International Conference on Learning Representations (ICLR) - 2023

Conference Proceedings:

Key: PC - Pseudocode, OSC - Open Source Code, OSD - Open Datasets, DS - Dataset Splits, HS - Hardware Specification, SD - Software Dependencies, ES - Experiment Setup

$O(T^{-1})$ Convergence of Optimistic-Follow-the-Regularized-Leader in Two-Player Zero-Sum Markov Games 1
$\Lambda$-DARTS: Mitigating Performance Collapse by Harmonizing Operation Selection among Cells 5
$\mathcal{O}$-GNN: incorporating ring priors into molecular modeling 4
$\mathrm{SE}(3)$-Equivariant Attention Networks for Shape Reconstruction in Function Space 2
$\mathscr{N}$-WL: A New Hierarchy of Expressivity for Graph Neural Networks 5
$\rm A^2Q$: Aggregation-Aware Quantization for Graph Neural Networks 7
$k$NN Prompting: Beyond-Context Learning with Calibration-Free Nearest Neighbor Inference 3
(Certified!!) Adversarial Robustness for Free! 6
3D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Prediction 5
3D Segmenter: 3D Transformer based Semantic Segmentation via 2D Panoramic Distillation 5
3D UX-Net: A Large Kernel Volumetric ConvNet Modernizing Hierarchical Transformer for Medical Image Segmentation 5
3D generation on ImageNet 4
A CMDP-within-online framework for Meta-Safe Reinforcement Learning 3
A Call to Reflect on Evaluation Practices for Failure Detection in Image Classification 5
A Closer Look at Model Adaptation using Feature Distortion and Simplicity Bias 4
A Control-Centric Benchmark for Video Prediction 5
A Convergent Single-Loop Algorithm for Relaxation of Gromov-Wasserstein in Graph Data 4
A Differential Geometric View and Explainability of GNN on Evolving Graphs 3
A GNN-Guided Predict-and-Search Framework for Mixed-Integer Linear Programming 7
A General Framework For Proving The Equivariant Strong Lottery Ticket Hypothesis 3
A General Framework for Sample-Efficient Function Approximation in Reinforcement Learning 2
A General Rank Preserving Framework for Asymmetric Image Retrieval 5
A Graph Neural Network Approach to Automated Model Building in Cryo-EM Maps 5
A Higher Precision Algorithm for Computing the $1$-Wasserstein Distance 2
A Holistic View of Label Noise Transition Matrix in Deep Learning and Beyond 4
A Kernel Perspective of Skip Connections in Convolutional Networks 2
A Laplace-inspired Distribution on SO(3) for Probabilistic Rotation Estimation 3
A Learning Based Hypothesis Test for Harmful Covariate Shift 5
A Message Passing Perspective on Learning Dynamics of Contrastive Learning 3
A Minimalist Dataset for Systematic Generalization of Perception, Syntax, and Semantics 5
A Mixture-of-Expert Approach to RL-based Dialogue Management 2
A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning 5
A Multi-Grained Self-Interpretable Symbolic-Neural Model For Single/Multi-Labeled Text Classification 5
A Neural Mean Embedding Approach for Back-door and Front-door Adjustment 3
A Non-Asymptotic Analysis of Oversmoothing in Graph Neural Networks 3
A Non-monotonic Self-terminating Language Model 3
A Primal-Dual Framework for Transformers and Neural Networks 5
A Self-Attention Ansatz for Ab-initio Quantum Chemistry 4
A Simple Approach for Visual Room Rearrangement: 3D Mapping and Semantic Search 6
A Simple Yet Powerful Deep Active Learning With Snapshots Ensembles 5
A Stable and Scalable Method for Solving Initial Value PDEs with Neural Networks 3
A Statistical Framework for Personalized Federated Learning and Estimation: Theory, Algorithms, and Privacy 4
A System for Morphology-Task Generalization via Unified Representation and Behavior Distillation 5
A Theoretical Framework for Inference and Learning in Predictive Coding Networks 3
A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity 4
A Theory of Dynamic Benchmarks 3
A Time Series is Worth 64 Words: Long-term Forecasting with Transformers 3
A Unified Algebraic Perspective on Lipschitz Neural Networks 4
A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games 4
A Unified Framework for Soft Threshold Pruning 4
A VAE for Transformers with Nonparametric Variational Information Bottleneck 5
A View From Somewhere: Human-Centric Face Representations 5
A critical look at the evaluation of GNNs under heterophily: Are we really making progress? 4
A framework for benchmarking Class-out-of-distribution detection and its application to ImageNet 6
A law of adversarial risk, interpolation, and label noise 2
A new characterization of the edge of stability based on a sharpness measure aware of batch gradient distribution 3
A probabilistic framework for task-aligned intra- and inter-area neural manifold estimation 4
A theoretical study of inductive biases in contrastive learning 2
A view of mini-batch SGD via generating functions: conditions of convergence, phase transitions, benefit from negative momenta. 4
AANG : Automating Auxiliary Learning 6
ACMP: Allen-Cahn Message Passing with Attractive and Repulsive Forces for Graph Neural Networks 6
AE-FLOW: Autoencoders with Normalizing Flows for Medical Images Anomaly Detection 3
AGRO: Adversarial discovery of error-prone Groups for Robust Optimization 5
AIM: Adapting Image Models for Efficient Video Action Recognition 6
Accelerated Single-Call Methods for Constrained Min-Max Optimization 4
Accelerating Guided Diffusion Sampling with Splitting Numerical Methods 4
Accelerating Hamiltonian Monte Carlo via Chebyshev Integration Time 4
Accurate Bayesian Meta-Learning by Accurate Task Posterior Inference 4
Accurate Image Restoration with Attention Retractable Transformer 4
Accurate Neural Training with 4-bit Matrix Multiplications at Standard Formats 3
Achieve the Minimum Width of Neural Networks for Universal Approximation 0
Achieving Near-Optimal Individual Regret & Low Communications in Multi-Agent Bandits 3
Achieving Sub-linear Regret in Infinite Horizon Average Reward Constrained MDP with Linear Function Approximation 2
Actionable Neural Representations: Grid Cells from Minimal Constraints 2
Active Image Indexing 4
Active Learning for Object Detection with Evidential Deep Learning and Hierarchical Uncertainty Aggregation 7
Active Learning in Bayesian Neural Networks with Balanced Entropy Learning Principle 5
Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning 6
Adaptive Optimization in the $\infty$-Width Limit 2
Adaptive Robust Evidential Optimization For Open Set Detection from Imbalanced Data 5
Addressing Parameter Choice Issues in Unsupervised Domain Adaptation by Aggregation 7
Advancing Radiograph Representation Learning with Masked Record Modeling 6
Adversarial Attacks on Adversarial Bandits 1
Adversarial Diversity in Hanabi 4
Adversarial Imitation Learning with Preferences 3
Adversarial Training of Self-supervised Monocular Depth Estimation against Physical-World Attacks 5
Agent-based Graph Neural Networks 4
Agnostic Learning of General ReLU Activation Using Gradient Descent 1
Agree to Disagree: Diversity through Disagreement for Better Transferability 6
Aligning Model and Macaque Inferior Temporal Cortex Representations Improves Model-to-Human Behavioral Alignment and Adversarial Robustness 4
Almost Linear Constant-Factor Sketching for $\ell_1$ and Logistic Regression 4
Alternating Differentiation for Optimization Layers 5
Amortised Invariance Learning for Contrastive Self-Supervision 5
An Adaptive Policy to Employ Sharpness-Aware Minimization 4
An Additive Instance-Wise Approach to Multi-class Model Interpretation 4
An Equal-Size Hard EM Algorithm for Diverse Dialogue Generation 5
An Exact Poly-Time Membership-Queries Algorithm for Extracting a Three-Layer ReLU Network 1
An Extensible Multi-modal Multi-task Object Dataset with Materials 4
An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion 4
An efficient encoder-decoder architecture with top-down attention for speech separation 5
Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning 4
Analogy-Forming Transformers for Few-Shot 3D Parsing 6
Analyzing Tree Architectures in Ensembles via Neural Tangent Kernel 5
Anamnesic Neural Differential Equations with Orthogonal Polynomial Projections 3
Anisotropic Message Passing: Graph Neural Networks with Directional and Long-Range Interactions 6
Anti-Symmetric DGN: a stable architecture for Deep Graph Networks 5
Any-scale Balanced Samplers for Discrete Space 5
AnyDA: Anytime Domain Adaptation 6
Approximate Bayesian Inference with Stein Functional Variational Gradient Descent 5
Approximate Nearest Neighbor Search through Modern Error-Correcting Codes 4
Approximate Vanishing Ideal Computations at Scale 6
Approximation and non-parametric estimation of functions over high-dimensional spheres via deep ReLU networks 0
ArCL: Enhancing Contrastive Learning with Augmentation-Robust Representations 3
Arbitrary Virtual Try-on Network: Characteristics Representation and Trade-off between Body and Clothing 4
Are More Layers Beneficial to Graph Transformers? 3
Artificial Neuronal Ensembles with Learned Context Dependent Gating 3
Ask Me Anything: A simple strategy for prompting language models 5
Associative Memory Augmented Asynchronous Spatiotemporal Representation Learning for Event-based Perception 5
