Skip to yearly menu bar
Skip to main content
Main Navigation
ICLR
Help/FAQ
Contact ICLR
Downloads
ICLR Blog
Code of Conduct
Privacy Policy
Create Profile
Journal To Conference Track
Diversity & Inclusion
Proceedings at OpenReview
Future Meetings
Press
Exhibitor Information
ICLR Twitter
About ICLR
My Stuff
Login
Select Year: (2024)
2024
2023
2022
2021
2020
2019
2018
2017
2016
2015
2014
2013
Getting Started
Schedule
Main Conference
Invited Talks
Awards
Papers
In-person Orals
Spotlight Posters
Workshops
Community
Socials
Town Hall
Affinity Events
Sponsors
Organizers
Help
Helpdesk
RocketChat Client
Website FAQ
Browse
mini
compact
topic
detail
Showing papers for
.
×
×
title
author
topic
session
shuffle
by
serendipity
bookmarked first
visited first
not visited first
bookmarked but not visited
Enable Javascript in your browser to see the papers page.
ResFields: Residual Neural Fields for Spatiotemporal Signals
DATS: Difficulty-Aware Task Sampler for Meta-Learning Physics-Informed Neural Networks
L2MAC: Large Language Model Automatic Computer for Extensive Code Generation
Variance Reduced Halpern Iteration for Finite-Sum Monotone Inclusions
Flow to Better: Offline Preference-based Reinforcement Learning via Preferred Trajectory Generation
Learning to Embed Time Series Patches Independently
VBH-GNN: Variational Bayesian Heterogeneous Graph Neural Networks for Cross-subject Emotion Recognition
Neural Rate Control for Learned Video Compression
LOQA: Learning with Opponent Q-Learning Awareness
PnP Inversion: Boosting Diffusion-based Editing with 3 Lines of Code
Bounding the Expected Robustness of Graph Neural Networks Subject to Node Feature Attacks
Point2SSM: Learning Morphological Variations of Anatomies from Point Clouds
Causal Fairness under Unobserved Confounding: A Neural Sensitivity Framework
Model Merging by Uncertainty-Based Gradient Matching
On Penalty Methods for Nonconvex Bilevel Optimization and First-Order Stochastic Approximation
InstructCV: Instruction-Tuned Text-to-Image Diffusion Models as Vision Generalists
Scaling Supervised Local Learning with Augmented Auxiliary Networks
BatteryML: An Open-source Platform for Machine Learning on Battery Degradation
PAC-FNO: Parallel-Structured All-Component Fourier Neural Operators for Recognizing Low-Quality Images
Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restoration
DENEVIL: TOWARDS DECIPHERING AND NAVIGATING THE ETHICAL VALUES OF LARGE LANGUAGE MODELS VIA INSTRUCTION LEARNING
Channel Vision Transformers: An Image Is Worth 1 x 16 x 16 Words
Robustifying State-space Models for Long Sequences via Approximate Diagonalization
RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
Scalable Monotonic Neural Networks
MagicDrive: Street View Generation with Diverse 3D Geometry Control
MetaCoCo: A New Few-Shot Classification Benchmark with Spurious Correlation
Generative Adversarial Equilibrium Solvers
Long-Term Typhoon Trajectory Prediction: A Physics-Conditioned Approach Without Reanalysis Data
Mitigating the Curse of Dimensionality for Certified Robustness via Dual Randomized Smoothing
Decoupled Marked Temporal Point Process using Neural Ordinary Differential Equations
FedImpro: Measuring and Improving Client Update in Federated Learning
Improving LoRA in Privacy-preserving Federated Learning
Solving Diffusion ODEs with Optimal Boundary Conditions for Better Image Super-Resolution
Breaking Physical and Linguistic Borders: Multilingual Federated Prompt Tuning for Low-Resource Languages
PB-LLM: Partially Binarized Large Language Models
Correlated Noise Provably Beats Independent Noise for Differentially Private Learning
Efficient Inverse Multiagent Learning
Confidence-aware Reward Optimization for Fine-tuning Text-to-Image Models
Large Language Models as Optimizers
Neural Neighborhood Search for Multi-agent Path Finding
Simple Hierarchical Planning with Diffusion
Accelerating Distributed Stochastic Optimization via Self-Repellent Random Walks
LogicMP: A Neuro-symbolic Approach for Encoding First-order Logic Constraints
Nemesis: Normalizing the Soft-prompt Vectors of Vision-Language Models
Language-Interfaced Tabular Oversampling via Progressive Imputation and Self-Authentication
Sparse MoE with Language Guided Routing for Multilingual Machine Translation
DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior
Neural Common Neighbor with Completion for Link Prediction
Geometry-Aware Projective Mapping for Unbounded Neural Radiance Fields
Distinguished In Uniform: Self-Attention Vs. Virtual Nodes
On Trajectory Augmentations for Off-Policy Evaluation
Plugin estimators for selective classification with out-of-distribution detection
DMBP: Diffusion model-based predictor for robust offline reinforcement learning against state observation perturbations
SOInter: A Novel Deep Energy-Based Interpretation Method for Explaining Structured Output Models
Adaptive Stochastic Gradient Algorithm for Black-box Multi-Objective Learning
Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning
Intriguing Properties of Data Attribution on Diffusion Models
SpaCE: The Spatial Confounding Environment
On the hardness of learning under symmetries
Large Language Models Are Not Robust Multiple Choice Selectors
Lemur: Integrating Large Language Models in Automated Program Verification
AdjointDPM: Adjoint Sensitivity Method for Gradient Backpropagation of Diffusion Probabilistic Models
MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Images
Retrieval meets Long Context Large Language Models
How do Language Models Bind Entities in Context?
Finite-Time Analysis of On-Policy Heterogeneous Federated Reinforcement Learning
Semantic Flow: Learning Semantic Fields of Dynamic Scenes from Monocular Videos
LLCP: Learning Latent Causal Processes for Reasoning-based Video Question Answer
Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors
Mastering Symbolic Operations: Augmenting Language Models with Compiled Neural Networks
Time Fairness in Online Knapsack Problems
AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation
A Data-Driven Measure of Relative Uncertainty for Misclassification Detection
Symbol as Points: Panoptic Symbol Spotting via Point-based Representation
Retrieval-Guided Reinforcement Learning for Boolean Circuit Minimization
One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention
DiffEnc: Variational Diffusion with a Learned Encoder
Exploring Weight Balancing on Long-Tailed Recognition Problem
Generative Learning for Financial Time Series with Irregular and Scale-Invariant Patterns
Combining Axes Preconditioners through Kronecker Approximation for Deep Learning
SpikePoint: An Efficient Point-based Spiking Neural Network for Event Cameras Action Recognition
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
Online Continual Learning for Interactive Instruction Following Agents
Nearly $d$-Linear Convergence Bounds for Diffusion Models via Stochastic Localization
SLiMe: Segment Like Me
RetroBridge: Modeling Retrosynthesis with Markov Bridges
Active Retrosynthetic Planning Aware of Route Quality
FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets
CO2: Efficient Distributed Training with Full Communication-Computation Overlap
Continuous Invariance Learning
Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy
Learning to solve Class-Constrained Bin Packing Problems via Encoder-Decoder Model
Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Models
CARD: Channel Aligned Robust Blend Transformer for Time Series Forecasting
Are Bert Family Good Instruction Followers? A Study on Their Potential And Limitations
Dynamic Discounted Counterfactual Regret Minimization
Synergistic Patch Pruning for Vision Transformer: Unifying Intra- & Inter-Layer Patch Importance
Sliced Wasserstein Estimation with Control Variates
DEEP NEURAL NETWORK INITIALIZATION WITH SPARSITY INDUCING ACTIVATIONS
Test-Time Training on Nearest Neighbors for Large Language Models
Early Stopping Against Label Noise Without Validation Data
INViTE: INterpret and Control Vision-Language Models with Text Explanations
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
Can Large Language Models Infer Causation from Correlation?
TEDDY: Trimming Edges with Degree-based Discrimination Strategy
Energy-based Automated Model Evaluation
Online Stabilization of Spiking Neural Networks
A Unified Experiment Design Approach for Cyclic and Acyclic Causal Models
FreeDyG: Frequency Enhanced Continuous-Time Dynamic Graph Model for Link Prediction
Weatherproofing Retrieval for Localization with Generative AI and Geometric Consistency
Provably Robust Conformal Prediction with Improved Efficiency
Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs
Structural Inference with Dynamics Encoding and Partial Correlation Coefficients
Physics-Regulated Deep Reinforcement Learning: Invariant Embeddings
SEAL: A Framework for Systematic Evaluation of Real-World Super-Resolution
Learning Delays in Spiking Neural Networks using Dilated Convolutions with Learnable Spacings
Unraveling the Enigma of Double Descent: An In-depth Analysis through the Lens of Learned Feature Space
Towards Robust and Efficient Cloud-Edge Elastic Model Adaptation via Selective Entropy Distillation
Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness
Neural structure learning with stochastic differential equations
Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis
Going Beyond Neural Network Feature Similarity: The Network Feature Complexity and Its Interpretation Using Category Theory
CoLiDE: Concomitant Linear DAG Estimation
Beyond task performance: evaluating and reducing the flaws of large multimodal models with in-context-learning
Tackling the Data Heterogeneity in Asynchronous Federated Learning with Cached Update Calibration
The Trickle-down Impact of Reward Inconsistency on RLHF
SliceGPT: Compress Large Language Models by Deleting Rows and Columns
Weakly-supervised Audio Separation via Bi-modal Semantic Similarity
Neurosymbolic Grounding for Compositional World Models
Xformer: Hybrid X-Shaped Transformer for Image Denoising
Memorization Capacity of Multi-Head Attention in Transformers
Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space
Domain-Inspired Sharpness-Aware Minimization Under Domain Shifts
Mean Field Theory in Deep Metric Learning
Bounding Box Stability against Feature Dropout Reflects Detector Generalization across Environments
Towards Principled Representation Learning from Videos for Reinforcement Learning
Privately Aligning Language Models with Reinforcement Learning
Learning Planning Abstractions from Language
Towards Characterizing Domain Counterfactuals for Invertible Latent Causal Models
Dictionary Contrastive Learning for Efficient Local Supervision without Auxiliary Networks
BTR: Binary Token Representations for Efficient Retrieval Augmented Language Models
An interpretable error correction method for enhancing code-to-code translation
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
Maximum Likelihood Estimation is All You Need for Well-Specified Covariate Shift
Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization
A Sublinear Adversarial Training Algorithm
Benign Overfitting and Grokking in ReLU Networks for XOR Cluster Data
Mixture of LoRA Experts
Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images
Neural Optimal Transport with General Cost Functionals
GOAt: Explaining Graph Neural Networks via Graph Output Attribution
Neuron Activation Coverage: Rethinking Out-of-distribution Detection and Generalization
Multimodal Learning Without Labeled Multimodal Data: Guarantees and Applications
ODICE: Revealing the Mystery of Distribution Correction Estimation via Orthogonal-gradient Update
RA-DIT: Retrieval-Augmented Dual Instruction Tuning
Enhancing Transferable Adversarial Attacks on Vision Transformers through Gradient Normalization Scaling and High-Frequency Adaptation
Tensor Programs VI: Feature Learning in Infinite Depth Neural Networks
An Unforgeable Publicly Verifiable Watermark for Large Language Models
Out-Of-Domain Unlabeled Data Improves Generalization
CoRe-GD: A Hierarchical Framework for Scalable Graph Visualization with GNNs
Class Probability Matching with Calibrated Networks for Label Shift Adaption
Improved Regret Bounds for Non-Convex Online-Within-Online Meta Learning
Spatio-Temporal Few-Shot Learning via Diffusive Neural Network Generation
Adaptive Self-training Framework for Fine-grained Scene Graph Generation
Fine-tuning Multimodal LLMs to Follow Zero-shot Demonstrative Instructions
InterpGNN: Understand and Improve Generalization Ability of Transdutive GNNs through the Lens of Interplay between Train and Test Nodes
WildChat: 1M ChatGPT Interaction Logs in the Wild
WOODS: Benchmarks for Out-of-Distribution Generalization in Time Series
Context is Environment
Memory-Assisted Sub-Prototype Mining for Universal Domain Adaptation
SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore
AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?
Bespoke Solvers for Generative Flow Models
Clifford Group Equivariant Simplicial Message Passing Networks
Multi-Source Diffusion Models for Simultaneous Music Generation and Separation
Consistent Video-to-Video Transfer Using Synthetic Dataset
Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources
Uncertainty-aware Constraint Inference in Inverse Constrained Reinforcement Learning
Enhancing Human-AI Collaboration Through Logic-Guided Reasoning
What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning
OWL: A Large Language Model for IT Operations
What Matters to You? Towards Visual Representation Alignment for Robot Learning
Geometrically Aligned Transfer Encoder for Inductive Transfer in Regression Tasks
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
DyVal: Dynamic Evaluation of Large Language Models for Reasoning Tasks
Neural Architecture Retrieval
Empirical Analysis of Model Selection for Heterogeneous Causal Effect Estimation
Provable Reward-Agnostic Preference-Based Reinforcement Learning
Inherently Interpretable Time Series Classification via Multiple Instance Learning
A Restoration Network as an Implicit Prior
ADOPD: A Large-Scale Document Page Decomposition Dataset
Statistically Optimal $K$-means Clustering via Nonnegative Low-rank Semidefinite Programming
Compressing LLMs: The Truth is Rarely Pure and Never Simple
Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs
Faithful Vision-Language Interpretation via Concept Bottleneck Models
Extending Power of Nature from Binary to Real-Valued Graph Learning in Real World
Robust Adversarial Reinforcement Learning via Bounded Rationality Curricula
Seer: Language Instructed Video Prediction with Latent Diffusion Models
Near-Optimal Quantum Algorithm for Minimizing the Maximal Loss
Backdoor Contrastive Learning via Bi-level Trigger Optimization
Closing the Gap between TD Learning and Supervised Learning - A Generalisation Point of View.
ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search
Searching for High-Value Molecules Using Reinforcement Learning and Transformers
Large Language Models as Tool Makers
On the Sample Complexity of Lipschitz Constant Estimation
LayoutNUWA: Revealing the Hidden Layout Expertise of Large Language Models
Learning Mean Field Games on Sparse Graphs: A Hybrid Graphex Approach
Rethinking the Benefits of Steerable Features in 3D Equivariant Graph Neural Networks
SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores
P2Seg: Pointly-supervised Segmentation via Mutual Distillation
Grounding Multimodal Large Language Models to the World
Adversarial Causal Bayesian Optimization
Lifting Architectural Constraints of Injective Flows
Learning Performance-Improving Code Edits
Contrastive Preference Learning: Learning from Human Feedback without Reinforcement Learning
$\alpha$TC-VAE: On the relationship between Disentanglement and Diversity
Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression
Adaptive Window Pruning for Efficient Local Motion Deblurring
Label-free Node Classification on Graphs with Large Language Models (LLMs)
A Progressive Training Framework for Spiking Neural Networks with Learnable Multi-hierarchical Model
Yet Another ICU Benchmark: A Flexible Multi-Center Framework for Clinical ML
LLM-grounded Video Diffusion Models
Annealing Self-Distillation Rectification Improves Adversarial Training
Critical Learning Periods Emerge Even in Deep Linear Networks
Generative Human Motion Stylization in Latent Space
Procedural Fairness Through Decoupling Objectionable Data Generating Components
Learning model uncertainty as variance-minimizing instance weights
Decision ConvFormer: Local Filtering in MetaFormer is Sufficient for Decision Making
Exploring the Promise and Limits of Real-Time Recurrent Learning
Diffusion Model for Dense Matching
One-hot Generalized Linear Model for Switching Brain State Discovery
Large Language Models as Analogical Reasoners
The importance of feature preprocessing for differentially private linear optimization
InstructPix2NeRF: Instructed 3D Portrait Editing from a Single Image
Mind Your Augmentation: The Key to Decoupling Dense Self-Supervised Learning
General Stability Analysis for Zeroth-Order Optimization Algorithms
EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models
PubDef: Defending Against Transfer Attacks From Public Models
Boundary Denoising for Video Activity Localization
Neur2RO: Neural Two-Stage Robust Optimization
A Primal-Dual Approach to Solving Variational Inequalities with General Constraints
Learning to Make Adherence-aware Advice
RLIF: Interactive Imitation Learning as Reinforcement Learning
Alt-Text with Context: Improving Accessibility for Images on Twitter
Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedback
Ghost on the Shell: An Expressive Representation of General 3D Shapes
Less is More: One-shot Subgraph Reasoning on Large-scale Knowledge Graphs
Deep Geodesic Canonical Correlation Analysis for Covariance-Based Neuroimaging Data
Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priors
Learning Energy Decompositions for Partial Inference in GFlowNets
Tractable Probabilistic Graph Representation Learning with Graph-Induced Sum-Product Networks
Convergence of Bayesian Bilevel Optimization
Rotation Has Two Sides: Evaluating Data Augmentation for Deep One-class Classification
Probabilistically Rewired Message-Passing Neural Networks
PILOT: An $\mathcal{O}(1/K)$-Convergent Approach for Policy Evaluation with Nonlinear Function Approximation
MaGIC: Multi-modality Guided Image Completion
Risk Bounds of Accelerated SGD for Overparameterized Linear Regression
DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Models
Improving equilibrium propagation without weight symmetry through Jacobian homeostasis
Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph
Image Inpainting via Tractable Steering of Diffusion Models
Tight Rates in Supervised Outlier Transfer Learning
SGD Finds then Tunes Features in Two-Layer Neural Networks with near-Optimal Sample Complexity: A Case Study in the XOR problem
Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs
Consistency Training with Learnable Data Augmentation for Graph Anomaly Detection with Limited Supervision
Improving Offline RL by Blending Heuristics
Delta-AI: Local objectives for amortized inference in sparse graphical models
ZipIt! Merging Models from Different Tasks without Training
Analysis of Learning a Flow-based Generative Model from Limited Sample Complexity
Learning Over Molecular Conformer Ensembles: Datasets and Benchmarks
Scaling Laws of RoPE-based Extrapolation
Reconciling Spatial and Temporal Abstractions for Goal Representation
Efficient Score Matching with Deep Equilibrium Layers
Talk like a Graph: Encoding Graphs for Large Language Models
Improved Active Learning via Dependent Leverage Score Sampling
Provable Memory Efficient Self-Play Algorithm for Model-free Reinforcement Learning
DiffusionSat: A Generative Foundation Model for Satellite Imagery
Behaviour Distillation
EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision
Implicit regularization of deep residual networks towards neural ODEs
Beyond Imitation: Leveraging Fine-grained Quality Signals for Alignment
Diffusion Sampling with Momentum for Mitigating Divergence Artifacts
PINNACLE: PINN Adaptive ColLocation and Experimental points selection
DreamSmooth: Improving Model-based Reinforcement Learning via Reward Smoothing
Class Incremental Learning via Likelihood Ratio Based Task Prediction
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.
AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning
Privileged Sensing Scaffolds Reinforcement Learning
AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors
Cascading Reinforcement Learning
Gaining Wisdom from Setbacks: Aligning Large Language Models via Mistake Analysis
Pre-training with Random Orthogonal Projection Image Modeling
How Well Do Supervised 3D Models Transfer to Medical Imaging Tasks?
Single Motion Diffusion
MEND: Meta Demonstration Distillation for Efficient and Effective In-Context Learning
Out-of-Distribution Detection by Leveraging Between-Layer Transformation Smoothness
Coeditor: Leveraging Repo-level Diffs for Code Auto-editing
BooookScore: A systematic exploration of book-length summarization in the era of LLMs
Only Pay for What Is Uncertain: Variance-Adaptive Thompson Sampling
The Consensus Game: Language Model Generation via Equilibrium Search
Graph-based Virtual Sensing from Sparse and Partial Multivariate Observations
Scalable Neural Network Kernels
Knowledge Fusion of Large Language Models
GeoDiffusion: Text-Prompted Geometric Control for Object Detection Data Generation
Mayfly: a Neural Data Structure for Graph Stream Summarization
OpenChat: Advancing Open-source Language Models with Mixed-Quality Data
FedCompass: Efficient Cross-Silo Federated Learning on Heterogeneous Client Devices Using a Computing Power-Aware Scheduler
Bridging State and History Representations: Understanding Self-Predictive RL
Bandits with Replenishable Knapsacks: the Best of both Worlds
ARGS: Alignment as Reward-Guided Search
Towards a statistical theory of data selection under weak supervision
Generalization in diffusion models arises from geometry-adaptive harmonic representations
KW-Design: Pushing the Limit of Protein Design via Knowledge Refinement
Respect the model: Fine-grained and Robust Explanation with Sharing Ratio Decomposition
A Stable, Fast, and Fully Automatic Learning Algorithm for Predictive Coding Networks
Causality-Inspired Spatial-Temporal Explanations for Dynamic Graph Neural Networks
Bongard-OpenWorld: Few-Shot Reasoning for Free-form Visual Concepts in the Real World
Non-Exchangeable Conformal Risk Control
Energy-guided Entropic Neural Optimal Transport
Rethinking Information-theoretic Generalization: Loss Entropy Induced PAC Bounds
Balancing Act: Constraining Disparate Impact in Sparse Models
Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers
On the Limitations of Temperature Scaling for Distributions with Overlaps
Compositional Generative Inverse Design
SpeechTokenizer: Unified Speech Tokenizer for Speech Language Models
Submodular Reinforcement Learning
Navigating the Design Space of Equivariant Diffusion-Based Generative Models for De Novo 3D Molecule Generation
Generative Learning for Solving Non-Convex Problem with Multi-Valued Input-Solution Mapping
Manipulating dropout reveals an optimal balance of efficiency and robustness in biological and machine visual systems
Hyper Evidential Deep Learning to Quantify Composite Classification Uncertainty
LUM-ViT: Learnable Under-sampling Mask Vision Transformer for Bandwidth Limited Optical Signal Acquisition
Accelerated Sampling with Stacked Restricted Boltzmann Machines
Logical Languages Accepted by Transformer Encoders with Hard Attention
NfgTransformer: Equivariant Representation Learning for Normal-form Games
CellPLM: Pre-training of Cell Language Model Beyond Single Cells
Prompt Learning with Quaternion Networks
Enhancing Tail Performance in Extreme Classifiers by Label Variance Reduction
How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions
EventRPG: Event Data Augmentation with Relevance Propagation Guidance
The Alignment Problem from a Deep Learning Perspective
Implicit Maximum a Posteriori Filtering via Adaptive Optimization
ContextRef: Evaluating Referenceless Metrics for Image Description Generation
MAPE-PPI: Towards Effective and Efficient Protein-Protein Interaction Prediction via Microenvironment-Aware Protein Embedding
Sufficient conditions for offline reactivation in recurrent neural networks
Magnushammer: A Transformer-Based Approach to Premise Selection
Bayesian Optimization through Gaussian Cox Process Models for Spatio-temporal Data
Kernel Metric Learning for In-Sample Off-Policy Evaluation of Deterministic RL Policies
Error Feedback Reloaded: From Quadratic to Arithmetic Mean of Smoothness Constants
Stabilizing Backpropagation Through Time to Learn Complex Physics
Fixed Non-negative Orthogonal Classifier: Inducing Zero-mean Neural Collapse with Feature Dimension Separation
Doubly Robust Proximal Causal Learning for Continuous Treatments
SaNN: Simple Yet Powerful Simplicial-aware Neural Networks
Memorization in Self-Supervised Learning Improves Downstream Generalization
Bounds on Representation-Induced Confounding Bias for Treatment Effect Estimation
Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion
Polynomial Width is Sufficient for Set Representation with High-dimensional Features
Interpretable Meta-Learning of Physical Systems
Evaluating Language Model Agency Through Negotiations
A Neural Framework for Generalized Causal Sensitivity Analysis
Most discriminative stimuli for functional cell type clustering
Fast, Expressive $\mathrm{SE}(n)$ Equivariant Networks through Weight-Sharing in Position-Orientation Space
A Dynamical View of the Question of Why
SPTNet: An Efficient Alternative Framework for Generalized Category Discovery with Spatial Prompt Tuning
On Double Descent in Reinforcement Learning with LSTD and Random Features
Large Language Models are Efficient Learners of Noise-Robust Speech Recognition
Federated Causal Discovery from Heterogeneous Data
Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning
FedDA: Faster Adaptive Gradient Methods for Federated Constrained Optimization
Treatment Effects Estimation By Uniform Transformer
It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition
How I Warped Your Noise: a Temporally-Correlated Noise Prior for Diffusion Models
Group Preference Optimization: Few-Shot Alignment of Large Language Models
The False Promise of Imitating Proprietary Language Models
Proximal Policy Gradient Arborescence for Quality Diversity Reinforcement Learning
Conditional Instrumental Variable Regression with Representation Learning for Causal Inference
Prompt Risk Control: A Rigorous Framework for Responsible Deployment of Large Language Models
Independent-Set Design of Experiments for Estimating Treatment and Spillover Effects under Network Interference
Get What You Want, Not What You Don't: Image Content Suppression for Text-to-Image Diffusion Models
FedInverse: Evaluating Privacy Leakage in Federated Learning
Elucidating the design space of classifier-guided diffusion generation
Imitation Learning from Observation with Automatic Discount Scheduling
Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasets
Reinforcement Symbolic Regression Machine
Less or More From Teacher: Exploiting Trilateral Geometry For Knowledge Distillation
ReMasker: Imputing Tabular Data with Masked Autoencoding
Quasi-Monte Carlo for 3D Sliced Wasserstein
Sparse Weight Averaging with Multiple Particles for Iterative Magnitude Pruning
Learning Decentralized Partially Observable Mean Field Control for Artificial Collective Behavior
COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL
DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization
Neuron-Enhanced AutoEncoder Matrix Completion and Collaborative Filtering: Theory and Practice
Efficient ConvBN Blocks for Transfer Learning and Beyond
Hybrid Internal Model: Learning Agile Legged Locomotion with Simulated Robot Response
Improved baselines for vision-language pre-training
Learning Flexible Body Collision Dynamics with Hierarchical Contact Mesh Transformer
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
Learning to Compose: Improving Object Centric Learning by Injecting Compositionality
True Knowledge Comes from Practice: Aligning Large Language Models with Embodied Environments via Reinforcement Learning
Transferring Learning Trajectories of Neural Networks
METRA: Scalable Unsupervised RL with Metric-Aware Abstraction
Unconstrained Stochastic CCA: Unifying Multiview and Self-Supervised Learning
Scalable and Effective Implicit Graph Neural Networks on Large Graphs
Rethinking Branching on Exact Combinatorial Optimization Solver: The First Deep Symbolic Discovery Framework
Learning Semantic Proxies from Visual Prompts for Parameter-Efficient Fine-Tuning in Deep Metric Learning
Lewis's Signaling Game as beta-VAE For Natural Word Lengths and Segments
R-MAE: Regions Meet Masked Autoencoders
Label-Focused Inductive Bias over Latent Object Features in Visual Classification
Dual-Encoders for Extreme Multi-label Classification
DynaVol: Unsupervised Learning for Dynamic Scenes through Object-Centric Voxelization
Bridging Neural and Symbolic Representations with Transitional Dictionary Learning
Consistency-guided Prompt Learning for Vision-Language Models
Amortized Network Intervention to Steer the Excitatory Point Processes
In defense of parameter sharing for model-compression
Generalized Neural Sorting Networks with Error-Free Differentiable Swap Functions
On the Stability of Expressive Positional Encodings for Graphs
OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models
Fast-ELECTRA for Efficient Pre-training
Dynamic Layer Tying for Parameter-Efficient Transformers
Transformers can optimally learn regression mixture models
CivRealm: A Learning and Reasoning Odyssey in Civilization for Decision-Making Agents
Learning from Label Proportions: Bootstrapping Supervised Learners via Belief Propagation
Masked Audio Generation using a Single Non-Autoregressive Transformer
Learning Multi-Faceted Prototypical User Interests
lpNTK: Better Generalisation with Less Data via Sample Interaction During Learning
BENO: Boundary-embedded Neural Operators for Elliptic PDEs
State Representation Learning Using an Unbalanced Atlas
VONet: Unsupervised Video Object Learning With Parallel U-Net Attention and Object-wise Sequential VAE
Selective Mixup Fine-Tuning for Optimizing Non-Decomposable Objectives
Relay Diffusion: Unifying diffusion process across resolutions for image synthesis
SparseFormer: Sparse Visual Recognition via Limited Latent Tokens
Efficient local linearity regularization to overcome catastrophic overfitting
CODE REPRESENTATION LEARNING AT SCALE
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
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
Learning with a Mole: Transferable latent spatial representations for navigation without reconstruction
Weaker MVI Condition: Extragradient Methods with Multi-Step Exploration
Grokking in Linear Estimators -- A Solvable Model that Groks without Understanding
InfoCon: Concept Discovery with Generative and Discriminative Informativeness
Efficient Heterogeneous Meta-Learning via Channel Shuffling Modulation
Neural Fine-Tuning Search for Few-Shot Learning
Tag2Text: Guiding Vision-Language Model via Image Tagging
Masked Autoencoders with Multi-Window Local-Global Attention Are Better Audio Learners
Meta Continual Learning Revisited: Implicitly Enhancing Online Hessian Approximation via Variance Reduction
Multi-task Learning with 3D-Aware Regularization
MixSATGEN: Learning Graph Mixing for SAT Instance Generation
Pareto Deep Long-Tailed Recognition: A Conflict-Averse Solution
Learning Personalized Causally Invariant Representations for Heterogeneous Federated Clients
Gradual Domain Adaptation via Gradient Flow
Layer-wise linear mode connectivity
The Joint Effect of Task Similarity and Overparameterization on Catastrophic Forgetting — An Analytical Model
Guiding Masked Representation Learning to Capture Spatio-Temporal Relationship of Electrocardiogram
Learning in reverse causal strategic environments with ramifications on two sided markets
CLAP: Collaborative Adaptation for Patchwork Learning
Whole-Song Hierarchical Generation of Symbolic Music Using Cascaded Diffusion Models
Social Reward: Evaluating and Enhancing Generative AI through Million-User Feedback from an Online Creative Community
Image Translation as Diffusion Visual Programmers
The Wasserstein Believer: Learning Belief Updates for Partially Observable Environments through Reliable Latent Space Models
A Policy Gradient Method for Confounded POMDPs
ImplicitSLIM and How it Improves Embedding-based Collaborative Filtering
Local Graph Clustering with Noisy Labels
DP-SGD Without Clipping: The Lipschitz Neural Network Way
Invariance-based Learning of Latent Dynamics
GRANDE: Gradient-Based Decision Tree Ensembles for Tabular Data
Differentially Private Synthetic Data via Foundation Model APIs 1: Images
On Differentially Private Federated Linear Contextual Bandits
Win-Win: Training High-Resolution Vision Transformers from Two Windows
ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate
Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation
Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning
Federated Wasserstein Distance
Bayesian Low-rank Adaptation for Large Language Models
Detecting, Explaining, and Mitigating Memorization in Diffusion Models
Causal Modelling Agents: Causal Graph Discovery through Synergising Metadata- and Data-driven Reasoning
Idempotent Generative Network
Attacking Perceptual Similarity Metrics
Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised Learning
Cauchy-Schwarz Divergence Information Bottleneck for Regression
Heterogeneous Personalized Federated Learning by Local-Global Updates Mixing via Convergence Rate
Plan-Seq-Learn: Language Model Guided RL for Solving Long Horizon Robotics Tasks
TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting
Continuous-Multiple Image Outpainting in One-Step via Positional Query and A Diffusion-based Approach
EQA-MX: Embodied Question Answering using Multimodal Expression
Proper Laplacian Representation Learning
Robust Classification via Regression for Learning with Noisy Labels
Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks
Does CLIP’s generalization performance mainly stem from high train-test similarity?
