxiliary Labels with Negligibly Extra Inference Cost

Language Model Self-improvement by Reinforcement Learning Contemplation

Fast Updating Truncated SVD for Representation Learning with Sparse Matrices

SOInter: A Novel Deep Energy-Based Interpretation Method for Explaining Structured Output Models

Sparse Spiking Neural Network: Exploiting Heterogeneity in Timescales for Pruning Recurrent SNN

Rethinking Model Ensemble in Transfer-based Adversarial Attacks

Policy Rehearsing: Training Generalizable Policies for Reinforcement Learning

ModernTCN: A Modern Pure Convolution Structure for General Time Series Analysis

Prototypical Information Bottlenecking and Disentangling for Multimodal Cancer Survival Prediction

Attention-based Iterative Decomposition for Tensor Product Representation

On the Role of General Function Approximation in Offline Reinforcement Learning

Learning Delays in Spiking Neural Networks using Dilated Convolutions with Learnable Spacings

The Generative AI Paradox: “What It Can Create, It May Not Understand”

The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning

Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement

Evaluating Large Language Models at Evaluating Instruction Following

Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning

The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction

Learning Grounded Action Abstractions from Language

SpikePoint: An Efficient Point-based Spiking Neural Network for Event Cameras Action Recognition

OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models

Scaling Laws for Sparsely-Connected Foundation Models

From Sparse to Soft Mixtures of Experts

iGraphMix: Input Graph Mixup Method for Node Classification

Retrieval-Enhanced Contrastive Vision-Text Models

Raidar: geneRative AI Detection viA Rewriting

Function Vectors in Large Language Models

Ring-A-Bell! How Reliable are Concept Removal Methods For Diffusion Models?

Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking

Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization

A Policy Gradient Method for Confounded POMDPs

MUSTARD: Mastering Uniform Synthesis of Theorem and Proof Data

LEGO-Prover: Neural Theorem Proving with Growing Libraries

THOUGHT PROPAGATION: AN ANALOGICAL APPROACH TO COMPLEX REASONING WITH LARGE LANGUAGE MODELS

GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher

On the Humanity of Conversational AI: Evaluating the Psychological Portrayal of LLMs

Accurate Retraining-free Pruning for Pretrained Encoder-based Language Models

INViTE: INterpret and Control Vision-Language Models with Text Explanations

Effective pruning of web-scale datasets based on complexity of concept clusters

Sin3DM: Learning a Diffusion Model from a Single 3D Textured Shape

Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignment

DiffEnc: Variational Diffusion with a Learned Encoder

GIM: Learning Generalizable Image Matcher From Internet Videos

DyVal: Dynamic Evaluation of Large Language Models for Reasoning Tasks

The Unreasonable Effectiveness of Linear Prediction as a Perceptual Metric

FFB: A Fair Fairness Benchmark for In-Processing Group Fairness Methods

SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer

Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languages

Learning to Relax: Setting Solver Parameters Across a Sequence of Linear System Instances

Self-supervised Pocket Pretraining via Protein Fragment-Surroundings Alignment

Solving Diffusion ODEs with Optimal Boundary Conditions for Better Image Super-Resolution

Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning

Rayleigh Quotient Graph Neural Networks for Graph-level Anomaly Detection

DQ-LoRe: Dual Queries with Low Rank Approximation Re-ranking for In-Context Learning

Large Language Models Are Not Robust Multiple Choice Selectors

MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework

In-context Autoencoder for Context Compression in a Large Language Model

GenCorres: Consistent Shape Matching via Coupled Implicit-Explicit Shape Generative Models

Hard-Constrained Deep Learning for Climate Downscaling

PB-LLM: Partially Binarized Large Language Models

Information Bottleneck Analysis of Deep Neural Networks via Lossy Compression

ZipIt! Merging Models from Different Tasks without Training

Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs

MIntRec2.0: A Large-scale Benchmark Dataset for Multimodal Intent Recognition and Out-of-scope Detection in Conversations

RLCD: Reinforcement Learning from Contrastive Distillation for LM Alignment

Localizing and Editing Knowledge In Text-to-Image Generative Models

Efficient Dynamics Modeling in Interactive Environments with Koopman Theory

Generative Learning for Financial Time Series with Irregular and Scale-Invariant Patterns

Linear attention is (maybe) all you need (to understand Transformer optimization)

Scalable Diffusion for Materials Generation

MG-TSD: Multi-Granularity Time Series Diffusion Models with Guided Learning Process

RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory Sketches

Differentiable Euler Characteristic Transforms for Shape Classification

Simplicial Representation Learning with Neural $k$-Forms

HAZARD Challenge: Embodied Decision Making in Dynamically Changing Environments

Efficient Multi-agent Reinforcement Learning by Planning

DSPy: Compiling Declarative Language Model Calls into State-of-the-Art Pipelines

On the Stability of Iterative Retraining of Generative Models on their own Data

A Study of Bayesian Neural Network Surrogates for Bayesian Optimization

Fine-Tuned Language Models Generate Stable Inorganic Materials as Text

BooookScore: A systematic exploration of book-length summarization in the era of LLMs

Prediction Error-based Classification for Class-Incremental Learning

Deep Geodesic Canonical Correlation Analysis for Covariance-Based Neuroimaging Data

Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness

The Need for Speed: Pruning Transformers with One Recipe

Adapting to Distribution Shift by Visual Domain Prompt Generation

ImplicitSLIM and How it Improves Embedding-based Collaborative Filtering