Asymptotic Instance-Optimal Algorithms for Interactive Decision Making 1
Asynchronous Distributed Bilevel Optimization 4
Asynchronous Gradient Play in Zero-Sum Multi-agent Games 2
AudioGen: Textually Guided Audio Generation 3
Augmentation Component Analysis: Modeling Similarity via the Augmentation Overlaps 6
Augmentation with Projection: Towards an Effective and Efficient Data Augmentation Paradigm for Distillation 6
Auto-Encoding Goodness of Fit 5
AutoGT: Automated Graph Transformer Architecture Search 5
AutoTransfer: AutoML with Knowledge Transfer - An Application to Graph Neural Networks 6
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning? 4
Automated Data Augmentations for Graph Classification 5
Automatic Chain of Thought Prompting in Large Language Models 4
Automating Nearest Neighbor Search Configuration with Constrained Optimization 5
Autoregressive Conditional Neural Processes 6
Average Sensitivity of Decision Tree Learning 4
Avoiding spurious correlations via logit correction 5
BALTO: fast tensor program optimization with diversity-based active learning 4
BAYES RISK CTC: CONTROLLABLE CTC ALIGNMENT IN SEQUENCE-TO-SEQUENCE TASKS 5
BC-IRL: Learning Generalizable Reward Functions from Demonstrations 3
BEEF: Bi-Compatible Class-Incremental Learning via Energy-Based Expansion and Fusion 4
BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object Detection 5
BSTT: A Bayesian Spatial-Temporal Transformer for Sleep Staging 4
Backpropagation at the Infinitesimal Inference Limit of Energy-Based Models: Unifying Predictive Coding, Equilibrium Propagation, and Contrastive Hebbian Learning 4
Backpropagation through Combinatorial Algorithms: Identity with Projection Works 5
Backstepping Temporal Difference Learning 3
Bag of Tricks for Unsupervised Text-to-Speech 5
Basic Binary Convolution Unit for Binarized Image Restoration Network 4
Batch Multivalid Conformal Prediction 5
Bayes-MIL: A New Probabilistic Perspective on Attention-based Multiple Instance Learning for Whole Slide Images 4
Bayesian Oracle for bounding information gain in neural encoding models 3
Become a Proficient Player with Limited Data through Watching Pure Videos 4
Behavior Prior Representation learning for Offline Reinforcement Learning 4
Behavior Proximal Policy Optimization 4
Behind the Scenes of Gradient Descent: A Trajectory Analysis via Basis Function Decomposition 5
Benchmarking Constraint Inference in Inverse Reinforcement Learning 5
Benchmarking Offline Reinforcement Learning on Real-Robot Hardware 3
Benign Overfitting in Classification: Provably Counter Label Noise with Larger Models 3
Better Generative Replay for Continual Federated Learning 3
Better Teacher Better Student: Dynamic Prior Knowledge for Knowledge Distillation 4
Betty: An Automatic Differentiation Library for Multilevel Optimization 5
Beyond Lipschitz: Sharp Generalization and Excess Risk Bounds for Full-Batch GD 0
Beyond calibration: estimating the grouping loss of modern neural networks 5
Bi-level Physics-Informed Neural Networks for PDE Constrained Optimization using Broyden's Hypergradients 4
Bias Propagation in Federated Learning 5
Bidirectional Language Models Are Also Few-shot Learners 3
BigVGAN: A Universal Neural Vocoder with Large-Scale Training 5
Binding Language Models in Symbolic Languages 3
Bispectral Neural Networks 5
Bit-Pruning: A Sparse Multiplication-Less Dot-Product 3
Bitrate-Constrained DRO: Beyond Worst Case Robustness To Unknown Group Shifts 4
Block and Subword-Scaling Floating-Point (BSFP) : An Efficient Non-Uniform Quantization For Low Precision Inference 4
Blurring Diffusion Models 3
Boosting Adversarial Transferability using Dynamic Cues 5
Boosting Causal Discovery via Adaptive Sample Reweighting 5
Boosting Multiagent Reinforcement Learning via Permutation Invariant and Permutation Equivariant Networks 5
Boosting the Cycle Counting Power of Graph Neural Networks with I$^2$-GNNs 4
Bort: Towards Explainable Neural Networks with Bounded Orthogonal Constraint 5
Brain-like representational straightening of natural movies in robust feedforward neural networks 2
BrainBERT: Self-supervised representation learning for intracranial recordings 4
Breaking Correlation Shift via Conditional Invariant Regularizer 4
Bridge the Inference Gaps of Neural Processes via Expectation Maximization 5
Bridging the Gap between ANNs and SNNs by Calibrating Offset Spikes 5
Bridging the Gap to Real-World Object-Centric Learning 6
Broken Neural Scaling Laws 4
Budgeted Training for Vision Transformer 3
Building Normalizing Flows with Stochastic Interpolants 3
Building a Subspace of Policies for Scalable Continual Learning 5
CANIFE: Crafting Canaries for Empirical Privacy Measurement in Federated Learning 7
CASR: Generating Complex Sequences with Autoregressive Self-Boost Refinement 6
CFlowNets: Continuous Control with Generative Flow Networks 4
CLARE: Conservative Model-Based Reward Learning for Offline Inverse Reinforcement Learning 6
CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks 6
CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Alignment 5
CLIPSep: Learning Text-queried Sound Separation with Noisy Unlabeled Videos 3
CO3: Cooperative Unsupervised 3D Representation Learning for Autonomous Driving 3
CROM: Continuous Reduced-Order Modeling of PDEs Using Implicit Neural Representations 4
CUDA: Curriculum of Data Augmentation for Long-tailed Recognition 4
CUTS: Neural Causal Discovery from Irregular Time-Series Data 5
Calibrating Sequence likelihood Improves Conditional Language Generation 4
Calibrating Transformers via Sparse Gaussian Processes 5
Calibrating the Rigged Lottery: Making All Tickets Reliable 4
Calibration Matters: Tackling Maximization Bias in Large-scale Advertising Recommendation Systems 5
Can Agents Run Relay Race with Strangers? Generalization of RL to Out-of-Distribution Trajectories 4
Can BERT Refrain from Forgetting on Sequential Tasks? A Probing Study 3
Can CNNs Be More Robust Than Transformers? 4
Can Neural Networks Learn Implicit Logic from Physical Reasoning? 0
Can We Faithfully Represent Absence States to Compute Shapley Values on a DNN? 4
Can We Find Nash Equilibria at a Linear Rate in Markov Games? 2
Can discrete information extraction prompts generalize across language models? 3
Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries 5
Capturing the Motion of Every Joint: 3D Human Pose and Shape Estimation with Independent Tokens 4
Causal Balancing for Domain Generalization 6
Causal Confusion and Reward Misidentification in Preference-Based Reward Learning 4
Causal Estimation for Text Data with (Apparent) Overlap Violations 3
Causal Imitation Learning via Inverse Reinforcement Learning 3
Causal Reasoning in the Presence of Latent Confounders via Neural ADMG Learning 3
Causal Representation Learning for Instantaneous and Temporal Effects in Interactive Systems 6
Causality Compensated Attention for Contextual Biased Visual Recognition 3
Certifiably Robust Policy Learning against Adversarial Multi-Agent Communication 5
Certified Defences Against Adversarial Patch Attacks on Semantic Segmentation 5
Certified Training: Small Boxes are All You Need 2
Characteristic Neural Ordinary Differential Equation 5
Characterizing intrinsic compositionality in transformers with Tree Projections 4
Characterizing the Influence of Graph Elements 3
Characterizing the spectrum of the NTK via a power series expansion 3
Chasing All-Round Graph Representation Robustness: Model, Training, and Optimization 4
Cheap Talk Discovery and Utilization in Multi-Agent Reinforcement Learning 4
ChiroDiff: Modelling chirographic data with Diffusion Models 4
ChordMixer: A Scalable Neural Attention Model for Sequences with Different Length 5
Choreographer: Learning and Adapting Skills in Imagination 6
CircNet: Meshing 3D Point Clouds with Circumcenter Detection 3
CktGNN: Circuit Graph Neural Network for Electronic Design Automation 4
Classically Approximating Variational Quantum Machine Learning with Random Fourier Features 4
Clean-image Backdoor: Attacking Multi-label Models with Poisoned Labels Only 2
Clifford Neural Layers for PDE Modeling 4
CoRTX: Contrastive Framework for Real-time Explanation 6
Code Translation with Compiler Representations 3
CodeBPE: Investigating Subtokenization Options for Large Language Model Pretraining on Source Code 4
CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis 4
CodeT: Code Generation with Generated Tests 3
CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers 4
Collaborative Pure Exploration in Kernel Bandit 3
Combating Exacerbated Heterogeneity for Robust Models in Federated Learning 5
Combinatorial Pure Exploration of Causal Bandits 1
Combinatorial-Probabilistic Trade-Off: P-Values of Community Properties Test in the Stochastic Block Models 1
Competitive Physics Informed Networks 5
Complexity-Based Prompting for Multi-step Reasoning 4
Composing Ensembles of Pre-trained Models via Iterative Consensus 3
Composing Task Knowledge With Modular Successor Feature Approximators 2
Composite Slice Transformer: An Efficient Transformer with Composition of Multi-Scale Multi-Range Attentions 4