LEGO-Prover: Neural Theorem Proving with Growing Libraries
Flag Aggregator: Scalable Distributed Training under Failures and Augmented Losses using Convex Optimization
Backdoor Federated Learning by Poisoning Backdoor-Critical Layers
Interpreting Robustness Proofs of Deep Neural Networks
Incentive-Aware Federated Learning with Training-Time Model Rewards
Domain Randomization via Entropy Maximization
Conditional Variational Diffusion Models
NECO: NEural Collapse Based Out-of-distribution detection
S$2$AC: Energy-Based Reinforcement Learning with Stein Soft Actor Critic
Demystifying Local & Global Fairness Trade-offs in Federated Learning Using Partial Information Decomposition
An LLM can Fool Itself: A Prompt-Based Adversarial Attack
DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Text
Assessing Uncertainty in Similarity Scoring: Performance & Fairness in Face Recognition
Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement
KITAB: Evaluating LLMs on Constraint Satisfaction for Information Retrieval
ArchLock: Locking DNN Transferability at the Architecture Level with a Zero-Cost Binary Predictor
Outlier-Robust Subsampling Techniques for Persistent Homology
VertiBench: Advancing Feature Distribution Diversity in Vertical Federated Learning Benchmarks
Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition
Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression
Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs
Novel Quadratic Constraints for Extending LipSDP beyond Slope-Restricted Activations
DOS: Diverse Outlier Sampling for Out-of-Distribution Detection
Optimal transport based adversarial patch to leverage large scale attack transferability
AttEXplore: Attribution for Explanation with model parameters eXploration
Simplicial Representation Learning with Neural $k$-Forms
Towards Faithful Explanations: Boosting Rationalization with Shortcuts Discovery
VDC: Versatile Data Cleanser based on Visual-Linguistic Inconsistency by Multimodal Large Language Models
Guiding Instruction-based Image Editing via Multimodal Large Language Models
Provable Compositional Generalization for Object-Centric Learning
A Linear Algebraic Framework for Counterfactual Generation
DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models
Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation Patching
Energy-Based Concept Bottleneck Models: Unifying Prediction, Concept Intervention, and Probabilistic Interpretations
Defining and extracting generalizable interaction primitives from DNNs
Prediction without Preclusion: Recourse Verification with Reachable Sets
Minimax optimality of convolutional neural networks for infinite dimensional input-output problems and separation from kernel methods
Elastic Feature Consolidation For Cold Start Exemplar-Free Incremental Learning
Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals
Amortizing intractable inference in large language models
Debiasing Algorithm through Model Adaptation
Let's do the time-warp-attend: Learning topological invariants of dynamical systems
Piecewise Linear Parametrization of Policies: Towards Interpretable Deep Reinforcement Learning
TAB: Temporal Accumulated Batch Normalization in Spiking Neural Networks
Better Neural PDE Solvers Through Data-Free Mesh Movers
Conserve-Update-Revise to Cure Generalization and Robustness Trade-off in Adversarial Training
Faster Approximation of Probabilistic and Distributional Values via Least Squares
Faithful and Efficient Explanations for Neural Networks via Neural Tangent Kernel Surrogate Models
On Characterizing the Trade-off in Invariant Representation Learning
FairTune: Optimizing Parameter Efficient Fine Tuning for Fairness in Medical Image Analysis
Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature
Enhancing Group Fairness in Online Settings Using Oblique Decision Forests
Adapting and Evaluating Influence-Estimation Methods for Gradient-Boosted Decision Trees
SafeDreamer: Safe Reinforcement Learning with World Models
Neural Ordinary Differential Equations for Modeling Epidemic Spreading
Does Writing with Language Models Reduce Content Diversity?
FairerCLIP: Debiasing CLIP's Zero-Shot Predictions using Functions in RKHSs
Multi-resolution HuBERT: Multi-resolution Speech Self-Supervised Learning with Masked Unit Prediction
Decodable and Sample Invariant Continuous Object Encoder
Finetuning Text-to-Image Diffusion Models for Fairness
AmortizedPeriod: Attention-based Amortized Inference for Periodicity Identification
Unprocessing Seven Years of Algorithmic Fairness
Ring-A-Bell! How Reliable are Concept Removal Methods For Diffusion Models?
FairSeg: A Large-Scale Medical Image Segmentation Dataset for Fairness Learning Using Segment Anything Model with Fair Error-Bound Scaling
Neural Fourier Transform: A General Approach to Equivariant Representation Learning
Hybrid Sharing for Multi-Label Image Classification
On the Fairness ROAD: Robust Optimization for Adversarial Debiasing
Safe Collaborative Filtering
Adversarial Adaptive Sampling: Unify PINN and Optimal Transport for the Approximation of PDEs
SolidGen: An Autoregressive Model for Direct B-rep Synthesis
A Foundation Model for Error Correction Codes
STREAM: Spatio-TempoRal Evaluation and Analysis Metric for Video Generative Models
High Fidelity Neural Audio Compression
A Generalist Agent
Scalable Real-Time Recurrent Learning Using Columnar-Constructive Networks
Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis
Pre-training LiDAR-based 3D Object Detectors through Colorization
Designing Skill-Compatible AI: Methodologies and Frameworks in Chess
Mirage: Model-agnostic Graph Distillation for Graph Classification
Exploring the Common Appearance-Boundary Adaptation for Nighttime Optical Flow
InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modules
Graph Neural Networks for Learning Equivariant Representations of Neural Networks
Towards Optimal Regret in Adversarial Linear MDPs with Bandit Feedback
Bayesian Neural Controlled Differential Equations for Treatment Effect Estimation
Towards Establishing Guaranteed Error for Learned Database Operations
Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions
Towards Diverse Behaviors: A Benchmark for Imitation Learning with Human Demonstrations
Accelerated Convergence of Stochastic Heavy Ball Method under Anisotropic Gradient Noise
Local Search GFlowNets
PAC Prediction Sets Under Label Shift
Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization
Diving Segmentation Model into Pixels
Data-independent Module-aware Pruning for Hierarchical Vision Transformers
Set Learning for Accurate and Calibrated Models
Differentiable Euler Characteristic Transforms for Shape Classification
Addressing Loss of Plasticity and Catastrophic Forgetting in Continual Learning
An Analytical Solution to Gauss-Newton Loss for Direct Image Alignment
Neural Auto-designer for Enhanced Quantum Kernels
Making Pre-trained Language Models Great on Tabular Prediction
Leveraging Generative Models for Unsupervised Alignment of Neural Time Series Data
Video Language Planning
Enhancing Instance-Level Image Classification with Set-Level Labels
Adversarial AutoMixup
First-order ANIL provably learns representations despite overparametrisation
Dynamics-Informed Protein Design with Structure Conditioning
Stochastic Modified Equations and Dynamics of Dropout Algorithm
PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback
A Lie Group Approach to Riemannian Batch Normalization
Fast Updating Truncated SVD for Representation Learning with Sparse Matrices
WizardLM: Empowering Large Pre-Trained Language Models to Follow Complex Instructions
Task Planning for Visual Room Rearrangement under Partial Observability
Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning
LitCab: Lightweight Language Model Calibration over Short- and Long-form Responses
Massive Editing for Large Language Models via Meta Learning
Some Fundamental Aspects about Lipschitz Continuity of Neural Networks
Understanding Convergence and Generalization in Federated Learning through Feature Learning Theory
Building Cooperative Embodied Agents Modularly with Large Language Models
Implicit Gaussian process representation of vector fields over arbitrary latent manifolds
MVDream: Multi-view Diffusion for 3D Generation
Multisize Dataset Condensation
Customizable Combination of Parameter-Efficient Modules for Multi-Task Learning
Effective Structural Encodings via Local Curvature Profiles
Accurate Retraining-free Pruning for Pretrained Encoder-based Language Models
Improved algorithm and bounds for successive projection
A Benchmark Study on Calibration
Learning dynamic representations of the functional connectome in neurobiological networks
SparseDFF: Sparse-View Feature Distillation for One-Shot Dexterous Manipulation
RAPPER: Reinforced Rationale-Prompted Paradigm for Natural Language Explanation in Visual Question Answering
Online GNN Evaluation Under Test-time Graph Distribution Shifts
Particle Guidance: non-I.I.D. Diverse Sampling with Diffusion Models
Accelerating Sinkhorn algorithm with sparse Newton iterations
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
GENOME: Generative Neuro-Symbolic Visual Reasoning by Growing and Reusing Modules
Plug-and-Play: An Efficient Post-training Pruning Method for Large Language Models
P$^2$OT: Progressive Partial Optimal Transport for Deep Imbalanced Clustering
Open-ended VQA benchmarking of Vision-Language models by exploiting Classification datasets and their semantic hierarchy
Navigating Text-To-Image Customization: From LyCORIS Fine-Tuning to Model Evaluation
Unified Generative Modeling of 3D Molecules with Bayesian Flow Networks
Steve-Eye: Equipping LLM-based Embodied Agents with Visual Perception in Open Worlds
Learning to Jointly Understand Visual and Tactile Signals
$\infty$-Diff: Infinite Resolution Diffusion with Subsampled Mollified States
Improved statistical and computational complexity of the mean-field Langevin dynamics under structured data
Fusing Models with Complementary Expertise
OpenTab: Advancing Large Language Models as Open-domain Table Reasoners
Offline Data Enhanced On-Policy Policy Gradient with Provable Guarantees
Meta-Evolve: Continuous Robot Evolution for One-to-many Policy Transfer
Understanding Transferable Representation Learning and Zero-shot Transfer in CLIP
A path-norm toolkit for modern networks: consequences, promises and challenges
Horizon-Free Regret for Linear Markov Decision Processes
Variational Bayesian Last Layers
Querying Easily Flip-flopped Samples for Deep Active Learning
Deep Confident Steps to New Pockets: Strategies for Docking Generalization
Lipschitz Singularities in Diffusion Models
Training-free Multi-objective Diffusion Model for 3D Molecule Generation
An Agnostic View on the Cost of Overfitting in (Kernel) Ridge Regression
Multilinear Operator Networks
Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification
Decongestion by Representation: Learning to Improve Economic Welfare in Marketplaces
Generalized Policy Iteration using Tensor Approximation for Hybrid Control
Small-scale proxies for large-scale Transformer training instabilities
Blending Imitation and Reinforcement Learning for Robust Policy Improvement
UniTabE: A Universal Pretraining Protocol for Tabular Foundation Model in Data Science
DIAGNOSIS: Detecting Unauthorized Data Usages in Text-to-image Diffusion Models
A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models
New Insight of Variance reduce in Zero-Order Hard-Thresholding: Mitigating Gradient Error and Expansivity Contradictions
How Do Transformers Learn In-Context Beyond Simple Functions? A Case Study on Learning with Representations
Jointly-Learned Exit and Inference for a Dynamic Neural Network
C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersion
Enhancing Contrastive Learning for Ordinal Regression via Ordinal Content Preserved Data Augmentation
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
Rethinking the Power of Graph Canonization in Graph Representation Learning with Stability
FedCDA: Federated Learning with Cross-rounds Divergence-aware Aggregation
Leveraging Uncertainty Estimates To Improve Classifier Performance
Sampling Multimodal Distributions with the Vanilla Score: Benefits of Data-Based Initialization
WebArena: A Realistic Web Environment for Building Autonomous Agents
Probabilistic Adaptation of Black-Box Text-to-Video Models
Conformal Language Modeling
Language Model Inversion
Matryoshka Diffusion Models
Enhancing One-Shot Federated Learning Through Data and Ensemble Co-Boosting
ScaleCrafter: Tuning-free Higher-Resolution Visual Generation with Diffusion Models
Encoding Unitig-level Assembly Graphs with Heterophilous Constraints for Metagenomic Contigs Binning
YaRN: Efficient Context Window Extension of Large Language Models
Fantastic Gains and Where to Find Them: On the Existence and Prospect of General Knowledge Transfer between Any Pretrained Model
Benign Oscillation of Stochastic Gradient Descent with Large Learning Rate
Adaptive deep spiking neural network with global-local learning via balanced excitatory and inhibitory mechanism
Learning Grounded Action Abstractions from Language
Conversational Drug Editing Using Retrieval and Domain Feedback
On the Joint Interaction of Models, Data, and Features
DIFFTACTILE: A Physics-based Differentiable Tactile Simulator for Contact-rich Robotic Manipulation
Plug-and-Play Posterior Sampling under Mismatched Measurement and Prior Models
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
Pose Modulated Avatars from Video
Learning to Relax: Setting Solver Parameters Across a Sequence of Linear System Instances
Whittle Index with Multiple Actions and State Constraint for Inventory Management
Goodhart's Law in Reinforcement Learning
Jointly Training Large Autoregressive Multimodal Models
Time-Efficient Reinforcement Learning with Stochastic Stateful Policies
MiniLLM: Knowledge Distillation of Large Language Models
OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text
Stack Attention: Improving the Ability of Transformers to Model Hierarchical Patterns
ControlVideo: Training-free Controllable Text-to-video Generation
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
An Intuitive Multi-Frequency Feature Representation for SO(3)-Equivariant Networks
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
Beyond Vanilla Variational Autoencoders: Detecting Posterior Collapse in Conditional and Hierarchical Variational Autoencoders
ADDP: Learning General Representations for Image Recognition and Generation with Alternating Denoising Diffusion Process
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
Trajeglish: Traffic Modeling as Next-Token Prediction
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
Learning from Sparse Offline Datasets via Conservative Density Estimation
Llemma: An Open Language Model for Mathematics
Unveiling the Unseen: Identifiable Clusters in Trained Depthwise Convolutional Kernels
Towards Non-Asymptotic Convergence for Diffusion-Based Generative Models
Towards Foundation Models for Knowledge Graph Reasoning
Locality-Aware Graph Rewiring in GNNs
Rayleigh Quotient Graph Neural Networks for Graph-level Anomaly Detection
MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning
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
Language Model Decoding as Direct Metrics Optimization
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
Efficient-3Dim: Learning a Generalizable Single-image Novel-view Synthesizer in One Day
Identifying Representations for Intervention Extrapolation
PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Training
Fusion Is Not Enough: Single Modal Attacks on Fusion Models for 3D Object Detection
Grokking as a First Order Phase Transition in Two Layer Networks
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
Language Model Self-improvement by Reinforcement Learning Contemplation
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
Function-space Parameterization of Neural Networks for Sequential Learning
Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints
Efficient and Scalable Graph Generation through Iterative Local Expansion
sRGB Real Noise Modeling via Noise-Aware Sampling with Normalizing Flows
PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts
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
PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization
RETSim: Resilient and Efficient Text Similarity
MUFFIN: Curating Multi-Faceted Instructions for Improving Instruction Following
Directly Fine-Tuning Diffusion Models on Differentiable Rewards
ConjNorm: Tractable Density Estimation for Out-of-Distribution Detection
Convolutional Deep Kernel Machines
Theoretical Analysis of Robust Overfitting for Wide DNNs: An NTK Approach
Reverse Diffusion Monte Carlo
Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs
Towards Few-Shot Adaptation of Foundation Models via Multitask Finetuning
ReSimAD: Zero-Shot 3D Domain Transfer for Autonomous Driving with Source Reconstruction and Target Simulation
I-PHYRE: Interactive Physical Reasoning
DreamTime: An Improved Optimization Strategy for Diffusion-Guided 3D Generation
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
Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency
Data Distillation Can Be Like Vodka: Distilling More Times For Better Quality
Rethinking Complex Queries on Knowledge Graphs with Neural Link Predictors
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
Sparse Spiking Neural Network: Exploiting Heterogeneity in Timescales for Pruning Recurrent SNN
UNR-Explainer: Counterfactual Explanations for Unsupervised Node Representation Learning Models
Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors
TopoMLP: A Simple yet Strong Pipeline for Driving Topology Reasoning
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
Language Control Diffusion: Efficiently Scaling through Space, Time, and Tasks
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
Consistent algorithms for multi-label classification with macro-at-$k$ metrics
NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers
PromptTTS 2: Describing and Generating Voices with Text Prompt
Discovering modular solutions that generalize compositionally
Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time Steps
Be More Active! Understanding the Differences Between Mean and Sampled Representations of Variational Autoencoders
CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity
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
PeFLL: Personalized Federated Learning by Learning to Learn
Robust Angular Synchronization via Directed Graph Neural Networks
Maximum Entropy Model Correction in Reinforcement Learning
Improving protein optimization with smoothed fitness landscapes
Emu: Generative Pretraining in Multimodality
Sample-Efficient Learning of POMDPs with Multiple Observations In Hindsight
Quantifying the Plausibility of Context Reliance in Neural Machine Translation
Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing
BrainSCUBA: Fine-Grained Natural Language Captions of Visual Cortex Selectivity
Evaluating Large Language Models at Evaluating Instruction Following
Enabling Efficient Equivariant Operations in the Fourier Basis via Gaunt Tensor Products
LLM-Assisted Code Cleaning For Training Accurate Code Generators
Views Can Be Deceiving: Improved SSL Through Feature Space Augmentation
Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning
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
ExeDec: Execution Decomposition for Compositional Generalization in Neural Program Synthesis
RAIN: Your Language Models Can Align Themselves without Finetuning
Traveling Waves Encode The Recent Past and Enhance Sequence Learning
Lie Group Decompositions for Equivariant Neural Networks
Universal Guidance for Diffusion Models
SAFLEX: Self-Adaptive Augmentation via Feature Label Extrapolation
Masks, Signs, And Learning Rate Rewinding
Counting Graph Substructures with Graph Neural Networks
From Graphs to Hypergraphs: Hypergraph Projection and its Reconstruction
Data Debugging with Shapley Importance over Machine Learning Pipelines
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
CAMIL: Context-Aware Multiple Instance Learning for Cancer Detection and Subtyping in Whole Slide Images
The Human-AI Substitution game: active learning from a strategic labeler
Towards Eliminating Hard Label Constraints in Gradient Inversion Attacks
Learning Interactive Real-World Simulators
Towards Meta-Pruning via Optimal Transport
Probabilistic Self-supervised Representation Learning via Scoring Rules Minimization
Classification with Conceptual Safeguards
Learning Conditional Invariances through Non-Commutativity
$\mathbb{D}^2$ Pruning: Message Passing for Balancing Diversity & Difficulty in Data Pruning
Dissecting learning and forgetting in language model finetuning
Scaling physics-informed hard constraints with mixture-of-experts
In-context Autoencoder for Context Compression in a Large Language Model
On Stationary Point Convergence of PPO-Clip
How to Capture Higher-order Correlations? Generalizing Matrix Softmax Attention to Kronecker Computation
Faster Sampling from Log-Concave Densities over Polytopes via Efficient Linear Solvers
General Graph Random Features
Grokking as the transition from lazy to rich training dynamics
Are Models Biased on Text without Gender-related Language?
SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs
Reverse Forward Curriculum Learning for Extreme Sample and Demo Efficiency
Uni3D: Exploring Unified 3D Representation at Scale
Toward Student-oriented Teacher Network Training for Knowledge Distillation
Privacy-Preserving In-Context Learning for Large Language Models
A Discretization Framework for Robust Contextual Stochastic Optimization
LQ-LoRA: Low-rank plus Quantized Matrix Decomposition for Efficient Language Model Finetuning
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
A ROBUST DIFFERENTIAL NEURAL ODE OPTIMIZER
Fast and unified path gradient estimators for normalizing flows
Out-of-Variable Generalisation for Discriminative Models
On the generalization capacity of neural networks during generic multimodal reasoning
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
Outliers with Opposing Signals Have an Outsized Effect on Neural Network Optimization
From Sparse to Soft Mixtures of Experts
Language-Informed Visual Concept Learning
Turning large language models into cognitive models
The Unreasonable Effectiveness of Linear Prediction as a Perceptual Metric
Neural Snowflakes: Universal Latent Graph Inference via Trainable Latent Geometries
Future Language Modeling from Temporal Document History
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
Light Schrödinger Bridge
Improved Techniques for Training Consistency Models
Modeling Boundedly Rational Agents with Latent Inference Budgets
A Unified Sampling Framework for Solver Searching of Diffusion Probabilistic Models
HYPO: Hyperspherical Out-Of-Distribution Generalization
On the Foundations of Shortcut Learning
Emergent Communication with Conversational Repair
THOUGHT PROPAGATION: AN ANALOGICAL APPROACH TO COMPLEX REASONING WITH LARGE LANGUAGE MODELS
SmartPlay : A Benchmark for LLMs as Intelligent Agents
A General Framework for User-Guided Bayesian Optimization
The Curse of Diversity in Ensemble-Based Exploration
InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior
SWAP: Sparse Entropic Wasserstein Regression for Robust Network Pruning
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?
Noisy Interpolation Learning with Shallow Univariate ReLU Networks
The LLM Surgeon
Causal-StoNet: Causal Inference for High-Dimensional Complex Data
Equivariant Scalar Fields for Molecular Docking with Fast Fourier Transforms
SPDER: Semiperiodic Damping-Enabled Object Representation
MgNO: Efficient Parameterization of Linear Operators via Multigrid
Belief-Enriched Pessimistic Q-Learning against Adversarial State Perturbations
Towards Identifiable Unsupervised Domain Translation: A Diversified Distribution Matching Approach
Diffusion-TS: Interpretable Diffusion for General Time Series Generation
Brain decoding: toward real-time reconstruction of visual perception
Why is SAM Robust to Label Noise?
Continual Learning in the Presence of Spurious Correlations: Analyses and a Simple Baseline
GIO: Gradient Information Optimization for Training Dataset Selection
An Efficient Tester-Learner for Halfspaces
Revisiting the Last-Iterate Convergence of Stochastic Gradient Methods
Batch normalization is sufficient for universal function approximation in CNNs
The Need for Speed: Pruning Transformers with One Recipe
How Does Unlabeled Data Provably Help Out-of-Distribution Detection?
Vision-by-Language for Training-Free Compositional Image Retrieval
Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks
Universal Jailbreak Backdoors from Poisoned Human Feedback
Variance-enlarged Poisson Learning for Graph-based Semi-Supervised Learning with Extremely Sparse Labeled Data
PROGRAM: PROtotype GRAph Model based Pseudo-Label Learning for Test-Time Adaptation
Coordinate-Aware Modulation for Neural Fields
COCO-Periph: Bridging the Gap Between Human and Machine Perception in the Periphery
Linear attention is (maybe) all you need (to understand Transformer optimization)
In-Context Learning Learns Label Relationships but Is Not Conventional Learning
Zero-Mean Regularized Spectral Contrastive Learning: Implicitly Mitigating Wrong Connections in Positive-Pair Graphs
ConR: Contrastive Regularizer for Deep Imbalanced Regression
TACTiS-2: Better, Faster, Simpler Attentional Copulas for Multivariate Time Series
Sign2GPT: Leveraging Large Language Models for Gloss-Free Sign Language Translation
Equivariant Matrix Function Neural Networks
Sparsistency for inverse optimal transport
Towards Poisoning Fair Representations
Provably Efficient UCB-type Algorithms For Learning Predictive State Representations
Boosting Graph Anomaly Detection with Adaptive Message Passing
NOLA: Compressing LoRA using Linear Combination of Random Basis
Are Transformers with One Layer Self-Attention Using Low-Rank Weight Matrices Universal Approximators?
MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models
GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformers
A Newborn Embodied Turing Test for Comparing Object Segmentation Across Animals and Machines
Effective Data Augmentation With Diffusion Models
Incremental Randomized Smoothing Certification
Training Graph Transformers via Curriculum-Enhanced Attention Distillation
AUGCAL: Improving Sim2Real Adaptation by Uncertainty Calibration on Augmented Synthetic Images
Symmetric Mean-field Langevin Dynamics for Distributional Minimax Problems
DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion Models
Beyond Stationarity: Convergence Analysis of Stochastic Softmax Policy Gradient Methods
The Effect of Intrinsic Dataset Properties on Generalization: Unraveling Learning Differences Between Natural and Medical Images
Early Neuron Alignment in Two-layer ReLU Networks with Small Initialization
Scaling Convex Neural Networks with Burer-Monteiro Factorization
Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach
Learning invariant representations of time-homogeneous stochastic dynamical systems
Image Clustering via the Principle of Rate Reduction in the Age of Pretrained Models
FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling
SWAP-NAS: Sample-Wise Activation Patterns for Ultra-fast NAS
USB-NeRF: Unrolling Shutter Bundle Adjusted Neural Radiance Fields
Generative Modeling of Regular and Irregular Time Series Data via Koopman VAEs
Near-Optimal Solutions of Constrained Learning Problems
Compositional Preference Models for Aligning LMs
Learning to Reject Meets Long-tail Learning
LabelDP-Pro: Learning with Label Differential Privacy via Projections
Unbalancedness in Neural Monge Maps Improves Unpaired Domain Translation
CoBIT: A Contrastive Bi-directional Image-Text Generation Model
Entropy Coding of Unordered Data Structures
Generalization of Scaled Deep ResNets in the Mean-Field Regime
Denoising Diffusion via Image-Based Rendering
On the Hardness of Online Nonconvex Optimization with Single Oracle Feedback
Energy-conserving equivariant GNN for elasticity of lattice architected metamaterials
Kernelised Normalising Flows
Constraint-Free Structure Learning with Smooth Acyclic Orientations
Removing Biases from Molecular Representations via Information Maximization
ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language Models
Attention-based Iterative Decomposition for Tensor Product Representation
DSPy: Compiling Declarative Language Model Calls into State-of-the-Art Pipelines
Self-Alignment with Instruction Backtranslation
Consistent4D: Consistent 360° Dynamic Object Generation from Monocular Video
Sum-Product-Set Networks: Deep Tractable Models for Tree-Structured Graphs
GraphCare: Enhancing Healthcare Predictions with Personalized Knowledge Graphs
Long-Short-Range Message-Passing: A Physics-Informed Framework to Capture Non-Local Interaction for Scalable Molecular Dynamics Simulation
A Framework and Benchmark for Deep Batch Active Learning for Regression
On Bias-Variance Alignment in Deep Models
InstructDET: Diversifying Referring Object Detection with Generalized Instructions
Patched Denoising Diffusion Models For High-Resolution Image Synthesis
Like Oil and Water: Group Robustness Methods and Poisoning Defenses May Be at Odds
Understanding Addition in Transformers
Teach LLMs to Phish: Stealing Private Information from Language Models
Noise-free Score Distillation
Efficient Integrators for Diffusion Generative Models
Demonstration-Regularized RL
Symmetric Basis Convolutions for Learning Lagrangian Fluid Mechanics
You Only Query Once: An Efficient Label-Only Membership Inference Attack
Unlocking the Power of Representations in Long-term Novelty-based Exploration
To the Cutoff... and Beyond? A Longitudinal Perspective on LLM Data Contamination
Exploring the cloud of feature interaction scores in a Rashomon set
Graph Transformers on EHRs: Better Representation Improves Downstream Performance
CLIP the Bias: How Useful is Balancing Data in Multimodal Learning?
Causally Aligned Curriculum Learning
GenCorres: Consistent Shape Matching via Coupled Implicit-Explicit Shape Generative Models
Scalable Modular Network: A Framework for Adaptive Learning via Agreement Routing
CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules
Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!
On Adversarial Training without Perturbing all Examples
Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ
Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation
Unsupervised Order Learning
Leftover Lunch: Advantage-based Offline Reinforcement Learning for Language Models
Communication-Efficient Gradient Descent-Accent Methods for Distributed Variational Inequalities: Unified Analysis and Local Updates
Random Feature Amplification: Feature Learning and Generalization in Neural Networks
Advancing the Lower Bounds: an Accelerated, Stochastic, Second-order Method with Optimal Adaptation to Inexactness
DDMI: Domain-agnostic Latent Diffusion Models for Synthesizing High-Quality Implicit Neural Representations
TiC-CLIP: Continual Training of CLIP Models
Label-Noise Robust Diffusion Models
Conditional Information Bottleneck Approach for Time Series Imputation
ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models
Transferring Labels to Solve Annotation Mismatches Across Object Detection Datasets
Scaling Laws for Sparsely-Connected Foundation Models
Human Feedback is not Gold Standard
Adaptive Retrieval and Scalable Indexing for k-NN Search with Cross-Encoders
DNABERT-2: Efficient Foundation Model and Benchmark For Multi-Species Genomes
COSA: Concatenated Sample Pretrained Vision-Language Foundation Model
FedWon: Triumphing Multi-domain Federated Learning Without Normalization
Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo
Adversarial Training Should Be Cast as a Non-Zero-Sum Game
Contrastive Learning is Spectral Clustering on Similarity Graph
Federated Orthogonal Training: Mitigating Global Catastrophic Forgetting in Continual Federated Learning
Feature Collapse
HAZARD Challenge: Embodied Decision Making in Dynamically Changing Environments
Fine-Tuning Language Models for Factuality
Multi-Resolution Diffusion Models for Time Series Forecasting
In-context Exploration-Exploitation for Reinforcement Learning
Node2ket: Efficient High-Dimensional Network Embedding in Quantum Hilbert Space
Non-negative Contrastive Learning
Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX
DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation
Zero-Shot Robustification of Zero-Shot Models
Successor Heads: Recurring, Interpretable Attention Heads In The Wild
SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents
Towards image compression with perfect realism at ultra-low bitrates
Fantastic Generalization Measures are Nowhere to be Found
Topological data analysis on noisy quantum computers
Path Choice Matters for Clear Attributions in Path Methods
Complete and Efficient Graph Transformers for Crystal Material Property Prediction
Robust Training of Federated Models with Extremely Label Deficiency
Diffeomorphic Mesh Deformation via Efficient Optimal Transport for Cortical Surface Reconstruction
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
Robust Model Based Reinforcement Learning Using $\mathcal{L}_1$ Adaptive Control
BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inference
Cameras as Rays: Pose Estimation via Ray Diffusion
STanHop: Sparse Tandem Hopfield Model for Memory-Enhanced Time Series Prediction
ODEFormer: Symbolic Regression of Dynamical Systems with Transformers
Exposing Text-Image Inconsistency Using Diffusion Models
Adapting to Distribution Shift by Visual Domain Prompt Generation
Analyzing and Improving Optimal-Transport-based Adversarial Networks
MINDE: Mutual Information Neural Diffusion Estimation
Efficient Multi-agent Reinforcement Learning by Planning
Universal Backdoor Attacks
Understanding the robustness difference between stochastic gradient descent and adaptive gradient methods
OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental Learning
ClimODE: Climate and Weather Forecasting with Physics-informed Neural ODEs
Confronting Reward Model Overoptimization with Constrained RLHF
PRES: Toward Scalable Memory-Based Dynamic Graph Neural Networks
Language Models Represent Space and Time
The Generalization Gap in Offline Reinforcement Learning
Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLM
On the Hardness of Constrained Cooperative Multi-Agent Reinforcement Learning
Uncertainty Quantification via Stable Distribution Propagation
$\pi$2vec: Policy Representation with Successor Features
Dissecting Sample Hardness: A Fine-Grained Analysis of Hardness Characterization Methods for Data-Centric AI
DyST: Towards Dynamic Neural Scene Representations on Real-World Videos
Würstchen: An Efficient Architecture for Large-Scale Text-to-Image Diffusion Models
LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models
Understanding the Robustness of Multi-modal Contrastive Learning to Distribution Shift
Investigating the Benefits of Projection Head for Representation Learning
Post-hoc bias scoring is optimal for fair classification
Identifying Policy Gradient Subspaces
GraphPulse: Topological representations for temporal graph property prediction
Implicit Neural Representations and the Algebra of Complex Wavelets
BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation
Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models
Conformal Inductive Graph Neural Networks
Consistency Models as a Rich and Efficient Policy Class for Reinforcement Learning
Functional Interpolation for Relative Positions improves Long Context Transformers
Polynormer: Polynomial-Expressive Graph Transformer in Linear Time
Democratizing Fine-grained Visual Recognition with Large Language Models
FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity
Adaptive Rational Activations to Boost Deep Reinforcement Learning
Linearity of Relation Decoding in Transformer Language Models
On the Parameterization of Second-Order Optimization Effective towards the Infinite Width
Posterior Sampling Based on Gradient Flows of the MMD with Negative Distance Kernel
LRM: Large Reconstruction Model for Single Image to 3D
FFB: A Fair Fairness Benchmark for In-Processing Group Fairness Methods
Generative Sliced MMD Flows with Riesz Kernels
Kosmos-G: Generating Images in Context with Multimodal Large Language Models
Domain-Agnostic Molecular Generation with Chemical Feedback
BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection
COLLIE: Systematic Construction of Constrained Text Generation Tasks
Self-Supervised Dataset Distillation for Transfer Learning
Improved sampling via learned diffusions
Learning Polynomial Problems with $SL(2, \mathbb{R})$-Equivariance
FLD: Fourier Latent Dynamics for Structured Motion Representation and Learning
Large-scale Training of Foundation Models for Wearable Biosignals
Adaptive Federated Learning with Auto-Tuned Clients
FedTrans: Client-Transparent Utility Estimation for Robust Federated Learning
Are Human-generated Demonstrations Necessary for In-context Learning?
OmniControl: Control Any Joint at Any Time for Human Motion Generation
Leave-one-out Distinguishability in Machine Learning
Pre-training Sequence, Structure, and Surface Features for Comprehensive Protein Representation Learning
Structuring Representation Geometry with Rotationally Equivariant Contrastive Learning
T-MARS: Improving Visual Representations by Circumventing Text Feature Learning
A Simple Romance Between Multi-Exit Vision Transformer and Token Reduction
Revisit and Outstrip Entity Alignment: A Perspective of Generative Models
Efficient Backpropagation with Variance Controlled Adaptive Sampling
DIG In: Evaluating Disparities in Image Generations with Indicators for Geographic Diversity
The Hidden Language of Diffusion Models
Federated Q-Learning: Linear Regret Speedup with Low Communication Cost
Follow-Up Differential Descriptions: Language Models Resolve Ambiguities for Image Classification
Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game
Consistent Multi-Class Classification from Multiple Unlabeled Datasets
Ito Diffusion Approximation of Universal Ito Chains for Sampling, Optimization and Boosting
Stochastic Gradient Descent for Gaussian Processes Done Right
HiGen: Hierarchical Graph Generative Networks
GAIA: a benchmark for General AI Assistants
Nougat: Neural Optical Understanding for Academic Documents
Unraveling the Key Components of OOD Generalization via Diversification
JoMA: Demystifying Multilayer Transformers via Joint Dynamics of MLP and Attention
Efficient Streaming Language Models with Attention Sinks
RLCD: Reinforcement Learning from Contrastive Distillation for LM Alignment
Unifying Feature and Cost Aggregation with Transformers for Semantic and Visual Correspondence
Illusory Attacks: Information-theoretic detectability matters in adversarial attacks
SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer
UniAdapter: Unified Parameter-Efficient Transfer Learning for Cross-modal Modeling
LiDAR: Sensing Linear Probing Performance in Joint Embedding SSL Architectures
Expressive Losses for Verified Robustness via Convex Combinations
AffineQuant: Affine Transformation Quantization for Large Language Models
AnyText: Multilingual Visual Text Generation and Editing
What Algorithms can Transformers Learn? A Study in Length Generalization
On the Provable Advantage of Unsupervised Pretraining
Object-Aware Inversion and Reassembly for Image Editing
Towards Optimal Feature-Shaping Methods for Out-of-Distribution Detection
Quality-Diversity through AI Feedback
Social-Transmotion: Promptable Human Trajectory Prediction
Decoding Natural Images from EEG for Object Recognition
Let Models Speak Ciphers: Multiagent Debate through Embeddings
LLM Augmented LLMs: Expanding Capabilities through Composition
Relaxing the Additivity Constraints in Decentralized No-Regret High-Dimensional Bayesian Optimization
FeatUp: A Model-Agnostic Framework for Features at Any Resolution
Enhancing Neural Subset Selection: Integrating Background Information into Set Representations
Poly-View Contrastive Learning
Peering Through Preferences: Unraveling Feedback Acquisition for Aligning Large Language Models
Safe and Robust Watermark Injection with a Single OoD Image
A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis
Soft Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample Complexity
Can LLM-Generated Misinformation Be Detected?