Compositional Law Parsing with Latent Random Functions 5
Compositional Prompt Tuning with Motion Cues for Open-vocabulary Video Relation Detection 4
Compositional Semantic Parsing with Large Language Models 3
Compositional Task Representations for Large Language Models 4
Compositionality with Variation Reliably Emerges in Neural Networks 4
Compressing multidimensional weather and climate data into neural networks 4
Computational Language Acquisition with Theory of Mind 4
Computing all Optimal Partial Transports 4
Concept Gradient: Concept-based Interpretation Without Linear Assumption 4
Concept-level Debugging of Part-Prototype Networks 5
Conditional Antibody Design as 3D Equivariant Graph Translation 5
Conditional Positional Encodings for Vision Transformers 6
Confidence Estimation Using Unlabeled Data 4
Confidence-Based Feature Imputation for Graphs with Partially Known Features 7
Confidence-Conditioned Value Functions for Offline Reinforcement Learning 3
Confidential-PROFITT: Confidential PROof of FaIr Training of Trees 6
Conservative Bayesian Model-Based Value Expansion for Offline Policy Optimization 4
Consolidator: Mergable Adapter with Group Connections for Visual Adaptation 4
Constraining Representations Yields Models That Know What They Don't Know 4
Constructive TT-representation of the tensors given as index interaction functions with applications 2
Context-enriched molecule representations improve few-shot drug discovery 5
Contextual Convolutional Networks 5
Contextual Image Masking Modeling via Synergized Contrasting without View Augmentation for Faster and Better Visual Pretraining 5
Contextual bandits with concave rewards, and an application to fair ranking 3
Continual Pre-training of Language Models 3
Continual Transformers: Redundancy-Free Attention for Online Inference 5
Continual Unsupervised Disentangling of Self-Organizing Representations 3
Continual evaluation for lifelong learning: Identifying the stability gap 4
Continuized Acceleration for Quasar Convex Functions in Non-Convex Optimization 2
Continuous PDE Dynamics Forecasting with Implicit Neural Representations 5
Continuous pseudo-labeling from the start 5
Continuous-Discrete Convolution for Geometry-Sequence Modeling in Proteins 6
Continuous-time identification of dynamic state-space models by deep subspace encoding 4
ContraNorm: A Contrastive Learning Perspective on Oversmoothing and Beyond 5
Contrastive Alignment of Vision to Language Through Parameter-Efficient Transfer Learning 5
Contrastive Audio-Visual Masked Autoencoder 5
Contrastive Corpus Attribution for Explaining Representations 4
Contrastive Learning Can Find An Optimal Basis For Approximately View-Invariant Functions 3
Contrastive Learning for Unsupervised Domain Adaptation of Time Series 5
Contrastive Meta-Learning for Partially Observable Few-Shot Learning 6
Copy is All You Need 6
Correlative Information Maximization Based Biologically Plausible Neural Networks for Correlated Source Separation 4
Corrupted Image Modeling for Self-Supervised Visual Pre-Training 4
Coupled Multiwavelet Operator Learning for Coupled Differential Equations 4
Coverage-centric Coreset Selection for High Pruning Rates 6
CrAM: A Compression-Aware Minimizer 7
Critic Sequential Monte Carlo 6
Cross-Layer Retrospective Retrieving via Layer Attention 6
Cross-Level Distillation and Feature Denoising for Cross-Domain Few-Shot Classification 3
Crossformer: Transformer Utilizing Cross-Dimension Dependency for Multivariate Time Series Forecasting 5
Curriculum-based Co-design of Morphology and Control of Voxel-based Soft Robots 4
Cycle to Clique (Cy2C) Graph Neural Network: A Sight to See beyond Neighborhood Aggregation 4
Cycle-consistent Masked AutoEncoder for Unsupervised Domain Generalization 3
D4AM: A General Denoising Framework for Downstream Acoustic Models 5
D4FT: A Deep Learning Approach to Kohn-Sham Density Functional Theory 3
DAG Learning on the Permutahedron 5
DAG Matters! GFlowNets Enhanced Explainer for Graph Neural Networks 4
DASHA: Distributed Nonconvex Optimization with Communication Compression and Optimal Oracle Complexity 6
DAVA: Disentangling Adversarial Variational Autoencoder 4
DBQ-SSD: Dynamic Ball Query for Efficient 3D Object Detection 4
DCI-ES: An Extended Disentanglement Framework with Connections to Identifiability 4
DDM$^2$: Self-Supervised Diffusion MRI Denoising with Generative Diffusion Models 4
DELTA: DEGRADATION-FREE FULLY TEST-TIME ADAPTATION 4
DENSE RGB SLAM WITH NEURAL IMPLICIT MAPS 4
DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systems 5
DFPC: Data flow driven pruning of coupled channels without data. 6
DFlow: Learning to Synthesize Better Optical Flow Datasets via a Differentiable Pipeline 5
DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion 6
DINO as a von Mises-Fisher mixture model 4
DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection 4
DM-NeRF: 3D Scene Geometry Decomposition and Manipulation from 2D Images 4
DamoFD: Digging into Backbone Design on Face Detection 6
Data Continuity Matters: Improving Sequence Modeling with Lipschitz Regularizer 4
Data Valuation Without Training of a Model 5
Data augmentation alone can improve adversarial training 7
Data-Free One-Shot Federated Learning Under Very High Statistical Heterogeneity 4
Dataless Knowledge Fusion by Merging Weights of Language Models 5
Dataset Pruning: Reducing Training Data by Examining Generalization Influence 4
DaxBench: Benchmarking Deformable Object Manipulation with Differentiable Physics 3
De Novo Molecular Generation via Connection-aware Motif Mining 5
DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing 4
DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training 5
DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge Bases 4
Decentralized Optimistic Hyperpolicy Mirror Descent: Provably No-Regret Learning in Markov Games 1
Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models 4
Decision S4: Efficient Sequence-Based RL via State Spaces Layers 4
Decision Transformer under Random Frame Dropping 3
Decompose to Generalize: Species-Generalized Animal Pose Estimation 4
Decomposed Prompting: A Modular Approach for Solving Complex Tasks 5
Decompositional Generation Process for Instance-Dependent Partial Label Learning 5
Deconstructing Distributions: A Pointwise Framework of Learning 2
Decoupled Training for Long-Tailed Classification With Stochastic Representations 6
Deep Declarative Dynamic Time Warping for End-to-End Learning of Alignment Paths 5
Deep Ensembles for Graphs with Higher-order Dependencies 5
Deep Generative Modeling on Limited Data with Regularization by Nontransferable Pre-trained Models 4
Deep Generative Symbolic Regression 6
Deep Learning From Crowdsourced Labels: Coupled Cross-Entropy Minimization, Identifiability, and Regularization 5
Deep Learning meets Nonparametric Regression: Are Weight-Decayed DNNs Locally Adaptive? 2
Deep Learning on Implicit Neural Representations of Shapes 5
Deep Ranking Ensembles for Hyperparameter Optimization 5
Deep Reinforcement Learning for Cost-Effective Medical Diagnosis 5
Deep Transformers without Shortcuts: Modifying Self-attention for Faithful Signal Propagation 3
Deep Variational Implicit Processes 3
Defending against Adversarial Audio via Diffusion Model 5
Deja Vu: Continual Model Generalization for Unseen Domains 3
Delving into Semantic Scale Imbalance 5
Denoising Diffusion Error Correction Codes 5
Denoising Diffusion Samplers 4
Denoising Masked Autoencoders Help Robust Classification 4
DensePure: Understanding Diffusion Models for Adversarial Robustness 5
Depth Separation with Multilayer Mean-Field Networks 2
DepthFL : Depthwise Federated Learning for Heterogeneous Clients 3
Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling 5
Deterministic training of generative autoencoders using invertible layers 6
DexDeform: Dexterous Deformable Object Manipulation with Human Demonstrations and Differentiable Physics 3
DiGress: Discrete Denoising diffusion for graph generation 4
Diagnosing and Rectifying Vision Models using Language 4
Dichotomy of Control: Separating What You Can Control from What You Cannot 5
DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking 7
DiffEdit: Diffusion-based semantic image editing with mask guidance 4
DiffMimic: Efficient Motion Mimicking with Differentiable Physics 5
Differentiable Gaussianization Layers for Inverse Problems Regularized by Deep Generative Models 6
Differentiable Mathematical Programming for Object-Centric Representation Learning 6
Differentially Private $L_2$-Heavy Hitters in the Sliding Window Model 1
Differentially Private Adaptive Optimization with Delayed Preconditioners 4
DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models 5
DiffusER: Diffusion via Edit-based Reconstruction 4
Diffusion Adversarial Representation Learning for Self-supervised Vessel Segmentation 5
Diffusion Models Already Have A Semantic Latent Space 5
Diffusion Models for Causal Discovery via Topological Ordering 4
Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning 5
Diffusion Posterior Sampling for General Noisy Inverse Problems 6
Diffusion Probabilistic Fields 4