Multimodal Web Navigation with Instruction-Finetuned Foundation Models
Exploring Effective Stimulus Encoding via Vision System Modeling for Visual Prostheses
Aux-NAS: Exploiting Auxiliary Labels with Negligibly Extra Inference Cost
Multi-View Causal Representation Learning with Partial Observability
DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer
Lion Secretly Solves a Constrained Optimization: As Lyapunov Predicts
Generating Pragmatic Examples to Train Neural Program Synthesizers
Symmetric Single Index Learning
Denoising Diffusion Step-aware Models
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
Teaching Arithmetic to Small Transformers
What's In My Big Data?
Generalizability of Adversarial Robustness Under Distribution Shifts
Counterfactual Density Estimation using Kernel Stein Discrepancies
On the Learnability of Watermarks for Language Models
Periodicity Decoupling Framework for Long-term Series Forecasting
Scaling Autoregressive Models for Content-Rich Text-to-Image Generation
Learning Stackable and Skippable LEGO Bricks for Efficient, Reconfigurable, and Variable-Resolution Diffusion Modeling
UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition
Statistical Rejection Sampling Improves Preference Optimization
UC-NERF: Neural Radiance Field for Under-Calibrated Multi-View Cameras in Autonomous Driving
Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models
Adaptive Regularization of Representation Rank as an Implicit Constraint of Bellman Equation
MBR and QE Finetuning: Training-time Distillation of the Best and Most Expensive Decoding Methods
RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory Sketches
PanoDiffusion: 360-degree Panorama Outpainting via Diffusion
Making LLaMA SEE and Draw with SEED Tokenizer
Human Motion Diffusion as a Generative Prior
Closing the Curious Case of Neural Text Degeneration
The Marginal Value of Momentum for Small Learning Rate SGD
Is attention required for ICL? Exploring the Relationship Between Model Architecture and In-Context Learning Ability
Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Data
LLMCarbon: Modeling the End-to-End Carbon Footprint of Large Language Models
StructComp: Substituting propagation with Structural Compression in Training Graph Contrastive Learning
Contrastive Difference Predictive Coding
Stable Anisotropic Regularization
A Framework for Inference Inspired by Human Memory Mechanisms
PBADet: A One-Stage Anchor-Free Approach for Part-Body Association
Kalman Filter for Online Classification of Non-Stationary Data
Large Language Models to Enhance Bayesian Optimization
A Characterization Theorem for Equivariant Networks with Point-wise Activations
Beyond Accuracy: Evaluating Self-Consistency of Code Large Language Models with IdentityChain
An Investigation of Representation and Allocation Harms in Contrastive Learning
Functional Bayesian Tucker Decomposition for Continuous-indexed Tensor Data
Circuit Component Reuse Across Tasks in Transformer Language Models
Neural-Symbolic Recursive Machine for Systematic Generalization
Context-Aware Meta-Learning
Accurate and Scalable Estimation of Epistemic Uncertainty for Graph Neural Networks
Neuro-Inspired Information-Theoretic Hierarchical Perception for Multimodal Learning
EmerDiff: Emerging Pixel-level Semantic Knowledge in Diffusion Models
FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores
MOTOR: A Time-to-Event Foundation Model For Structured Medical Records
Spurious Feature Diversification Improves Out-of-distribution Generalization
Structured Video-Language Modeling with Temporal Grouping and Spatial Grounding
OMNI: Open-endedness via Models of human Notions of Interestingness
End-to-End (Instance)-Image Goal Navigation through Correspondence as an Emergent Phenomenon
Tuning LayerNorm in Attention: Towards Efficient Multi-Modal LLM Finetuning
Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning
Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking
Learning from Aggregate responses: Instance Level versus Bag Level Loss Functions
Few-Shot Detection of Machine-Generated Text using Style Representations
HyperAttention: Long-context Attention in Near-Linear Time
Improved Analysis of Sparse Linear Regression in Local Differential Privacy Model
GlucoBench: Curated List of Continuous Glucose Monitoring Datasets with Prediction Benchmarks
On the Posterior Distribution in Denoising: Application to Uncertainty Quantification
Visual Data-Type Understanding does not emerge from scaling Vision-Language Models
Reward Design for Justifiable Sequential Decision-Making
Source-Free and Image-Only Unsupervised Domain Adaptation for Category Level Object Pose Estimation
Retro-fallback: retrosynthetic planning in an uncertain world
Efficiently Computing Similarities to Private Datasets
Enhancing Neural Training via a Correlated Dynamics Model
Modeling state-dependent communication between brain regions with switching nonlinear dynamical systems
BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models
Domain constraints improve risk prediction when outcome data is missing
fairret: a Framework for Differentiable Fairness Regularization Terms
On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes
DistillSpec: Improving Speculative Decoding via Knowledge Distillation
Understanding Reconstruction Attacks with the Neural Tangent Kernel and Dataset Distillation
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
DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models
FedLoGe: Joint Local and Generic Federated Learning under Long-tailed Data
GNNX-BENCH: Unravelling the Utility of Perturbation-based GNN Explainers through In-depth Benchmarking
Structural Fairness-aware Active Learning for Graph Neural Networks
Efficient Planning with Latent Diffusion
A Differentially Private Clustering Algorithm for Well-Clustered Graphs
Fast Imitation via Behavior Foundation Models
Enhancing Small Medical Learners with Privacy-preserving Contextual Prompting
Sin3DM: Learning a Diffusion Model from a Single 3D Textured Shape
Prediction Error-based Classification for Class-Incremental Learning
Score Models for Offline Goal-Conditioned Reinforcement Learning
Fourier Transporter: Bi-Equivariant Robotic Manipulation in 3D
Abstractors and relational cross-attention: An inductive bias for explicit relational reasoning in Transformers
Solving Homogeneous and Heterogeneous Cooperative Tasks with Greedy Sequential Execution
Large Language Models as Generalizable Policies for Embodied Tasks
Latent Representation and Simulation of Markov Processes via Time-Lagged Information Bottleneck
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
VDT: General-purpose Video Diffusion Transformers via Mask Modeling
What Makes a Good Prune? Maximal Unstructured Pruning for Maximal Cosine Similarity
Representation Deficiency in Masked Language Modeling
WizardCoder: Empowering Code Large Language Models with Evol-Instruct
SALMON: Self-Alignment with Instructable Reward Models
Retrieval-Enhanced Contrastive Vision-Text Models
CrossLoco: Human Motion Driven Control of Legged Robots via Guided Unsupervised Reinforcement Learning
Numerical Accounting in the Shuffle Model of Differential Privacy
The Generative AI Paradox: “What It Can Create, It May Not Understand”
Provable Benefits of Multi-task RL under Non-Markovian Decision Making Processes
A Cognitive Model for Learning Abstract Relational Structures from Memory-based Decision-Making Tasks
RECOMP: Improving Retrieval-Augmented LMs with Context Compression and Selective Augmentation
Few-shot Hybrid Domain Adaptation of Image Generator
ASID: Active Exploration for System Identification in Robotic Manipulation
Learning Multi-Agent Communication from Graph Modeling Perspective
Unveiling and Manipulating Prompt Influence in Large Language Models
SOHES: Self-supervised Open-world Hierarchical Entity Segmentation
Epitopological learning and Cannistraci-Hebb network shape intelligence brain-inspired theory for ultra-sparse advantage in deep learning
SCHEMA: State CHangEs MAtter for Procedure Planning in Instructional Videos
Horizon-free Reinforcement Learning in Adversarial Linear Mixture MDPs
The mechanistic basis of data dependence and abrupt learning in an in-context classification task
A Probabilistic Framework for Modular Continual Learning
LILO: Learning Interpretable Libraries by Compressing and Documenting Code
Towards Robust Offline Reinforcement Learning under Diverse Data Corruption
Sentence-level Prompts Benefit Composed Image Retrieval
Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory
Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy Optimization
When Semantic Segmentation Meets Frequency Aliasing
Rethinking Backdoor Attacks on Dataset Distillation: A Kernel Method Perspective
Distributionally Robust Optimization with Bias and Variance Reduction
Scaling for Training Time and Post-hoc Out-of-distribution Detection Enhancement
Test-time Adaptation against Multi-modal Reliability Bias
Retrieval-based Disentangled Representation Learning with Natural Language Supervision
INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection
PolyVoice: Language Models for Speech to Speech Translation
OpenNeRF: Open Set 3D Neural Scene Segmentation with Pixel-Wise Features and Rendered Novel Views
Bayesian Bi-clustering of Neural Spiking Activity with Latent Structures
DrS: Learning Reusable Dense Rewards for Multi-Stage Tasks
A Fast and Provable Algorithm for Sparse Phase Retrieval
HypeBoy: Generative Self-Supervised Representation Learning on Hypergraphs
Multi-granularity Correspondence Learning from Long-term Noisy Videos
LEAP: Liberate Sparse-View 3D Modeling from Camera Poses
Robustifying and Boosting Training-Free Neural Architecture Search
Understanding prompt engineering may not require rethinking generalization
Skill or Luck? Return Decomposition via Advantage Functions
Rethinking the symmetry-preserving circuits for constrained variational quantum algorithms
TorchRL: A data-driven decision-making library for PyTorch
Candidate Label Set Pruning: A Data-centric Perspective for Deep Partial-label Learning
TUVF: Learning Generalizable Texture UV Radiance Fields
Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking
LLM-CXR: Instruction-Finetuned LLM for CXR Image Understanding and Generation
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
Do Generated Data Always Help Contrastive Learning?
Revisiting Link Prediction: a data perspective
AUC-CL: A Batchsize-Robust Framework for Self-Supervised Contrastive Representation Learning
Realistic Evaluation of Semi-supervised Learning Algorithms in Open Environments
Simplifying Transformer Blocks
AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models
Achieving Human Parity in Content-Grounded Datasets Generation
Tree Search-Based Policy Optimization under Stochastic Execution Delay
Unbiased Watermark for Large Language Models
Image2Sentence based Asymmetrical Zero-shot Composed Image Retrieval
TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models
Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning with Diverse Tasks
Parsing neural dynamics with infinite recurrent switching linear dynamical systems
Asymptotically Free Sketched Ridge Ensembles: Risks, Cross-Validation, and Tuning
Provable Offline Preference-Based Reinforcement Learning
SineNet: Learning Temporal Dynamics in Time-Dependent Partial Differential Equations
Provably Efficient CVaR RL in Low-rank MDPs
Improved Probabilistic Image-Text Representations
BRUSLEATTACK: A QUERY-EFFICIENT SCORE- BASED BLACK-BOX SPARSE ADVERSARIAL ATTACK
Continual Learning on a Diet: Learning from Sparsely Labeled Streams Under Constrained Computation
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
Overthinking the Truth: Understanding how Language Models Process False Demonstrations
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
Get more for less: Principled Data Selection for Warming Up Fine-Tuning in LLMs
Towards Category Unification of 3D Single Object Tracking on Point Clouds
Learning Hierarchical Polynomials with Three-Layer Neural Networks
LEAD: Min-Max Optimization from a Physical Perspective
FROSTER: Frozen CLIP is A Strong Teacher for Open-Vocabulary Action Recognition
What does automatic differentiation compute for neural networks?
Self-Consuming Generative Models Go MAD
Out-of-Distribution Detection with Negative Prompts
STARC: A General Framework For Quantifying Differences Between Reward Functions
Theoretical Understanding of Learning from Adversarial Perturbations
Quadratic models for understanding catapult dynamics of neural networks
How to Fine-Tune Vision Models with SGD
NEFTune: Noisy Embeddings Improve Instruction Finetuning
Frozen Transformers in Language Models Are Effective Visual Encoder Layers
Gene Regulatory Network Inference in the Presence of Dropouts: a Causal View
An operator preconditioning perspective on training in physics-informed machine learning
Meta-Learning Priors Using Unrolled Proximal Networks
CircuitNet 2.0: An Advanced Dataset for Promoting Machine Learning Innovations in Realistic Chip Design Environment
Understanding the Effects of RLHF on LLM Generalisation and Diversity
GNNBoundary: Towards Explaining Graph Neural Networks through the Lens of Decision Boundaries
Chain-of-Experts: When LLMs Meet Complex Operations Research Problems
TextField3D: Towards Enhancing Open-Vocabulary 3D Generation with Noisy Text Fields
Looped Transformers are Better at Learning Learning Algorithms
Overcoming the Pitfalls of Vision-Language Model Finetuning for OOD Generalization
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
Learning Optimal Contracts: How to Exploit Small Action Spaces
A Flexible Generative Model for Heterogeneous Tabular EHR with Missing Modality
Tree Cross Attention
Don't Play Favorites: Minority Guidance for Diffusion Models
Koopman-based generalization bound: New aspect for full-rank weights
Frequency-Aware Transformer for Learned Image Compression
MUSTARD: Mastering Uniform Synthesis of Theorem and Proof Data
GeoLLM: Extracting Geospatial Knowledge from Large Language Models
Long-tailed Diffusion Models with Oriented Calibration
On Harmonizing Implicit Subpopulations
Provably Efficient Iterated CVaR Reinforcement Learning with Function Approximation and Human Feedback
DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified Robustness
ImageNet-OOD: Deciphering Modern Out-of-Distribution Detection Algorithms
CoT3DRef: Chain-of-Thoughts Data-Efficient 3D Visual Grounding
Habitat 3.0: A Co-Habitat for Humans, Avatars, and Robots
Diffusion Posterior Sampling for Linear Inverse Problem Solving: A Filtering Perspective
Policy Rehearsing: Training Generalizable Policies for Reinforcement Learning
Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks
Towards Codable Watermarking for Injecting Multi-Bits Information to LLMs
An Extensible Framework for Open Heterogeneous Collaborative Perception
Protein Multimer Structure Prediction via Prompt Learning
Circumventing Concept Erasure Methods For Text-To-Image Generative Models
A Multi-Level Framework for Accelerating Training Transformer Models
Idempotence and Perceptual Image Compression
Supervised Knowledge Makes Large Language Models Better In-context Learners
Aligning Relational Learning with Lipschitz Fairness
Accelerating Data Generation for Neural Operators via Krylov Subspace Recycling
Understanding In-Context Learning from Repetitions
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
Discovering Temporally-Aware Reinforcement Learning Algorithms
Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs
A Precise Characterization of SGD Stability Using Loss Surface Geometry
Neural Field Classifiers via Target Encoding and Classification Loss
The Expressive Power of Transformers with Chain of Thought
Memory-Consistent Neural Networks for Imitation Learning
Scaling Laws for Associative Memories
JointNet: Extending Text-to-Image Diffusion for Dense Distribution Modeling
Towards Reliable and Efficient Backdoor Trigger Inversion via Decoupling Benign Features
Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models
Federated Text-driven Prompt Generation for Vision-Language Models
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
Reclaiming the Source of Programmatic Policies: Programmatic versus Latent Spaces
Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation
Large Language Models Cannot Self-Correct Reasoning Yet
Elucidating the Exposure Bias in Diffusion Models
LMUFormer: Low Complexity Yet Powerful Spiking Model With Legendre Memory Units
Forward Learning with Top-Down Feedback: Empirical and Analytical Characterization
Prometheus: Inducing Fine-Grained Evaluation Capability in Language Models
Experimental Design for Multi-Channel Imaging via Task-Driven Feature Selection
Fast Ensembling with Diffusion Schrödinger Bridge
Linear Log-Normal Attention with Unbiased Concentration
L2P-MIP: Learning to Presolve for Mixed Integer Programming
SyncDreamer: Generating Multiview-consistent Images from a Single-view Image
Momentum Benefits Non-iid Federated Learning Simply and Provably
Towards Transparent Time Series Forecasting
Symphony: Symmetry-Equivariant Point-Centered Spherical Harmonics for 3D Molecule Generation
Fast Hyperboloid Decision Tree Algorithms
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
Universal Humanoid Motion Representations for Physics-Based Control
Bridging Vision and Language Spaces with Assignment Prediction
Modulate Your Spectrum in Self-Supervised Learning
Continual Momentum Filtering on Parameter Space for Online Test-time Adaptation
Simple Minimax Optimal Byzantine Robust Algorithm for Nonconvex Objectives with Uniform Gradient Heterogeneity
Bilevel Optimization under Unbounded Smoothness: A New Algorithm and Convergence Analysis
PhyloGFN: Phylogenetic inference with generative flow networks
Graph Parsing Networks
CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing
IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Models
SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation
Learning to reconstruct signals from binary measurements alone
R-EDL: Relaxing Nonessential Settings of Evidential Deep Learning
Entropy-MCMC: Sampling from Flat Basins with Ease
BECLR: Batch Enhanced Contrastive Few-Shot Learning
Open the Black Box: Step-based Policy Updates for Temporally-Correlated Episodic Reinforcement Learning
Training Bayesian Neural Networks with Sparse Subspace Variational Inference
Dropout-Based Rashomon Set Exploration for Efficient Predictive Multiplicity Estimation
Attention-Guided Contrastive Role Representations for Multi-agent Reinforcement Learning
Masked Distillation Advances Self-Supervised Transformer Architecture Search
FITS: Modeling Time Series with $10k$ Parameters
A Plug-and-Play Image Registration Network
DeepSPF: Spherical SO(3)-Equivariant Patches for Scan-to-CAD Estimation
The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Language Models
Don't Judge by the Look: Towards Motion Coherent Video Representation
Interventional Fairness on Partially Known Causal Graphs: A Constrained Optimization Approach
Delphic Offline Reinforcement Learning under Nonidentifiable Hidden Confounding
Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languages
Convolution Meets LoRA: Parameter Efficient Finetuning for Segment Anything Model
CABINET: Content Relevance-based Noise Reduction for Table Question Answering
Graph Metanetworks for Processing Diverse Neural Architectures
A Variational Framework for Estimating Continuous Treatment Effects with Measurement Error
Mitigating Emergent Robustness Degradation while Scaling Graph Learning
Kill Two Birds with One Stone: Rethinking Data Augmentation for Deep Long-tailed Learning
On the Markov Property of Neural Algorithmic Reasoning: Analyses and Methods
Can We Evaluate Domain Adaptation Models Without Target-Domain Labels?