Diffusion Probabilistic Modeling of Protein Backbones in 3D for the motif-scaffolding problem 5
Diffusion-GAN: Training GANs with Diffusion 4
Diffusion-based Image Translation using disentangled style and content representation 5
Dilated convolution with learnable spacings 6
Diminishing Return of Value Expansion Methods in Model-Based Reinforcement Learning 4
Direct Embedding of Temporal Network Edges via Time-Decayed Line Graphs 4
Dirichlet-based Uncertainty Calibration for Active Domain Adaptation 6
Discovering Evolution Strategies via Meta-Black-Box Optimization 5
Discovering Generalizable Multi-agent Coordination Skills from Multi-task Offline Data 5
Discovering Informative and Robust Positives for Video Domain Adaptation 4
Discovering Latent Knowledge in Language Models Without Supervision 4
Discovering Policies with DOMiNO: Diversity Optimization Maintaining Near Optimality 3
Discrete Contrastive Diffusion for Cross-Modal Music and Image Generation 5
Discrete Predictor-Corrector Diffusion Models for Image Synthesis 3
Disentanglement of Correlated Factors via Hausdorff Factorized Support 6
Disentanglement with Biological Constraints: A Theory of Functional Cell Types 3
Disentangling Learning Representations with Density Estimation 5
Disentangling the Mechanisms Behind Implicit Regularization in SGD 4
Disparate Impact in Differential Privacy from Gradient Misalignment 7
Distilling Cognitive Backdoor Patterns within an Image 5
Distilling Model Failures as Directions in Latent Space 6
Distributed Differential Privacy in Multi-Armed Bandits 4
Distributed Extra-gradient with Optimal Complexity and Communication Guarantees 5
Distributional Meta-Gradient Reinforcement Learning 3
Distributionally Robust Post-hoc Classifiers under Prior Shifts 4
Distributionally Robust Recourse Action 5
Diversify and Disambiguate: Out-of-Distribution Robustness via Disagreement 4
Divide to Adapt: Mitigating Confirmation Bias for Domain Adaptation of Black-Box Predictors 4
Do We Really Need Complicated Model Architectures For Temporal Networks? 6
DocPrompting: Generating Code by Retrieving the Docs 5
Does Deep Learning Learn to Abstract? A Systematic Probing Framework 5
Does Learning from Decentralized Non-IID Unlabeled Data Benefit from Self Supervision? 5
Does Zero-Shot Reinforcement Learning Exist? 4
Domain Generalisation via Domain Adaptation: An Adversarial Fourier Amplitude Approach 5
Domain Generalization via Heckman-type Selection Models 5
Domain-Indexing Variational Bayes: Interpretable Domain Index for Domain Adaptation 3
Don’t fear the unlabelled: safe semi-supervised learning via debiasing 4
Don’t forget the nullspace! Nullspace occupancy as a mechanism for out of distribution failure 4
Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustness 5
Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs 5
DreamFusion: Text-to-3D using 2D Diffusion 4
DropIT: Dropping Intermediate Tensors for Memory-Efficient DNN Training 6
Dual Algorithmic Reasoning 4
Dual Diffusion Implicit Bridges for Image-to-Image Translation 3
Dual Student Networks for Data-Free Model Stealing 3
DualAfford: Learning Collaborative Visual Affordance for Dual-gripper Manipulation 3
DySR: Adaptive Super-Resolution via Algorithm and System Co-design 5
DynaMS: Dyanmic Margin Selection for Efficient Deep Learning 6
Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning 6
Dynamic Update-to-Data Ratio: Minimizing World Model Overfitting 4
E-CRF: Embedded Conditional Random Field for Boundary-caused Class Weights Confusion in Semantic Segmentation 5
E3Bind: An End-to-End Equivariant Network for Protein-Ligand Docking 4
EA-HAS-Bench: Energy-aware Hyperparameter and Architecture Search Benchmark 6
EAGLE: Large-scale Learning of Turbulent Fluid Dynamics with Mesh Transformers 4
EPISODE: Episodic Gradient Clipping with Periodic Resampled Corrections for Federated Learning with Heterogeneous Data 5
ERL-Re$^2$: Efficient Evolutionary Reinforcement Learning with Shared State Representation and Individual Policy Representation 5
ESCHER: Eschewing Importance Sampling in Games by Computing a History Value Function to Estimate Regret 5
ESD: Expected Squared Difference as a Tuning-Free Trainable Calibration Measure 6
EUCLID: Towards Efficient Unsupervised Reinforcement Learning with Multi-choice Dynamics Model 4
EVA3D: Compositional 3D Human Generation from 2D Image Collections 2
EVC: Towards Real-Time Neural Image Compression with Mask Decay 5
Easy Differentially Private Linear Regression 4
Edge Guided GANs with Contrastive Learning for Semantic Image Synthesis 3
Edgeformers: Graph-Empowered Transformers for Representation Learning on Textual-Edge Networks 6
Editing models with task arithmetic 4
Effective Self-supervised Pre-training on Low-compute Networks without Distillation 4
Effective passive membership inference attacks in federated learning against overparameterized models 3
Effectively Modeling Time Series with Simple Discrete State Spaces 6
Effects of Graph Convolutions in Multi-layer Networks 3
Efficient Attention via Control Variates 6
Efficient Certified Training and Robustness Verification of Neural ODEs 5
Efficient Conditionally Invariant Representation Learning 5
Efficient Deep Reinforcement Learning Requires Regulating Overfitting 5
Efficient Discrete Multi Marginal Optimal Transport Regularization 6
Efficient Edge Inference by Selective Query 6
Efficient Federated Domain Translation 4
Efficient Model Updates for Approximate Unlearning of Graph-Structured Data 6
Efficient Offline Policy Optimization with a Learned Model 5
Efficient Planning in a Compact Latent Action Space 5
Efficient approximation of neural population structure and correlations with probabilistic circuits 4
Efficient recurrent architectures through activity sparsity and sparse back-propagation through time 3
Efficiently Computing Nash Equilibria in Adversarial Team Markov Games 1
Efficiently Controlling Multiple Risks with Pareto Testing 5
Embedding Fourier for Ultra-High-Definition Low-Light Image Enhancement 5
Emergence of Maps in the Memories of Blind Navigation Agents 2
Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task 5
Empowering Graph Representation Learning with Test-Time Graph Transformation 6
Empowering Networks With Scale and Rotation Equivariance Using A Similarity Convolution 3
Encoding Recurrence into Transformers 4
Energy-Based Test Sample Adaptation for Domain Generalization 6
Energy-Inspired Self-Supervised Pretraining for Vision Models 4
Energy-based Out-of-Distribution Detection for Graph Neural Networks 6
Enhancing Meta Learning via Multi-Objective Soft Improvement Functions 5
Enhancing the Inductive Biases of Graph Neural ODE for Modeling Physical Systems 5
Ensuring DNN Solution Feasibility for Optimization Problems with Linear Constraints 4
Equal Improvability: A New Fairness Notion Considering the Long-term Impact 4
EquiMod: An Equivariance Module to Improve Visual Instance Discrimination 4
Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs 5
Equivariance-aware Architectural Optimization of Neural Networks 4
Equivariant Descriptor Fields: SE(3)-Equivariant Energy-Based Models for End-to-End Visual Robotic Manipulation Learning 4
Equivariant Energy-Guided SDE for Inverse Molecular Design 5
Equivariant Hypergraph Diffusion Neural Operators 6
Equivariant Shape-Conditioned Generation of 3D Molecules for Ligand-Based Drug Design 5
Error Sensitivity Modulation based Experience Replay: Mitigating Abrupt Representation Drift in Continual Learning 4
Estimating individual treatment effects under unobserved confounding using binary instruments 6
Eva: Practical Second-order Optimization with Kronecker-vectorized Approximation 6
Evaluating Long-Term Memory in 3D Mazes 3
Evaluating Representations with Readout Model Switching 4
Everybody Needs Good Neighbours: An Unsupervised Locality-based Method for Bias Mitigation 6
Evidential Uncertainty and Diversity Guided Active Learning for Scene Graph Generation 4
Evolve Smoothly, Fit Consistently: Learning Smooth Latent Dynamics For Advection-Dominated Systems 5
Evolving Populations of Diverse RL Agents with MAP-Elites 4
Excess Risk of Two-Layer ReLU Neural Networks in Teacher-Student Settings and its Superiority to Kernel Methods 2
Explaining RL Decisions with Trajectories 4
Explaining Temporal Graph Models through an Explorer-Navigator Framework 6
Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimation 5
Explicitly Minimizing the Blur Error of Variational Autoencoders 2
Exploring Active 3D Object Detection from a Generalization Perspective 5
Exploring Low-Rank Property in Multiple Instance Learning for Whole Slide Image Classification 5
Exploring Temporally Dynamic Data Augmentation for Video Recognition 5
Exploring The Role of Mean Teachers in Self-supervised Masked Auto-Encoders 4
Exploring and Exploiting Decision Boundary Dynamics for Adversarial Robustness 5
Exploring perceptual straightness in learned visual representations 3
Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping 6
Exponential Generalization Bounds with Near-Optimal Rates for $L_q$-Stable Algorithms 1