Sparse Autoencoders Find Highly Interpretable Features in Language Models
Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model
MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts
Role of Locality and Weight Sharing in Image-Based Tasks: A Sample Complexity Separation between CNNs, LCNs, and FCNs
Magnitude Invariant Parametrizations Improve Hypernetwork Learning
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
Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled video
MIntRec2.0: A Large-scale Benchmark Dataset for Multimodal Intent Recognition and Out-of-scope Detection in Conversations
ALAM: Averaged Low-Precision Activation for Memory-Efficient Training of Transformer Models
On the Reliability of Watermarks for Large Language Models
Controlled Text Generation via Language Model Arithmetic
A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation
Toward effective protection against diffusion-based mimicry through score distillation
TOSS: High-quality Text-guided Novel View Synthesis from a Single Image
Rethinking Channel Dependence for Multivariate Time Series Forecasting: Learning from Leading Indicators
Multi-View Representation is What You Need for Point-Cloud Pre-Training
PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization
When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations
LDReg: Local Dimensionality Regularized Self-Supervised Learning
Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCI
iTransformer: Inverted Transformers Are Effective for Time Series Forecasting
KoLA: Carefully Benchmarking World Knowledge of Large Language Models
Foundation Model-oriented Robustness: Robust Image Model Evaluation with Pretrained Models
On the Role of General Function Approximation in Offline Reinforcement Learning
Pseudo-Generalized Dynamic View Synthesis from a Video
Hybrid Distillation: Connecting Masked Autoencoders with Contrastive Learners
Image Inpainting via Iteratively Decoupled Probabilistic Modeling
Maximum Entropy Heterogeneous-Agent Reinforcement Learning
Transformer Fusion with Optimal Transport
Knowledge Distillation Based on Transformed Teacher Matching
Minimum width for universal approximation using ReLU networks on compact domain
Tree-Planner: Efficient Close-loop Task Planning with Large Language Models
Deep Temporal Graph Clustering
DV-3DLane: End-to-end Multi-modal 3D Lane Detection with Dual-view Representation
A Semantic Invariant Robust Watermark for Large Language Models
On the Analysis of GAN-based Image-to-Image Translation with Gaussian Noise Injection
Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agents
QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models
Retrieval is Accurate Generation
Confidential-DPproof: Confidential Proof of Differentially Private Training
ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs
Transport meets Variational Inference: Controlled Monte Carlo Diffusions
ACRF: Compressing Explicit Neural Radiance Fields via Attribute Compression
Navigating Dataset Documentations in AI: A Large-Scale Analysis of Dataset Cards on HuggingFace
De novo Protein Design Using Geometric Vector Field Networks
Robust agents learn causal world models
Sample-Efficient Quality-Diversity by Cooperative Coevolution
DecompOpt: Controllable and Decomposed Diffusion Models for Structure-based Molecular Optimization
Adversarial Feature Map Pruning for Backdoor
TD-MPC2: Scalable, Robust World Models for Continuous Control
Towards Cheaper Inference in Deep Networks with Lower Bit-Width Accumulators
DiLu: A Knowledge-Driven Approach to Autonomous Driving with Large Language Models
The Expressive Leaky Memory Neuron: an Efficient and Expressive Phenomenological Neuron Model Can Solve Long-Horizon Tasks.
DisenBooth: Identity-Preserving Disentangled Tuning for Subject-Driven Text-to-Image Generation
Chain of Hindsight aligns Language Models with Feedback
Adversarial Supervision Makes Layout-to-Image Diffusion Models Thrive
Inner Classifier-Free Guidance and Its Taylor Expansion for Diffusion Models
More is Better: when Infinite Overparameterization is Optimal and Overfitting is Obligatory
Understanding In-Context Learning in Transformers and LLMs by Learning to Learn Discrete Functions
Efficient Sharpness-Aware Minimization for Molecular Graph Transformer Models
From Posterior Sampling to Meaningful Diversity in Image Restoration
Discovering Failure Modes of Text-guided Diffusion Models via Adversarial Search
MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training
Bootstrapping Variational Information Pursuit with Large Language and Vision Models for Interpretable Image Classification
Headless Language Models: Learning without Predicting with Contrastive Weight Tying
MAP IT to Visualize Representations
PolyGCL: GRAPH CONTRASTIVE LEARNING via Learnable Spectral Polynomial Filters
Analytically Tractable Hidden-States Inference in Bayesian Neural Networks
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
Explaining Time Series via Contrastive and Locally Sparse Perturbations
Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecasting
Generative Judge for Evaluating Alignment
GIM: Learning Generalizable Image Matcher From Internet Videos
Lemur: Harmonizing Natural Language and Code for Language Agents
Language Modeling Is Compression
IceFormer: Accelerated Inference with Long-Sequence Transformers on CPUs
ModuLoRA: Finetuning 2-Bit LLMs on Consumer GPUs by Integrating with Modular Quantizers
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
Perceptual Group Tokenizer: Building Perception with Iterative Grouping
SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis
Branch-GAN: Improving Text Generation with (not so) Large Language Models
Negatively Correlated Ensemble Reinforcement Learning for Online Diverse Game Level Generation
Gradual Optimization Learning for Conformational Energy Minimization
Bidirectional Temporal Diffusion Model for Temporally Consistent Human Animation
Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts
Predictive, scalable and interpretable knowledge tracing on structured domains
Replay across Experiments: A Natural Extension of Off-Policy RL
Sample-efficient Learning of Infinite-horizon Average-reward MDPs with General Function Approximation
iGraphMix: Input Graph Mixup Method for Node Classification
Training Socially Aligned Language Models on Simulated Social Interactions
Cleanba: A Reproducible and Efficient Distributed Reinforcement Learning Platform
CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction
Graphical Multioutput Gaussian Process with Attention
Optimal Sample Complexity of Contrastive Learning
CLaM-TTS: Improving Neural Codec Language Model for Zero-Shot Text-to-Speech
Enhanced Face Recognition using Intra-class Incoherence Constraint
Global Optimality for Non-linear Constrained Restoration Problems via Invexity
The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing
How Realistic Is Your Synthetic Data? Constraining Deep Generative Models for Tabular Data
Towards Energy Efficient Spiking Neural Networks: An Unstructured Pruning Framework
Towards Offline Opponent Modeling with In-context Learning
Evaluating Representation Learning on the Protein Structure Universe
Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL
CPPO: Continual Learning for Reinforcement Learning with Human Feedback
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
Large Language Model Cascades with Mixture of Thought Representations for Cost-Efficient Reasoning
Algorithms for Caching and MTS with reduced number of predictions
Dual Associated Encoder for Face Restoration
Constrained Decoding for Cross-lingual Label Projection
MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
Fully Hyperbolic Convolutional Neural Networks for Computer Vision
Denoising Task Routing for Diffusion Models
Matrix Manifold Neural Networks++
Towards Aligned Layout Generation via Diffusion Model with Aesthetic Constraints
Diffusion Models for Multi-Task Generative Modeling
Robot Fleet Learning via Policy Merging
Rethinking and Extending the Probabilistic Inference Capacity of GNNs
Multi-Scale Representations by Varying Window Attention for Semantic Segmentation
Synaptic Weight Distributions Depend on the Geometry of Plasticity
The Effectiveness of Random Forgetting for Robust Generalization
How connectivity structure shapes rich and lazy learning in neural circuits
PAE: Reinforcement Learning from External Knowledge for Efficient Exploration
Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognition
Ins-DetCLIP: Aligning Detection Model to Follow Human-Language Instruction
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
Compressed Context Memory for Online Language Model Interaction
GAIA: Zero-shot Talking Avatar Generation
Dynamic Sparse Training with Structured Sparsity
Instructive Decoding: Instruction-Tuned Large Language Models are Self-Refiner from Noisy Instructions
Cycle Consistency Driven Object Discovery
Object centric architectures enable efficient causal representation learning
Pre-Training and Fine-Tuning Generative Flow Networks
Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization
Duolando: Follower GPT with Off-Policy Reinforcement Learning for Dance Accompaniment
Expected flow networks in stochastic environments and two-player zero-sum games
LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection
Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning
Function Vectors in Large Language Models
RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation
Personalize Segment Anything Model with One Shot
Hebbian Learning based Orthogonal Projection for Continual Learning of Spiking Neural Networks
VCR-Graphormer: A Mini-batch Graph Transformer via Virtual Connections
LaneSegNet: Map Learning with Lane Segment Perception for Autonomous Driving
Teaching Large Language Models to Self-Debug
Langevin Monte Carlo for strongly log-concave distributions: Randomized midpoint revisited
Un-Mixing Test-Time Normalization Statistics: Combatting Label Temporal Correlation
Generative Pre-training for Speech with Flow Matching
Det-CGD: Compressed Gradient Descent with Matrix Stepsizes for Non-Convex Optimization
FedHyper: A Universal and Robust Learning Rate Scheduler for Federated Learning with Hypergradient Descent
Improving the Convergence of Dynamic NeRFs via Optimal Transport
A Symmetry-Aware Exploration of Bayesian Neural Network Posteriors
Language Model Cascades: Token-Level Uncertainty And Beyond
SEA: Sparse Linear Attention with Estimated Attention Mask
Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling Limit
When should we prefer Decision Transformers for Offline Reinforcement Learning?
ReFusion: Improving Natural Language Understanding with Computation-Efficient Retrieval Representation Fusion
CORN: Contact-based Object Representation for Nonprehensile Manipulation of General Unseen Objects
EBMDock: Neural Probabilistic Protein-Protein Docking via a Differentiable Energy Model
Protein-Ligand Interaction Prior for Binding-aware 3D Molecule Diffusion Models
Learning Implicit Representation for Reconstructing Articulated Objects
At Which Training Stage Does Code Data Help LLMs Reasoning?
Self-Supervised Speech Quality Estimation and Enhancement Using Only Clean Speech
Robust Similarity Learning with Difference Alignment Regularization
CAMBranch: Contrastive Learning with Augmented MILPs for Branching
Zipformer: A faster and better encoder for automatic speech recognition
A differentiable brain simulator bridging brain simulation and brain-inspired computing
BarLeRIa: An Efficient Tuning Framework for Referring Image Segmentation
Latent Intuitive Physics: Learning to Transfer Hidden Physics from A 3D Video
Hindsight PRIORs for Reward Learning from Human Preferences
Augmented Bayesian Policy Search
Symmetric Neural-Collapse Representations with Supervised Contrastive Loss: The Impact of ReLU and Batching
Align With Purpose: Optimize Desired Properties in CTC Models with a General Plug-and-Play Framework
Think before you speak: Training Language Models With Pause Tokens
Data Filtering Networks
SPADE: Semi-supervised Anomaly Detection under Distribution Mismatch
TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting
MT-Ranker: Reference-free machine translation evaluation by inter-system ranking
Pathologies of Predictive Diversity in Deep Ensembles
Rethinking Label Poisoning for GNNs: Pitfalls and Attacks
Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks
VQ-TR: Vector Quantized Attention for Time Series Forecasting
A Good Learner can Teach Better: Teacher-Student Collaborative Knowledge Distillation
Multilingual Jailbreak Challenges in Large Language Models
CLEX: Continuous Length Extrapolation for Large Language Models
Neural Active Learning Beyond Bandits
Ground-A-Video: Zero-shot Grounded Video Editing using Text-to-image Diffusion Models
Prompt Gradient Projection for Continual Learning
One-shot Active Learning Based on Lewis Weight Sampling for Multiple Deep Models
BayesPrompt: Prompting Large-Scale Pre-Trained Language Models on Few-shot Inference via Debiased Domain Abstraction
The Blessing of Randomness: SDE Beats ODE in General Diffusion-based Image Editing
Learning Multi-Agent Communication with Contrastive Learning
Improving Domain Generalization with Domain Relations
MG-TSD: Multi-Granularity Time Series Diffusion Models with Guided Learning Process
Window Attention is Bugged: How not to Interpolate Position Embeddings
Towards Robust Fidelity for Evaluating Explainability of Graph Neural Networks
GNNCert: Deterministic Certification of Graph Neural Networks against Adversarial Perturbations
Performance Gaps in Multi-view Clustering under the Nested Matrix-Tensor Model
Combinatorial Bandits for Maximum Value Reward Function under Value-Index Feedback
InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning
Sharpness-Aware Data Poisoning Attack
Sliced Denoising: A Physics-Informed Molecular Pre-Training Method
NetInfoF Framework: Measuring and Exploiting Network Usable Information
Sample-Efficiency in Multi-Batch Reinforcement Learning: The Need for Dimension-Dependent Adaptivity
Eureka: Human-Level Reward Design via Coding Large Language Models
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
DreamLLM: Synergistic Multimodal Comprehension and Creation
Self-Guided Masked Autoencoders for Domain-Agnostic Self-Supervised Learning
Thin-Shell Object Manipulations With Differentiable Physics Simulations
Dynamic Neural Response Tuning
BatchPrompt: Accomplish more with less
NeuroBack: Improving CDCL SAT Solving using Graph Neural Networks
Rethinking Model Ensemble in Transfer-based Adversarial Attacks
Forward Learning of Graph Neural Networks
Towards Cross Domain Generalization of Hamiltonian Representation via Meta Learning
M3C: A Framework towards Convergent, Flexible, and Unsupervised Learning of Mixture Graph Matching and Clustering
AutoChunk: Automated Activation Chunk for Memory-Efficient Deep Learning Inference
One Forward is Enough for Neural Network Training via Likelihood Ratio Method
SweetDreamer: Aligning Geometric Priors in 2D diffusion for Consistent Text-to-3D
Topic Modeling as Multi-Objective Contrastive Optimization
MetaPhysiCa: Improving OOD Robustness in Physics-informed Machine Learning
Neural Language of Thought Models
Optimistic Bayesian Optimization with Unknown Constraints
EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations
Meta-VBO: Utilizing Prior Tasks in Optimizing Risk Measures with Gaussian Processes
VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs
In-Context Learning through the Bayesian Prism
Cross-Modal Contextualized Diffusion Models for Text-Guided Visual Generation and Editing
From Molecules to Materials: Pre-training Large Generalizable Models for Atomic Property Prediction
Zoology: Measuring and Improving Recall in Efficient Language Models
On gauge freedom, conservativity and intrinsic dimensionality estimation in diffusion models
TRAM: Bridging Trust Regions and Sharpness Aware Minimization
Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection
Uncertainty-aware Graph-based Hyperspectral Image Classification
MOFDiff: Coarse-grained Diffusion for Metal-Organic Framework Design
Temporal Generalization Estimation in Evolving Graphs
Beam Enumeration: Probabilistic Explainability For Sample Efficient Self-conditioned Molecular Design
GNeRP: Gaussian-guided Neural Reconstruction of Reflective Objects with Noisy Polarization Priors
"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
NoiseDiffusion: Correcting Noise for Image Interpolation with Diffusion Models beyond Spherical Linear Interpolation
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
Learning to Act without Actions
Unified Projection-Free Algorithms for Adversarial DR-Submodular Optimization
Contextual Bandits with Online Neural Regression
Predictive auxiliary objectives in deep RL mimic learning in the brain
Score Regularized Policy Optimization through Diffusion Behavior
What's in a Prior? Learned Proximal Networks for Inverse Problems
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
Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation
Where We Have Arrived in Proving the Emergence of Sparse Interaction Primitives in DNNs
Grounded Object-Centric Learning
Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models
Robust NAS under adversarial training: benchmark, theory, and beyond
Hard-Constrained Deep Learning for Climate Downscaling
Mega-TTS 2: Boosting Prompting Mechanisms for Zero-Shot Speech Synthesis
SE(3)-Stochastic Flow Matching for Protein Backbone Generation
PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
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
IMPUS: Image Morphing with Perceptually-Uniform Sampling Using Diffusion Models
Effective pruning of web-scale datasets based on complexity of concept clusters
Offline RL with Observation Histories: Analyzing and Improving Sample Complexity
Learning From Simplicial Data Based on Random Walks and 1D Convolutions
Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning
Strategic Preys Make Acute Predators: Enhancing Camouflaged Object Detectors by Generating Camouflaged Objects
On the Scalability and Memory Efficiency of Semidefinite Programs for Lipschitz Constant Estimation of Neural Networks
InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation
PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Prediction
Approximating Nash Equilibria in Normal-Form Games via Stochastic Optimization
SemiReward: A General Reward Model for Semi-supervised Learning
A Simple and Effective Pruning Approach for Large Language Models
Adaptive Sharpness-Aware Pruning for Robust Sparse Networks
Learning with Language-Guided State Abstractions
REValueD: Regularised Ensemble Value-Decomposition for Factorisable Markov Decision Processes
LLaMA-Adapter: Efficient Fine-tuning of Large Language Models with Zero-initialized Attention
SWE-bench: Can Language Models Resolve Real-world Github Issues?