ExpressivE: A Spatio-Functional Embedding For Knowledge Graph Completion 6
Expressive Monotonic Neural Networks 3
Extracting Robust Models with Uncertain Examples 6
Extreme Q-Learning: MaxEnt RL without Entropy 4
Extremely Simple Activation Shaping for Out-of-Distribution Detection 6
FIFA: Making Fairness More Generalizable in Classifiers Trained on Imbalanced Data 5
FIGARO: Controllable Music Generation using Learned and Expert Features 6
FINDE: Neural Differential Equations for Finding and Preserving Invariant Quantities 5
FIT: A Metric for Model Sensitivity 4
FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning 5
Factorized Fourier Neural Operators 5
FaiREE: fair classification with finite-sample and distribution-free guarantee 5
Fair Attribute Completion on Graph with Missing Attributes 4
FairGBM: Gradient Boosting with Fairness Constraints 6
Fairness and Accuracy under Domain Generalization 7
Fairness-aware Contrastive Learning with Partially Annotated Sensitive Attributes 3
Fake It Until You Make It : Towards Accurate Near-Distribution Novelty Detection 3
Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems 5
Fast Nonlinear Vector Quantile Regression 5
Fast Sampling of Diffusion Models with Exponential Integrator 4
Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search 6
FastFill: Efficient Compatible Model Update 4
Faster Gradient-Free Methods for Escaping Saddle Points 3
Faster Last-iterate Convergence of Policy Optimization in Zero-Sum Markov Games 1
Faster federated optimization under second-order similarity 4
Feature Reconstruction From Outputs Can Mitigate Simplicity Bias in Neural Networks 5
Feature selection and low test error in shallow low-rotation ReLU networks 2
FedDAR: Federated Domain-Aware Representation Learning 5
FedExP: Speeding Up Federated Averaging via Extrapolation 4
FedFA: Federated Feature Augmentation 6
FedSpeed: Larger Local Interval, Less Communication Round, and Higher Generalization Accuracy 4
Federated Learning as Variational Inference: A Scalable Expectation Propagation Approach 5
Federated Learning from Small Datasets 4
Federated Nearest Neighbor Machine Translation 5
Federated Neural Bandits 5
Few-Shot Domain Adaptation For End-to-End Communication 5
Few-shot Backdoor Attacks via Neural Tangent Kernels 5
Few-shot Cross-domain Image Generation via Inference-time Latent-code Learning 4
FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image Classification 6
Filter-Recovery Network for Multi-Speaker Audio-Visual Speech Separation 3
Finding Actual Descent Directions for Adversarial Training 4
Finding the Global Semantic Representation in GAN through Fréchet Mean 2
First Steps Toward Understanding the Extrapolation of Nonlinear Models to Unseen Domains 0
Fisher-Legendre (FishLeg) optimization of deep neural networks 5
Flow Annealed Importance Sampling Bootstrap 5
Flow Matching for Generative Modeling 3
Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow 4
FluidLab: A Differentiable Environment for Benchmarking Complex Fluid Manipulation 3
FoSR: First-order spectral rewiring for addressing oversquashing in GNNs 6
Fooling SHAP with Stealthily Biased Sampling 5
Formal Mathematics Statement Curriculum Learning 5
Forward Super-Resolution: How Can GANs Learn Hierarchical Generative Models for Real-World Distributions 2
Free Lunch for Domain Adversarial Training: Environment Label Smoothing 5
FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning 5
From $t$-SNE to UMAP with contrastive learning 7
From Play to Policy: Conditional Behavior Generation from Uncurated Robot Data 2
Function-Consistent Feature Distillation 5
Function-space regularized Rényi divergences 2
Fundamental Limits in Formal Verification of Message-Passing Neural Networks 0
Fundamental limits on the robustness of image classifiers 2
FunkNN: Neural Interpolation for Functional Generation 4
Fuzzy Alignments in Directed Acyclic Graph for Non-Autoregressive Machine Translation 6
GAIN: On the Generalization of Instructional Action Understanding 3
GAMR: A Guided Attention Model for (visual) Reasoning 4
GEASS: Neural causal feature selection for high-dimensional biological data 2
GFlowNets and variational inference 2
GLM-130B: An Open Bilingual Pre-trained Model 5
GNNDelete: A General Strategy for Unlearning in Graph Neural Networks 4
GNNInterpreter: A Probabilistic Generative Model-Level Explanation for Graph Neural Networks 5
GOGGLE: Generative Modelling for Tabular Data by Learning Relational Structure 5
GOOD: Exploring geometric cues for detecting objects in an open world 4
GPViT: A High Resolution Non-Hierarchical Vision Transformer with Group Propagation 4
GRACE-C: Generalized Rate Agnostic Causal Estimation via Constraints 5
GReTo: Remedying dynamic graph topology-task discordance via target homophily 3
GeneFace: Generalized and High-Fidelity Audio-Driven 3D Talking Face Synthesis 4
General Neural Gauge Fields 4
Generalization Bounds for Federated Learning: Fast Rates, Unparticipating Clients and Unbounded Losses 2
Generalization and Estimation Error Bounds for Model-based Neural Networks 2
Generalize Learned Heuristics to Solve Large-scale Vehicle Routing Problems in Real-time 3
Generalized Precision Matrix for Scalable Estimation of Nonparametric Markov Networks 2
Generalizing and Decoupling Neural Collapse via Hyperspherical Uniformity Gap 3
Generate rather than Retrieve: Large Language Models are Strong Context Generators 5
Generating Diverse Cooperative Agents by Learning Incompatible Policies 4
Generating Sequences by Learning to Self-Correct 5
Generative Augmented Flow Networks 4
Generative Modeling Helps Weak Supervision (and Vice Versa) 6
Generative Modelling with Inverse Heat Dissipation 5
Geometrically regularized autoencoders for non-Euclidean data 6
Git Re-Basin: Merging Models modulo Permutation Symmetries 5
Global Explainability of GNNs via Logic Combination of Learned Concepts 4
Globally Optimal Training of Neural Networks with Threshold Activation Functions 3
GoBigger: A Scalable Platform for Cooperative-Competitive Multi-Agent Interactive Simulation 2
Gradient Boosting Performs Gaussian Process Inference 5
Gradient Gating for Deep Multi-Rate Learning on Graphs 4
Gradient-Guided Importance Sampling for Learning Binary Energy-Based Models 4
Graph Contrastive Learning for Skeleton-based Action Recognition 5
Graph Domain Adaptation via Theory-Grounded Spectral Regularization 5
Graph Neural Network-Inspired Kernels for Gaussian Processes in Semi-Supervised Learning 7
Graph Neural Networks are Inherently Good Generalizers: Insights by Bridging GNNs and MLPs 6
Graph Neural Networks for Link Prediction with Subgraph Sketching 6
Graph Signal Sampling for Inductive One-Bit Matrix Completion: a Closed-form Solution 7
Graph-based Deterministic Policy Gradient for Repetitive Combinatorial Optimization Problems 5
Gray-Box Gaussian Processes for Automated Reinforcement Learning 4
Greedy Actor-Critic: A New Conditional Cross-Entropy Method for Policy Improvement 4
Gromov-Wasserstein Autoencoders 5
Grounding Graph Network Simulators using Physical Sensor Observations 4
Guarded Policy Optimization with Imperfect Online Demonstrations 4
Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot Learners 3
Guiding Energy-based Models via Contrastive Latent Variables 5
Guiding Safe Exploration with Weakest Preconditions 4
Guiding continuous operator learning through Physics-based boundary constraints 4
H2RBox: Horizontal Box Annotation is All You Need for Oriented Object Detection 5
Hard-Meta-Dataset++: Towards Understanding Few-Shot Performance on Difficult Tasks 5
Harnessing Mixed Offline Reinforcement Learning Datasets via Trajectory Weighting 4
Harnessing Out-Of-Distribution Examples via Augmenting Content and Style 5
Hebbian Deep Learning Without Feedback 5
Hebbian and Gradient-based Plasticity Enables Robust Memory and Rapid Learning in RNNs 5
Heterogeneous Neuronal and Synaptic Dynamics for Spike-Efficient Unsupervised Learning: Theory and Design Principles 2
HiCLIP: Contrastive Language-Image Pretraining with Hierarchy-aware Attention 6
HiT-MDP: Learning the SMDP option framework on MDPs with Hidden Temporal Embeddings 5
HiViT: A Simpler and More Efficient Design of Hierarchical Vision Transformer 6
Hidden Markov Transformer for Simultaneous Machine Translation 6
Hierarchical Abstraction for Combinatorial Generalization in Object Rearrangement 2
Hierarchical Relational Learning for Few-Shot Knowledge Graph Completion 6
Hierarchical Sliced Wasserstein Distance 4
Holistic Adversarially Robust Pruning 5
HomoDistil: Homotopic Task-Agnostic Distillation of Pre-trained Transformers 5
HotProtein: A Novel Framework for Protein Thermostability Prediction and Editing 5
How Does Semi-supervised Learning with Pseudo-labelers Work? A Case Study 2
How I Learned to Stop Worrying and Love Retraining 4
How Informative is the Approximation Error from Tensor Decomposition for Neural Network Compression? 4
How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization 5
How Much Space Has Been Explored? Measuring the Chemical Space Covered by Databases and Machine-Generated Molecules 4