GROOT: Learning to Follow Instructions by Watching Gameplay Videos
ED-NeRF: Efficient Text-Guided Editing of 3D Scene With Latent Space NeRF
Neural Network-Based Score Estimation in Diffusion Models: Optimization and Generalization
Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse Problems
SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression
DreamFlow: High-quality text-to-3D generation by Approximating Probability Flow
Mediator Interpretation and Faster Learning Algorithms for Linear Correlated Equilibria in General Sequential Games
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
SNIP: Bridging Mathematical Symbolic and Numeric Realms with Unified Pre-training
Two-stage LLM Fine-tuning with Less Specialization and More Generalization
Object-Centric Learning with Slot Mixture Module
$t^3$-Variational Autoencoder: Learning Heavy-tailed Data with Student's t and Power Divergence
Understanding Catastrophic Forgetting in Language Models via Implicit Inference
TESTAM: A Time-Enhanced Spatio-Temporal Attention Model with Mixture of Experts
Training Diffusion Models with Reinforcement Learning
Shadow Cones: A Generalized Framework for Partial Order Embeddings
Feature emergence via margin maximization: case studies in algebraic tasks
When can transformers reason with abstract symbols?
A Lightweight Method for Tackling Unknown Participation Statistics in Federated Averaging
Localizing and Editing Knowledge In Text-to-Image Generative Models
Private Zeroth-Order Nonsmooth Nonconvex Optimization
ZeroFlow: Scalable Scene Flow via Distillation
Identifying the Risks of LM Agents with an LM-Emulated Sandbox
Learning semilinear neural operators: A unified recursive framework for prediction and data assimilation.
Reward-Consistent Dynamics Models are Strongly Generalizable for Offline Reinforcement Learning
Motif: Intrinsic Motivation from Artificial Intelligence Feedback
Empirical Likelihood for Fair Classification
Hypothesis Search: Inductive Reasoning with Language Models
Does Progress On Object Recognition Benchmarks Improve Generalization on Crowdsourced, Global Data?
LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attacks
Analyzing Feed-Forward Blocks in Transformers through the Lens of Attention Maps
MogaNet: Multi-order Gated Aggregation Network
Forward $\chi^2$ Divergence Based Variational Importance Sampling
Compositional Conservatism: A Transductive Approach in Offline Reinforcement Learning
MMD Graph Kernel: Effective Metric Learning for Graphs via Maximum Mean Discrepancy
Deep Orthogonal Hypersphere Compression for Anomaly Detection
Towards Faithful XAI Evaluation via Generalization-Limited Backdoor Watermark
GeneOH Diffusion: Towards Generalizable Hand-Object Interaction Denoising via Denoising Diffusion
Learning Energy-Based Models by Cooperative Diffusion Recovery Likelihood
Machine Unlearning for Image-to-Image Generative Models
LipVoicer: Generating Speech from Silent Videos Guided by Lip Reading
COLEP: Certifiably Robust Learning-Reasoning Conformal Prediction via Probabilistic Circuits
WildFusion: Learning 3D-Aware Latent Diffusion Models in View Space
Workflow Discovery from Dialogues in the Low Data Regime
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
VersVideo: Leveraging Enhanced Temporal Diffusion Models for Versatile Video Generation
Selective Visual Representations Improve Convergence and Generalization for Embodied AI
SEPT: Towards Efficient Scene Representation Learning for Motion Prediction
BrainLM: A foundation model for brain activity recordings
RDesign: Hierarchical Data-efficient Representation Learning for Tertiary Structure-based RNA Design
A Versatile Causal Discovery Framework to Allow Causally-Related Hidden Variables
On the Power of the Weisfeiler-Leman Test for Graph Motif Parameters
Principled Federated Domain Adaptation: Gradient Projection and Auto-Weighting
Teaching Language Models to Hallucinate Less with Synthetic Tasks
Graph Generation with $K^2$-trees
Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning
Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models
TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Series
Neural Polynomial Gabor Fields for Macro Motion Analysis
Pre-training with Synthetic Data Helps Offline Reinforcement Learning
Is Self-Repair a Silver Bullet for Code Generation?
To Grok or not to Grok: Disentangling Generalization and Memorization on Corrupted Algorithmic Datasets
Learning with Mixture of Prototypes for Out-of-Distribution Detection
SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction
Decentralized Riemannian Conjugate Gradient Method on the Stiefel Manifold
Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generation
SequenceMatch: Imitation Learning for Autoregressive Sequence Modelling with Backtracking
Str2Str: A Score-based Framework for Zero-shot Protein Conformation Sampling
On the Humanity of Conversational AI: Evaluating the Psychological Portrayal of LLMs
Incentivized Truthful Communication for Federated Bandits
Fake It Till Make It: Federated Learning with Consensus-Oriented Generation
GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher
Harnessing Density Ratios for Online Reinforcement Learning
Zeroth-Order Optimization Meets Human Feedback: Provable Learning via Ranking Oracles
H-GAP: Humanoid Control with a Generalist Planner
Biased Temporal Convolution Graph Network for Time Series Forecasting with Missing Values
IRAD: Implicit Representation-driven Image Resampling against Adversarial Attacks
One For All: Towards Training One Graph Model For All Classification Tasks
Parameter-Efficient Multi-Task Model Fusion with Partial Linearization
Select to Perfect: Imitating desired behavior from large multi-agent data
Unleashing the Potential of Fractional Calculus in Graph Neural Networks with FROND
Toward Optimal Policy Population Growth in Two-Player Zero-Sum Games
The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction
DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning
ReTaSA: A Nonparametric Functional Estimation Approach for Addressing Continuous Target Shift
Integrating Planning and Deep Reinforcement Learning via Automatic Induction of Task Substructures
Holistic Evaluation of Language Models
Achieving Fairness in Multi-Agent MDP Using Reinforcement Learning
Detecting Pretraining Data from Large Language Models
Achieving Sample and Computational Efficient Reinforcement Learning by Action Space Reduction via Grouping
Parallelizing non-linear sequential models over the sequence length
DAFA: Distance-Aware Fair Adversarial Training
Multimarginal Generative Modeling with Stochastic Interpolants
The Update-Equivalence Framework for Decision-Time Planning
Less is More: Fewer Interpretable Region via Submodular Subset Selection
CADS: Unleashing the Diversity of Diffusion Models through Condition-Annealed Sampling
AgentBench: Evaluating LLMs as Agents
MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning
BadEdit: Backdooring Large Language Models by Model Editing
Neural Monge Map estimation and its applications
Principled Architecture-aware Scaling of Hyperparameters
The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning
Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-tuning
Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion
Image Background Serves as Good Proxy for Out-of-distribution Data
ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models
ReLoRA: High-Rank Training Through Low-Rank Updates
MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning
Inverse Approximation Theory for Nonlinear Recurrent Neural Networks
LEMON: Lossless model expansion
Debiased Collaborative Filtering with Kernel-Based Causal Balancing
Sparse Model Soups: A Recipe for Improved Pruning via Model Averaging
Deceptive Fairness Attacks on Graphs via Meta Learning
Mixture of Weak and Strong Experts on Graphs
Improving Non-Transferable Representation Learning by Harnessing Content and Style
Learning to Reject with a Fixed Predictor: Application to Decontextualization
In-Context Pretraining: Language Modeling Beyond Document Boundaries
Towards Training Without Depth Limits: Batch Normalization Without Gradient Explosion
Optimal Sketching for Residual Error Estimation for Matrix and Vector Norms
Explaining Kernel Clustering via Decision Trees
Constrained Bi-Level Optimization: Proximal Lagrangian Value Function Approach and Hessian-free Algorithm
Geographic Location Encoding with Spherical Harmonics and Sinusoidal Representation Networks
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
Parametric Augmentation for Time Series Contrastive Learning
LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models
On the Effect of Batch Size in Byzantine-Robust Distributed Learning
Neuroformer: Multimodal and Multitask Generative Pretraining for Brain Data
Causal Inference with Conditional Front-Door Adjustment and Identifiable Variational Autoencoder
Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignment
Gen-Z: Generative Zero-Shot Text Classification with Contextualized Label Descriptions
Batched Low-Rank Adaptation of Foundation Models
GRAPH-CONSTRAINED DIFFUSION FOR END-TO-END PATH PLANNING
Towards LLM4QPE: Unsupervised Pretraining of Quantum Property Estimation and A Benchmark
From Bricks to Bridges: Product of Invariances to Enhance Latent Space Communication
Weakly Supervised Virus Capsid Detection with Image-Level Annotations in Electron Microscopy Images
Impact of Computation in Integral Reinforcement Learning for Continuous-Time Control
Task Adaptation from Skills: Information Geometry, Disentanglement, and New Objectives for Unsupervised Reinforcement Learning
SAS: Structured Activation Sparsification
Neural Processing of Tri-Plane Hybrid Neural Fields
Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Models
SetCSE: Set Operations using Contrastive Learning of Sentence Embeddings
Byzantine Robust Cooperative Multi-Agent Reinforcement Learning as a Bayesian Game
Patches Are All You Need?
Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching
How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression?
Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation
Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios
Manifold Diffusion Fields
Bayes Conditional Distribution Estimation for Knowledge Distillation Based on Conditional Mutual Information
ValUES: A Framework for Systematic Validation of Uncertainty Estimation in Semantic Segmentation
Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining
Adapting Large Language Models via Reading Comprehension
Threaten Spiking Neural Networks through Combining Rate and Temporal Information
Emergent mechanisms for long timescales depend on training curriculum and affect performance in memory tasks
Massively Scalable Inverse Reinforcement Learning in Google Maps
Dual RL: Unification and New Methods for Reinforcement and Imitation Learning
Let's Verify Step by Step
AlpaGasus: Training a Better Alpaca with Fewer Data
Exploring Target Representations for Masked Autoencoders
Federated Recommendation with Additive Personalization
Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs
Learning to design protein-protein interactions with enhanced generalization
Privacy Amplification for Matrix Mechanisms
LLMs Meet VLMs: Boost Open Vocabulary Object Detection with Fine-grained Descriptors
Negative Label Guided OOD Detection with Pretrained Vision-Language Models
Latent Trajectory Learning for Limited Timestamps under Distribution Shift over Time
Subtractive Mixture Models via Squaring: Representation and Learning
Mathematical Justification of Hard Negative Mining via Isometric Approximation Theorem
Bellman Optimal Stepsize Straightening of Flow-Matching Models
Benchmarking Algorithms for Federated Domain Generalization
Embodied Active Defense: Leveraging Recurrent Feedback to Counter Adversarial Patches
$\texttt{NAISR}$: A 3D Neural Additive Model for Interpretable Shape Representation
Guaranteed Approximation Bounds for Mixed-Precision Neural Operators
MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereo
AutoVP: An Automated Visual Prompting Framework and Benchmark
LoTa-Bench: Benchmarking Language-oriented Task Planners for Embodied Agents
Score-based generative models break the curse of dimensionality in learning a family of sub-Gaussian distributions
Adversarial Training on Purification (AToP): Advancing Both Robustness and Generalization
Course Correcting Koopman Representations
ModernTCN: A Modern Pure Convolution Structure for General Time Series Analysis
Understanding the Robustness of Randomized Feature Defense Against Query-Based Adversarial Attacks
Fine-Tuned Language Models Generate Stable Inorganic Materials as Text
SYMBOL: Generating Flexible Black-Box Optimizers through Symbolic Equation Learning
On Error Propagation of Diffusion Models
R&B: Region and Boundary Aware Zero-shot Grounded Text-to-image Generation
Bayesian Coreset Optimization for Personalized Federated Learning
Beyond Spatio-Temporal Representations: Evolving Fourier Transform for Temporal Graphs
Soft Mixture Denoising: Beyond the Expressive Bottleneck of Diffusion Models
Self-supervised Pocket Pretraining via Protein Fragment-Surroundings Alignment
A Benchmark for Learning to Translate a New Language from One Grammar Book
BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks
Flow Matching on General Geometries
Mixture-of-Experts Meets Instruction Tuning: A Winning Combination for Large Language Models
Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data
DreamClean: Restoring Clean Image Using Deep Diffusion Prior
Quick-Tune: Quickly Learning Which Pretrained Model to Finetune and How
Reasoning with Latent Diffusion in Offline Reinforcement Learning
GenSim: Generating Robotic Simulation Tasks via Large Language Models
Adversarial Attacks on Fairness of Graph Neural Networks
Controlling Vision-Language Models for Multi-Task Image Restoration
Towards Robust Out-of-Distribution Generalization Bounds via Sharpness
DREAM: Dual Structured Exploration with Mixup for Open-set Graph Domain Adaption
Partitioning Message Passing for Graph Fraud Detection
Measuring Vision-Language STEM Skills of Neural Models
Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding
AutoCast++: Enhancing World Event Prediction with Zero-shot Ranking-based Context Retrieval
Stylized Offline Reinforcement Learning: Extracting Diverse High-Quality Behaviors from Heterogeneous Datasets
VFLAIR: A Research Library and Benchmark for Vertical Federated Learning
Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning
Learning Thresholds with Latent Values and Censored Feedback
Guess & Sketch: Language Model Guided Transpilation
Deep Reinforcement Learning for Modelling Protein Complexes
Leveraging Hyperbolic Embeddings for Coarse-to-Fine Robot Design
Large-Vocabulary 3D Diffusion Model with Transformer
Understanding Expressivity of GNN in Rule Learning
Skip-Attention: Improving Vision Transformers by Paying Less Attention
Solving High Frequency and Multi-Scale PDEs with Gaussian Processes
ODE Discovery for Longitudinal Heterogeneous Treatment Effects Inference
Differentiable Learning of Generalized Structured Matrices for Efficient Deep Neural Networks
Compose and Conquer: Diffusion-Based 3D Depth Aware Composable Image Synthesis
Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning
Reward Model Ensembles Help Mitigate Overoptimization
Learning Robust Generalizable Radiance Field with Visibility and Feature Augmented Point Representation
An Image Is Worth 1000 Lies: Transferability of Adversarial Images across Prompts on Vision-Language Models
Fiber Monte Carlo
NeRM: Learning Neural Representations for High-Framerate Human Motion Synthesis
Pooling Image Datasets with Multiple Covariate Shift and Imbalance
NuwaDynamics: Discovering and Updating in Causal Spatio-Temporal Modeling
Noise Map Guidance: Inversion with Spatial Context for Real Image Editing
Fair and Efficient Contribution Valuation for Vertical Federated Learning
ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation
The Expressive Power of Low-Rank Adaptation
SocioDojo: Building Lifelong Analytical Agents with Real-world Text and Time Series
Automatic Functional Differentiation in JAX
Neural SDF Flow for 3D Reconstruction of Dynamic Scenes
A Poincaré Inequality and Consistency Results for Signal Sampling on Large Graphs
$\mathcal{B}$-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis
Continuous Field Reconstruction from Sparse Observations with Implicit Neural Networks
Smooth ECE: Principled Reliability Diagrams via Kernel Smoothing
Transformer-VQ: Linear-Time Transformers via Vector Quantization
Faithful Rule Extraction for Differentiable Rule Learning Models
Variational Inference for SDEs Driven by Fractional Noise
What does the Knowledge Neuron Thesis Have to do with Knowledge?
Progressive Fourier Neural Representation for Sequential Video Compilation
Space Group Constrained Crystal Generation
Hybrid Directional Graph Neural Network for Molecules
Intriguing Properties of Generative Classifiers
Pushing Boundaries: Mixup's Influence on Neural Collapse
BioBridge: Bridging Biomedical Foundation Models via Knowledge Graphs
Compressing Latent Space via Least Volume
Octavius: Mitigating Task Interference in MLLMs via LoRA-MoE
Towards Lossless Dataset Distillation via Difficulty-Aligned Trajectory Matching
Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency
Neural Contractive Dynamical Systems
Language Model Beats Diffusion - Tokenizer is key to visual generation
Information Bottleneck Analysis of Deep Neural Networks via Lossy Compression
GPAvatar: Generalizable and Precise Head Avatar from Image(s)
Variance-aware Regret Bounds for Stochastic Contextual Dueling Bandits
Threshold-Consistent Margin Loss for Open-World Deep Metric Learning
Understanding Certified Training with Interval Bound Propagation
ZeRO++: Extremely Efficient Collective Communication for Large Model Training
Towards domain-invariant Self-Supervised Learning with Batch Styles Standardization
On the Expressivity of Objective-Specification Formalisms in Reinforcement Learning
Demystifying Embedding Spaces using Large Language Models
CausalLM is not optimal for in-context learning
Grounding Language Plans in Demonstrations Through Counterfactual Perturbations
Efficient Subgraph GNNs by Learning Effective Selection Policies
Evaluating the Zero-shot Robustness of Instruction-tuned Language Models
Crystalformer: Infinitely Connected Attention for Periodic Structure Encoding
Diverse Projection Ensembles for Distributional Reinforcement Learning
Transformer-Modulated Diffusion Models for Probabilistic Multivariate Time Series Forecasting
Improving Generalization of Alignment with Human Preferences through Group Invariant Learning
Efficient Dynamics Modeling in Interactive Environments with Koopman Theory
Unveiling the Pitfalls of Knowledge Editing for Large Language Models
Enabling Lanuguage Models to Implicitly Learn Self-Improvement
Diffusion in Diffusion: Cyclic One-Way Diffusion for Text-Vision-Conditioned Generation
Zero and Few-shot Semantic Parsing with Ambiguous Inputs
Reward-Free Curricula for Training Robust World Models
PORF: POSE RESIDUAL FIELD FOR ACCURATE NEURAL SURFACE RECONSTRUCTION
Understanding when Dynamics-Invariant Data Augmentations Benefit Model-free Reinforcement Learning Updates
DeepZero: Scaling Up Zeroth-Order Optimization for Deep Model Training
Boosting of Thoughts: Trial-and-Error Problem Solving with Large Language Models
Unified Human-Scene Interaction via Prompted Chain-of-Contacts
Tool-Augmented Reward Modeling
Latent 3D Graph Diffusion
Optimal criterion for feature learning of two-layer linear neural network in high dimensional interpolation regime
Decoupling Weighing and Selecting for Integrating Multiple Graph Pre-training Tasks
Towards Enhancing Time Series Contrastive Learning: A Dynamic Bad Pair Mining Approach
GAFormer: Enhancing Timeseries Transformers Through Group-Aware Embeddings
Prioritized Soft Q-Decomposition for Lexicographic Reinforcement Learning
A Simple Interpretable Transformer for Fine-Grained Image Classification and Analysis
Raidar: geneRative AI Detection viA Rewriting
Facing the Elephant in the Room: Visual Prompt Tuning or Full finetuning?
Quantifying the Sensitivity of Inverse Reinforcement Learning to Misspecification
Effective and Efficient Federated Tree Learning on Hybrid Data
Expressivity of ReLU-Networks under Convex Relaxations
A Topological Perspective on Demystifying GNN-Based Link Prediction Performance
Boosting the Adversarial Robustness of Graph Neural Networks: An OOD Perspective
Approximately Piecewise E(3) Equivariant Point Networks
REFACTOR: Learning to Extract Theorems from Proofs
#InsTag: Instruction Tagging for Analyzing Supervised Fine-tuning of Large Language Models
Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models
Curriculum reinforcement learning for quantum architecture search under hardware errors
Harnessing Joint Rain-/Detail-aware Representations to Eliminate Intricate Rains
SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning
Making Retrieval-Augmented Language Models Robust to Irrelevant Context
Addressing Signal Delay in Deep Reinforcement Learning
Unsupervised Pretraining for Fact Verification by Language Model Distillation
Improving Intrinsic Exploration by Creating Stationary Objectives
Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization
Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularization
Adversarial Imitation Learning via Boosting
On the Variance of Neural Network Training with respect to Test Sets and Distributions
Leveraging augmented-Lagrangian techniques for differentiating over infeasible quadratic programs in machine learning
GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction
Time Travel in LLMs: Tracing Data Contamination in Large Language Models
Generating Images with 3D Annotations Using Diffusion Models
Motion Guidance: Diffusion-Based Image Editing with Differentiable Motion Estimators
RECOMBINER: Robust and Enhanced Compression with Bayesian Implicit Neural Representations
Prototypical Information Bottlenecking and Disentangling for Multimodal Cancer Survival Prediction
Towards Green AI in Fine-tuning Large Language Models via Adaptive Backpropagation
Order-Preserving GFlowNets
Tangent Transformers for Composition,Privacy and Removal
Look, Remember and Reason: Grounded Reasoning in Videos with Language Models
Meaning Representations from Trajectories in Autoregressive Models
Text2Reward: Reward Shaping with Language Models for Reinforcement Learning
Copula Conformal prediction for multi-step time series prediction
Analyzing and Mitigating Object Hallucination in Large Vision-Language Models
On the Stability of Iterative Retraining of Generative Models on their own Data
A representation-learning game for classes of prediction tasks
Query-Policy Misalignment in Preference-Based Reinforcement Learning
Time-LLM: Time Series Forecasting by Reprogramming Large Language Models
PTaRL: Prototype-based Tabular Representation Learning via Space Calibration
Decoupling regularization from the action space
CALICO: Self-Supervised Camera-LiDAR Contrastive Pre-training for BEV Perception
Leveraging Low-Rank and Sparse Recurrent Connectivity for Robust Closed-Loop Control
Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Models
Self-supervised Representation Learning from Random Data Projectors
3D-Aware Hypothesis & Verification for Generalizable Relative Object Pose Estimation
Safe RLHF: Safe Reinforcement Learning from Human Feedback
Large Content And Behavior Models To Understand, Simulate, And Optimize Content And Behavior
Causal Structure Recovery with Latent Variables under Milder Distributional and Graphical Assumptions
Learning Hierarchical World Models with Adaptive Temporal Abstractions from Discrete Latent Dynamics
A Branching Decoder for Set Generation
Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps
ARM: Refining Multivariate Forecasting with Adaptive Temporal-Contextual Learning
Scalable Diffusion for Materials Generation
Information Retention via Learning Supplemental Features
Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages
Augmenting Transformers with Recursively Composed Multi-grained Representations
Identifiable Latent Polynomial Causal Models through the Lens of Change
Manifold Preserving Guided Diffusion
Graph Lottery Ticket Automated
Complex priors and flexible inference in recurrent circuits with dendritic nonlinearities
A Study of Bayesian Neural Network Surrogates for Bayesian Optimization
Adaptive Regret for Bandits Made Possible: Two Queries Suffice
AdaMerging: Adaptive Model Merging for Multi-Task Learning
Ensemble Distillation for Unsupervised Constituency Parsing
CAS: A Probability-Based Approach for Universal Condition Alignment Score
Efficient Continual Finite-Sum Minimization
Neural Atoms: Propagating Long-range Interaction in Molecular Graphs through Efficient Communication Channel
Zero Bubble (Almost) Pipeline Parallelism
PRIME: Prioritizing Interpretability in Failure Mode Extraction
Input-gradient space particle inference for neural network ensembles
SF(DA)$^2$: Source-free Domain Adaptation Through the Lens of Data Augmentation
Structural Estimation of Partially Observed Linear Non-Gaussian Acyclic Model: A Practical Approach with Identifiability
Ferret: Refer and Ground Anything Anywhere at Any Granularity
MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models
Quantifying Network Similarity using Graph Cumulants
Self-Supervised Contrastive Learning for Long-term Forecasting
Learning to Solve Bilevel Programs with Binary Tender
Towards Best Practices of Activation Patching in Language Models: Metrics and Methods
AirPhyNet: Harnessing Physics-Guided Neural Networks for Air Quality Prediction
Scale-Adaptive Diffusion Model for Complex Sketch Synthesis
On the Over-Memorization During Natural, Robust and Catastrophic Overfitting
Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation
Making RL with Preference-based Feedback Efficient via Randomization
Masked Completion via Structured Diffusion with White-Box Transformers
f-FERM: A Scalable Framework for Robust Fair Empirical Risk Minimization
Robust Model-Based Optimization for Challenging Fitness Landscapes
Towards Unified Multi-Modal Personalization: Large Vision-Language Models for Generative Recommendation and Beyond
Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting
EasyTPP: Towards Open Benchmarking Temporal Point Processes
Rethinking CNN’s Generalization to Backdoor Attack from Frequency Domain
A Hierarchical Bayesian Model for Few-Shot Meta Learning
H2O-SDF: Two-phase Learning for 3D Indoor Reconstruction using Object Surface Fields
ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving
Language Model Detectors Are Easily Optimized Against
LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed Prompts
ImagenHub: Standardizing the evaluation of conditional image generation models
Seeking Neural Nuggets: Knowledge Transfer in Large Language Models from a Parametric Perspective
Estimating Conditional Mutual Information for Dynamic Feature Selection
Interpretable Diffusion via Information Decomposition
Label-Agnostic Forgetting: A Supervision-Free Unlearning in Deep Models
Spectrally Transformed Kernel Regression
Leveraging Optimization for Adaptive Attacks on Image Watermarks
CNN Kernels Can Be the Best Shapelets
Fast Equilibrium of SGD in Generic Situations
Modelling complex vector drawings with stroke-clouds
FOSI: Hybrid First and Second Order Optimization
Constructing Adversarial Examples for Vertical Federated Learning: Optimal Client Corruption through Multi-Armed Bandit
Spatially-Aware Transformers for Embodied Agents
3D Reconstruction with Generalizable Neural Fields using Scene Priors
Lagrangian Flow Networks for Conservation Laws
Denoising Diffusion Bridge Models
Intelligent Switching for Reset-Free RL
VeRA: Vector-based Random Matrix Adaptation
An Emulator for Fine-tuning Large Language Models using Small Language Models
Towards Imitation Learning to Branch for MIP: A Hybrid Reinforcement Learning based Sample Augmentation Approach
V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection
Generative Modeling with Phase Stochastic Bridge
RobustTSF: Towards Theory and Design of Robust Time Series Forecasting with Anomalies
Bandits Meet Mechanism Design to Combat Clickbait in Online Recommendation
SEABO: A Simple Search-Based Method for Offline Imitation Learning
The Cost of Scaling Down Large Language Models: Reducing Model Size Affects Memory before In-context Learning
Improved Efficiency Based on Learned Saccade and Continuous Scene Reconstruction From Foveated Visual Sampling
MCM: Masked Cell Modeling for Anomaly Detection in Tabular Data
Learning interpretable control inputs and dynamics underlying animal locomotion
Recursive Generalization Transformer for Image Super-Resolution
AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents
CLIP-MUSED: CLIP-Guided Multi-Subject Visual Neural Information Semantic Decoding
Vision-Language Foundation Models as Effective Robot Imitators
OctoPack: Instruction Tuning Code Large Language Models
Concept Bottleneck Generative Models
Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering
Estimating Shape Distances on Neural Representations with Limited Samples
Improving Convergence and Generalization Using Parameter Symmetries
Revisiting Deep Audio-Text Retrieval Through the Lens of Transportation
Tailoring Self-Rationalizers with Multi-Reward Distillation
Text-to-3D with Classifier Score Distillation
Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learning
DQ-LoRe: Dual Queries with Low Rank Approximation Re-ranking for In-Context Learning
Dirichlet-based Per-Sample Weighting by Transition Matrix for Noisy Label Learning
Beyond Memorization: Violating Privacy via Inference with Large Language Models
Local Composite Saddle Point Optimization
Pre-Training Goal-based Models for Sample-Efficient Reinforcement Learning
Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization
A unique M-pattern for micro-expression spotting in long videos
Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting
Internal Cross-layer Gradients for Extending Homogeneity to Heterogeneity in Federated Learning
Entity-Centric Reinforcement Learning for Object Manipulation from Pixels
Rethinking Channel Dimensions to Isolate Outliers for Low-bit Weight Quantization of Large Language Models
Off-Policy Primal-Dual Safe Reinforcement Learning
A Mutual Information Perspective on Federated Contrastive Learning
Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations
Tractable MCMC for Private Learning with Pure and Gaussian Differential Privacy
Repeated Random Sampling for Minimizing the Time-to-Accuracy of Learning
Communication-Efficient Federated Non-Linear Bandit Optimization
Demystifying Linear MDPs and Novel Dynamics Aggregation Framework
Leveraging Unpaired Data for Vision-Language Generative Models via Cycle Consistency
Provable Robust Watermarking for AI-Generated Text
FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing
ASMR: Activation-Sharing Multi-Resolution Coordinate Networks for Efficient Inference
AuG-KD: Anchor-Based Mixup Generation for Out-of-Domain Knowledge Distillation
Debiasing Attention Mechanism in Transformer without Demographics
SKILL-MIX: a Flexible and Expandable Family of Evaluations for AI Models
Multimodal Patient Representation Learning with Missing Modalities and Labels
Multi-modal Gaussian Process Variational Autoencoders for Neural and Behavioral Data
Stable Neural Stochastic Differential Equations in Analyzing Irregular Time Series Data
GraphChef: Decision-Tree Recipes to Explain Graph Neural Networks
Vanishing Gradients in Reinforcement Finetuning of Language Models
Task structure and nonlinearity jointly determine learned representational geometry
Locality Sensitive Sparse Encoding for Learning World Models Online
Towards Generative Abstract Reasoning: Completing Raven’s Progressive Matrix via Rule Abstraction and Selection
Deep Generative Clustering with Multimodal Diffusion Variational Autoencoders
PINNsFormer: A Transformer-Based Framework For Physics-Informed Neural Networks
Statistical Perspective of Top-K Sparse Softmax Gating Mixture of Experts
Learning Hierarchical Image Segmentation For Recognition and By Recognition
Oracle Efficient Algorithms for Groupwise Regret
FasterViT: Fast Vision Transformers with Hierarchical Attention
Soft Contrastive Learning for Time Series
Towards Understanding Factual Knowledge of Large Language Models
Alice Benchmarks: Connecting Real World Re-Identification with the Synthetic
HoloNets: Spectral Convolutions do extend to Directed Graphs
Mastering Memory Tasks with World Models
Orbit-Equivariant Graph Neural Networks
The Reversal Curse: LLMs trained on “A is B” fail to learn “B is A”
CIFAR-10-Warehouse: Broad and More Realistic Testbeds in Model Generalization Analysis
Fast Value Tracking for Deep Reinforcement Learning
Interpretable Sparse System Identification: Beyond Recent Deep Learning Techniques on Time-Series Prediction
Image Clustering Conditioned on Text Criteria
QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models
Generalized Schrödinger Bridge Matching
Certified Adversarial Robustness for Rate Encoded Spiking Neural Networks
Implicit bias of SGD in $L_2$-regularized linear DNNs: One-way jumps from high to low rank
We use cookies to store which papers have been visited.
I agree
Successful Page Load
ICLR uses cookies to remember that you are logged in. By using our websites, you agree to the placement of cookies.
Our Privacy Policy »
Accept Cookies