How Sharpness-Aware Minimization Minimizes Sharpness? 0
How gradient estimator variance and bias impact learning in neural networks 3
How robust is unsupervised representation learning to distribution shift? 3
How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection? 6
How to Train your HIPPO: State Space Models with Generalized Orthogonal Basis Projections 2
How to prepare your task head for finetuning 4
Human Motion Diffusion Model 4
Human MotionFormer: Transferring Human Motions with Vision Transformers 4
Human alignment of neural network representations 4
Human-Guided Fair Classification for Natural Language Processing 4
Human-level Atari 200x faster 4
Humanly Certifying Superhuman Classifiers 4
Hungry Hungry Hippos: Towards Language Modeling with State Space Models 6
Hybrid RL: Using both offline and online data can make RL efficient 4
HypeR: Multitask Hyper-Prompted Training Enables Large-Scale Retrieval Generalization 4
Hyper-Decision Transformer for Efficient Online Policy Adaptation 3
HyperDeepONet: learning operator with complex target function space using the limited resources via hypernetwork 3
Hyperbolic Deep Reinforcement Learning 3
Hyperbolic Self-paced Learning for Self-supervised Skeleton-based Action Representations 5
Hyperparameter Optimization through Neural Network Partitioning 6
IDEAL: Query-Efficient Data-Free Learning from Black-Box Models 3
ILA-DA: Improving Transferability of Intermediate Level Attack with Data Augmentation 6
IS SYNTHETIC DATA FROM GENERATIVE MODELS READY FOR IMAGE RECOGNITION? 4
ISAAC Newton: Input-based Approximate Curvature for Newton's Method 4
ISS: Image as Stepping Stone for Text-Guided 3D Shape Generation 4
Identifiability Results for Multimodal Contrastive Learning 3
Image as Set of Points 5
Image to Sphere: Learning Equivariant Features for Efficient Pose Prediction 4
ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotations 4
Images as Weight Matrices: Sequential Image Generation Through Synaptic Learning Rules 4
ImaginaryNet: Learning Object Detectors without Real Images and Annotations 4
Imbalanced Semi-supervised Learning with Bias Adaptive Classifier 6
Imitating Graph-Based Planning with Goal-Conditioned Policies 4
Imitating Human Behaviour with Diffusion Models 4
Implicit Bias in Leaky ReLU Networks Trained on High-Dimensional Data 2
Implicit Bias of Large Depth Networks: a Notion of Rank for Nonlinear Functions 2
Implicit Regularization for Group Sparsity 3
Implicit regularization in Heavy-ball momentum accelerated stochastic gradient descent 2
Impossibly Good Experts and How to Follow Them 4
Improved Convergence of Differential Private SGD with Gradient Clipping 4
Improved Learning-augmented Algorithms for k-means and k-medians Clustering 5
Improved Sample Complexity for Reward-free Reinforcement Learning under Low-rank MDPs 1
Improved Training of Physics-Informed Neural Networks Using Energy-Based Priors: a Study on Electrical Impedance Tomography 4
Improving Deep Policy Gradients with Value Function Search 4
Improving Deep Regression with Ordinal Entropy 3
Improving Differentiable Neural Architecture Search by Encouraging Transferability 6
Improving Object-centric Learning with Query Optimization 4
Improving Out-of-distribution Generalization with Indirection Representations 3
Improving the imputation of missing data with Markov Blanket discovery 4
In-Situ Text-Only Adaptation of Speech Models with Low-Overhead Speech Imputations 5
In-context Reinforcement Learning with Algorithm Distillation 2
In-sample Actor Critic for Offline Reinforcement Learning 4
InCoder: A Generative Model for Code Infilling and Synthesis 5
InPL: Pseudo-labeling the Inliers First for Imbalanced Semi-supervised Learning 3
Incompatibility Clustering as a Defense Against Backdoor Poisoning Attacks 4
Incremental Learning of Structured Memory via Closed-Loop Transcription 5
Indiscriminate Poisoning Attacks on Unsupervised Contrastive Learning 5
Individual Privacy Accounting with Gaussian Differential Privacy 4
Inequality phenomenon in $l_{\infty}$-adversarial training, and its unrealized threats 3
Information Plane Analysis for Dropout Neural Networks 4
Information-Theoretic Analysis of Unsupervised Domain Adaptation 5
Information-Theoretic Diffusion 5
Instance-wise Batch Label Restoration via Gradients in Federated Learning 4
Integrating Symmetry into Differentiable Planning with Steerable Convolutions 4
Interaction-Based Disentanglement of Entities for Object-Centric World Models 2
Interactive Portrait Harmonization 4
Interneurons accelerate learning dynamics in recurrent neural networks for statistical adaptation 2
Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 Small 2
Interpretability with full complexity by constraining feature information 5
Interpretable Debiasing of Vectorized Language Representations with Iterative Orthogonalization 5
Interpretable Geometric Deep Learning via Learnable Randomness Injection 4
Interpretations of Domain Adaptations via Layer Variational Analysis 5
Investigating Multi-task Pretraining and Generalization in Reinforcement Learning 3
Is Adversarial Training Really a Silver Bullet for Mitigating Data Poisoning? 4
Is Attention All That NeRF Needs? 4
Is Conditional Generative Modeling all you need for Decision Making? 3
Is Forgetting Less a Good Inductive Bias for Forward Transfer? 4
Is Model Ensemble Necessary? Model-based RL via a Single Model with Lipschitz Regularized Value Function 3
Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization 5
Is a Caption Worth a Thousand Images? A Study on Representation Learning 3
Is the Performance of My Deep Network Too Good to Be True? A Direct Approach to Estimating the Bayes Error in Binary Classification 5
Iterative Circuit Repair Against Formal Specifications 7
Iterative Patch Selection for High-Resolution Image Recognition 6
Joint Edge-Model Sparse Learning is Provably Efficient for Graph Neural Networks 5
Jointly Learning Visual and Auditory Speech Representations from Raw Data 5
Kernel Neural Optimal Transport 4
KnowDA: All-in-One Knowledge Mixture Model for Data Augmentation in Low-Resource NLP 4
Knowledge Distillation based Degradation Estimation for Blind Super-Resolution 4
Knowledge-in-Context: Towards Knowledgeable Semi-Parametric Language Models 4
Koopman Neural Operator Forecaster for Time-series with Temporal Distributional Shifts 4
KwikBucks: Correlation Clustering with Cheap-Weak and Expensive-Strong Signals 4
LAVA: Data Valuation without Pre-Specified Learning Algorithms 4
LDMIC: Learning-based Distributed Multi-view Image Coding 6
LMC: Fast Training of GNNs via Subgraph Sampling with Provable Convergence 6
LMSeg: Language-guided Multi-dataset Segmentation 4
LPT: Long-tailed Prompt Tuning for Image Classification 4
LS-IQ: Implicit Reward Regularization for Inverse Reinforcement Learning 5
Label Propagation with Weak Supervision 5
Label-free Concept Bottleneck Models 5
Language Modelling with Pixels 6
Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought 4
Language Models Can Teach Themselves to Program Better 3
Language Models are Realistic Tabular Data Generators 4
Language models are multilingual chain-of-thought reasoners 3
Large Language Models are Human-Level Prompt Engineers 5
Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations 5
Latent Bottlenecked Attentive Neural Processes 4
Latent Graph Inference using Product Manifolds 5
Latent Neural ODEs with Sparse Bayesian Multiple Shooting 6
Latent State Marginalization as a Low-cost Approach for Improving Exploration 5
Latent Variable Representation for Reinforcement Learning 4
Layer Grafted Pre-training: Bridging Contrastive Learning And Masked Image Modeling For Label-Efficient Representations 5
Learnable Behavior Control: Breaking Atari Human World Records via Sample-Efficient Behavior Selection 4
Learnable Graph Convolutional Attention Networks 5
Learnable Topological Features For Phylogenetic Inference via Graph Neural Networks 4
Learned Index with Dynamic $\epsilon$ 5
Learning About Progress From Experts 4
Learning Achievement Structure for Structured Exploration in Domains with Sparse Reward 3
Learning Adversarial Linear Mixture Markov Decision Processes with Bandit Feedback and Unknown Transition 1
Learning Continuous Normalizing Flows For Faster Convergence To Target Distribution via Ascent Regularizations 4
Learning Controllable Adaptive Simulation for Multi-resolution Physics 4
Learning Cut Selection for Mixed-Integer Linear Programming via Hierarchical Sequence Model 7
Learning Diffusion Bridges on Constrained Domains 4
Learning Domain-Agnostic Representation for Disease Diagnosis 3
Learning Fair Graph Representations via Automated Data Augmentations 4
Learning Fast and Slow for Online Time Series Forecasting 5
Learning Group Importance using the Differentiable Hypergeometric Distribution 6
Learning Harmonic Molecular Representations on Riemannian Manifold 5
Learning Heterogeneous Interaction Strengths by Trajectory Prediction with Graph Neural Network 4
Learning Hierarchical Protein Representations via Complete 3D Graph Networks 5
Learning Human-Compatible Representations for Case-Based Decision Support 5
Learning Hyper Label Model for Programmatic Weak Supervision 5
Learning Input-agnostic Manipulation Directions in StyleGAN with Text Guidance 4
Learning Iterative Neural Optimizers for Image Steganography 6
Learning Kernelized Contextual Bandits in a Distributed and Asynchronous Environment 3
Learning Label Encodings for Deep Regression 6
Learning Language Representations with Logical Inductive Bias 4
Learning Locality and Isotropy in Dialogue Modeling 5
Learning Low Dimensional State Spaces with Overparameterized Recurrent Neural Nets 1
Learning MLPs on Graphs: A Unified View of Effectiveness, Robustness, and Efficiency 3
Learning Math Reasoning from Self-Sampled Correct and Partially-Correct Solutions 6
Learning Multimodal Data Augmentation in Feature Space 5
Learning Object-Language Alignments for Open-Vocabulary Object Detection 5
Learning Probabilistic Topological Representations Using Discrete Morse Theory 5
Learning Proximal Operators to Discover Multiple Optima 5
Learning Rationalizable Equilibria in Multiplayer Games 1
Learning ReLU networks to high uniform accuracy is intractable 3
Learning Simultaneous Navigation and Construction in Grid Worlds 5
Learning Soft Constraints From Constrained Expert Demonstrations 3
Learning Sparse Group Models Through Boolean Relaxation 6
Learning Sparse and Low-Rank Priors for Image Recovery via Iterative Reweighted Least Squares Minimization 5
Learning Structured Representations by Embedding Class Hierarchy 2
Learning Symbolic Models for Graph-structured Physical Mechanism 3
Learning Uncertainty for Unknown Domains with Zero-Target-Assumption 4
Learning Vortex Dynamics for Fluid Inference and Prediction 4
Learning What and Where: Disentangling Location and Identity Tracking Without Supervision 5
Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biased 3
Learning a Data-Driven Policy Network for Pre-Training Automated Feature Engineering 7
Learning differentiable solvers for systems with hard constraints 4
Learning in temporally structured environments 2
Learning multi-scale local conditional probability models of images 5
Learning on Large-scale Text-attributed Graphs via Variational Inference 5
Learning rigid dynamics with face interaction graph networks 4
Learning the Positions in CountSketch 4
Learning to CROSS exchange to solve min-max vehicle routing problems 4
Learning to Compose Soft Prompts for Compositional Zero-Shot Learning 6
Learning to Decompose Visual Features with Latent Textual Prompts 2
Learning to Estimate Shapley Values with Vision Transformers 6
Learning to Estimate Single-View Volumetric Flow Motions without 3D Supervision 5
Learning to Extrapolate: A Transductive Approach 3
Learning to Generate Columns with Application to Vertex Coloring 6
Learning to Grow Pretrained Models for Efficient Transformer Training 4
Learning to Induce Causal Structure 2
Learning to Jointly Share and Prune Weights for Grounding Based Vision and Language Models 3
Learning to Linearize Deep Neural Networks for Secure and Efficient Private Inference 5
Learning to Segment from Noisy Annotations: A Spatial Correction Approach 6
Learning to Solve Constraint Satisfaction Problems with Recurrent Transformer 5
Learning to reason over visual objects 5
Learning topology-preserving data representations 4
Learning where and when to reason in neuro-symbolic inference 5
Learning with Auxiliary Activation for Memory-Efficient Training 5
Learning with Logical Constraints but without Shortcut Satisfaction 5
Learning with Stochastic Orders 6
Learning without Prejudices: Continual Unbiased Learning via Benign and Malignant Forgetting 4
Least-to-Most Prompting Enables Complex Reasoning in Large Language Models 3
Leveraging Future Relationship Reasoning for Vehicle Trajectory Prediction 2
Leveraging Importance Weights in Subset Selection 5
Leveraging Large Language Models for Multiple Choice Question Answering 4
Leveraging Unlabeled Data to Track Memorization 6
LexMAE: Lexicon-Bottlenecked Pretraining for Large-Scale Retrieval 5
LiftedCL: Lifting Contrastive Learning for Human-Centric Perception 3
Light Sampling Field and BRDF Representation for Physically-based Neural Rendering 2
LightGCL: Simple Yet Effective Graph Contrastive Learning for Recommendation 4
LilNetX: Lightweight Networks with EXtreme Model Compression and Structured Sparsification 4
Limitless Stability for Graph Convolutional Networks 2
Linear Connectivity Reveals Generalization Strategies 5
Linear Convergence of Natural Policy Gradient Methods with Log-Linear Policies 1
Linearly Mapping from Image to Text Space 5
Link Prediction with Non-Contrastive Learning 6
LipsFormer: Introducing Lipschitz Continuity to Vision Transformers 4
Liquid Structural State-Space Models 5
Localized Randomized Smoothing for Collective Robustness Certification 6
LogicDP: Creating Labels for Graph Data via Inductive Logic Programming 6
Logical Entity Representation in Knowledge-Graphs for Differentiable Rule Learning 4
Logical Message Passing Networks with One-hop Inference on Atomic Formulas 4
Long Range Language Modeling via Gated State Spaces 4
Long-Tailed Learning Requires Feature Learning 2
Long-Tailed Partial Label Learning via Dynamic Rebalancing 5
Loss Landscapes are All You Need: Neural Network Generalization Can Be Explained Without the Implicit Bias of Gradient Descent 3
Lossless Adaptation of Pretrained Vision Models For Robotic Manipulation 2
Lower Bounds on the Depth of Integral ReLU Neural Networks via Lattice Polytopes 0
M-L2O: Towards Generalizable Learning-to-Optimize by Test-Time Fast Self-Adaptation 4
MA-BERT: Towards Matrix Arithmetic-only BERT Inference by Eliminating Complex Non-Linear Functions 5
MACTA: A Multi-agent Reinforcement Learning Approach for Cache Timing Attacks and Detection 6
MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning 5
MARS: Meta-learning as Score Matching in the Function Space 5
MAST: Masked Augmentation Subspace Training for Generalizable Self-Supervised Priors 2
MCAL: Minimum Cost Human-Machine Active Labeling 5
MECTA: Memory-Economic Continual Test-Time Model Adaptation 6
MEDFAIR: Benchmarking Fairness for Medical Imaging 6
MEDICAL IMAGE UNDERSTANDING WITH PRETRAINED VISION LANGUAGE MODELS: A COMPREHENSIVE STUDY 4
MICN: Multi-scale Local and Global Context Modeling for Long-term Series Forecasting 5
MIMT: Masked Image Modeling Transformer for Video Compression 4
MLPInit: Embarrassingly Simple GNN Training Acceleration with MLP Initialization 7
MMVAE+: Enhancing the Generative Quality of Multimodal VAEs without Compromises 4
MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models 5
MPCFORMER: FAST, PERFORMANT AND PRIVATE TRANSFORMER INFERENCE WITH MPC 4
Machine Unlearning of Federated Clusters 4
Make-A-Video: Text-to-Video Generation without Text-Video Data 2
Making Better Decision by Directly Planning in Continuous Control 4
Making Substitute Models More Bayesian Can Enhance Transferability of Adversarial Examples 5
Malign Overfitting: Interpolation and Invariance are Fundamentally at Odds 3
ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills 5
ManyDG: Many-domain Generalization for Healthcare Applications 6
MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction 4
Markup-to-Image Diffusion Models with Scheduled Sampling 6
Martingale Posterior Neural Processes 6
MaskFusion: Feature Augmentation for Click-Through Rate Prediction via Input-adaptive Mask Fusion 4
MaskViT: Masked Visual Pre-Training for Video Prediction 4
Masked Distillation with Receptive Tokens 4
Masked Frequency Modeling for Self-Supervised Visual Pre-Training 6
Masked Image Modeling with Denoising Contrast 5
Masked Unsupervised Self-training for Label-free Image Classification 4
Masked Vision and Language Modeling for Multi-modal Representation Learning 4
Mass-Editing Memory in a Transformer 6
Massively Scaling Heteroscedastic Classifiers 5
Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning 5
Matching receptor to odorant with protein language and graph neural networks 5
Max-Margin Works while Large Margin Fails: Generalization without Uniform Convergence 0
Maximizing Communication Efficiency for Large-scale Training via 0/1 Adam 6
Maximizing Spatio-Temporal Entropy of Deep 3D CNNs for Efficient Video Recognition 6
Measure the Predictive Heterogeneity 2
Measuring Forgetting of Memorized Training Examples 3
Measuring axiomatic soundness of counterfactual image models 4
Mega: Moving Average Equipped Gated Attention 3
Memorization Capacity of Neural Networks with Conditional Computation 1
Memorization-Dilation: Modeling Neural Collapse Under Noise 2
Memory Gym: Partially Observable Challenges to Memory-Based Agents 6
MeshDiffusion: Score-based Generative 3D Mesh Modeling 6
Meta Knowledge Condensation for Federated Learning 4
Meta Learning to Bridge Vision and Language Models for Multimodal Few-Shot Learning 5
Meta Temporal Point Processes 3
Meta-Learning in Games 3
Meta-learning Adaptive Deep Kernel Gaussian Processes for Molecular Property Prediction 6
Meta-prediction Model for Distillation-Aware NAS on Unseen Datasets 5
MetaGL: Evaluation-Free Selection of Graph Learning Models via Meta-Learning 5
Metadata Archaeology: Unearthing Data Subsets by Leveraging Training Dynamics 3
Mid-Vision Feedback 3
Min-Max Multi-objective Bilevel Optimization with Applications in Robust Machine Learning 7
Mind the Gap: Offline Policy Optimization for Imperfect Rewards 5
Mind the Pool: Convolutional Neural Networks Can Overfit Input Size 4
Mind's Eye: Grounded Language Model Reasoning through Simulation 2
Mini-batch $k$-means terminates within $O(d/\epsilon)$ iterations 1
Minimalistic Unsupervised Representation Learning with the Sparse Manifold Transform 3
Minimax Optimal Kernel Operator Learning via Multilevel Training 0
Minimum Description Length Control 3
Minimum Variance Unbiased N:M Sparsity for the Neural Gradients 4
Mitigating Dataset Bias by Using Per-Sample Gradient 5
Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Approach 4
Mitigating Memorization of Noisy Labels via Regularization between Representations 3
MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision Transformer 5
MoDem: Accelerating Visual Model-Based Reinforcement Learning with Demonstrations 4
MocoSFL: enabling cross-client collaborative self-supervised learning 5
Model ensemble instead of prompt fusion: a sample-specific knowledge transfer method for few-shot prompt tuning 4
Model-based Causal Bayesian Optimization 5
Modeling Multimodal Aleatoric Uncertainty in Segmentation with Mixture of Stochastic Experts 6
Modeling Sequential Sentence Relation to Improve Cross-lingual Dense Retrieval 4
Modeling content creator incentives on algorithm-curated platforms 6
Modeling the Data-Generating Process is Necessary for Out-of-Distribution Generalization 7
Modelling Long Range Dependencies in $N$D: From Task-Specific to a General Purpose CNN 5
Moderate Coreset: A Universal Method of Data Selection for Real-world Data-efficient Deep Learning 5
Mole-BERT: Rethinking Pre-training Graph Neural Networks for Molecules 4
Molecular Geometry Pretraining with SE(3)-Invariant Denoising Distance Matching 6
Molecule Generation For Target Protein Binding with Structural Motifs 6
Momentum Stiefel Optimizer, with Applications to Suitably-Orthogonal Attention, and Optimal Transport 5
Monocular Scene Reconstruction with 3D SDF Transformers 4
More Centralized Training, Still Decentralized Execution: Multi-Agent Conditional Policy Factorization 4
More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity 7
Mosaic Representation Learning for Self-supervised Visual Pre-training 6
Moving Forward by Moving Backward: Embedding Action Impact over Action Semantics 5
Multi-Objective Online Learning 4
Multi-Objective Reinforcement Learning: Convexity, Stationarity and Pareto Optimality 5
Multi-Rate VAE: Train Once, Get the Full Rate-Distortion Curve 5
Multi-domain image generation and translation with identifiability guarantees 3
Multi-level Protein Structure Pre-training via Prompt Learning 5
Multi-lingual Evaluation of Code Generation Models 4
Multi-objective optimization via equivariant deep hypervolume approximation 5
Multi-skill Mobile Manipulation for Object Rearrangement 4
Multi-task Self-supervised Graph Neural Networks Enable Stronger Task Generalization 6
MultiViz: Towards Visualizing and Understanding Multimodal Models 5
Multifactor Sequential Disentanglement via Structured Koopman Autoencoders 5
Multimodal Analogical Reasoning over Knowledge Graphs 5
Multimodal Federated Learning via Contrastive Representation Ensemble 3
Multiple sequence alignment as a sequence-to-sequence learning problem 3
Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learning 3
Multivariate Time-series Imputation with Disentangled Temporal Representations 6
Mutual Partial Label Learning with Competitive Label Noise 4
NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs 6
NANSY++: Unified Voice Synthesis with Neural Analysis and Synthesis 4
NERDS: A General Framework to Train Camera Denoisers from Raw-RGB Noisy Image Pairs 3
NORM: Knowledge Distillation via N-to-One Representation Matching 5
NTFields: Neural Time Fields for Physics-Informed Robot Motion Planning 4
NTK-SAP: Improving neural network pruning by aligning training dynamics 5
NeRF-SOS: Any-View Self-supervised Object Segmentation on Complex Scenes 4
NeRN: Learning Neural Representations for Neural Networks 4
Near-Optimal Adversarial Reinforcement Learning with Switching Costs 1
Near-Optimal Deployment Efficiency in Reward-Free Reinforcement Learning with Linear Function Approximation 1
Near-optimal Coresets for Robust Clustering 5
Near-optimal Policy Identification in Active Reinforcement Learning 3
Nearly Minimax Optimal Offline Reinforcement Learning with Linear Function Approximation: Single-Agent MDP and Markov Game 2
Neural Agents Struggle to Take Turns in Bidirectional Emergent Communication 4
Neural Architecture Design and Robustness: A Dataset 5
Neural Bregman Divergences for Distance Learning 5
Neural Causal Models for Counterfactual Identification and Estimation 2
Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class-Incremental Learning 3
Neural Compositional Rule Learning for Knowledge Graph Reasoning 4
Neural DAG Scheduling via One-Shot Priority Sampling 5
Neural Design for Genetic Perturbation Experiments 4
Neural Episodic Control with State Abstraction 5
Neural Groundplans: Persistent Neural Scene Representations from a Single Image 4
Neural Image-based Avatars: Generalizable Radiance Fields for Human Avatar Modeling 2
Neural Implicit Shape Editing using Boundary Sensitivity 2
Neural Lagrangian Schr\"{o}dinger Bridge: Diffusion Modeling for Population Dynamics 6
Neural Networks Efficiently Learn Low-Dimensional Representations with SGD 1
Neural Networks and the Chomsky Hierarchy 5
Neural Optimal Transport 5
Neural Radiance Field Codebooks 4
Neural Systematic Binder 4
Neural ePDOs: Spatially Adaptive Equivariant Partial Differential Operator Based Networks 2
Neural-based classification rule learning for sequential data 5
Neuro-Symbolic Procedural Planning with Commonsense Prompting 5
Neuroevolution is a Competitive Alternative to Reinforcement Learning for Skill Discovery 5
Neuromechanical Autoencoders: Learning to Couple Elastic and Neural Network Nonlinearity 3
New Insights for the Stability-Plasticity Dilemma in Online Continual Learning 4
No Reason for No Supervision: Improved Generalization in Supervised Models 5
Noise Injection Node Regularization for Robust Learning 4
Noise Is Not the Main Factor Behind the Gap Between Sgd and Adam on Transformers, But Sign Descent Might Be 5
Noise-Robust De-Duplication at Scale 5
Non-parametric Outlier Synthesis 6
Nonlinear Reconstruction for Operator Learning of PDEs with Discontinuities 2
Not All Tasks Are Born Equal: Understanding Zero-Shot Generalization 3
Novel View Synthesis with Diffusion Models 5
ODAM: Gradient-based Instance-Specific Visual Explanations for Object Detection 5
OPTQ: Accurate Quantization for Generative Pre-trained Transformers 6
OTOv2: Automatic, Generic, User-Friendly 5
Offline Congestion Games: How Feedback Type Affects Data Coverage Requirement 2
Offline Q-learning on Diverse Multi-Task Data Both Scales And Generalizes 3
Offline RL for Natural Language Generation with Implicit Language Q Learning 4
Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization 4
Offline Reinforcement Learning via High-Fidelity Generative Behavior Modeling 5
Offline Reinforcement Learning with Differentiable Function Approximation is Provably Efficient 1
Ollivier-Ricci Curvature for Hypergraphs: A Unified Framework 3
Omnigrok: Grokking Beyond Algorithmic Data 3
On Accelerated Perceptrons and Beyond 1
On Achieving Optimal Adversarial Test Error 1
On Compositional Uncertainty Quantification for Seq2seq Graph Parsing 4
On Explaining Neural Network Robustness with Activation Path 4
On Pre-training Language Model for Antibody 4
On Representing Linear Programs by Graph Neural Networks 4
On Representing Mixed-Integer Linear Programs by Graph Neural Networks 4
On The Inadequacy of Optimizing Alignment and Uniformity in Contrastive Learning of Sentence Representations 6
On The Relative Error of Random Fourier Features for Preserving Kernel Distance 1
On The Specialization of Neural Modules 3
On amortizing convex conjugates for optimal transport 5
On the Convergence of AdaGrad(Norm) on $\mathbb{R}^d$: Beyond Convexity, Non-Asymptotic Rate and Acceleration 2
On the Data-Efficiency with Contrastive Image Transformation in Reinforcement Learning 3
On the Effectiveness of Out-of-Distribution Data in Self-Supervised Long-Tail Learning. 5
On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning 3
On the Importance and Applicability of Pre-Training for Federated Learning 5
On the Performance of Temporal Difference Learning With Neural Networks 2
On the Perils of Cascading Robust Classifiers 5
On the Robustness of Safe Reinforcement Learning under Observational Perturbations 5
On the Saturation Effect of Kernel Ridge Regression 1
On the Sensitivity of Reward Inference to Misspecified Human Models 2
On the Soft-Subnetwork for Few-Shot Class Incremental Learning 6
On the Trade-Off between Actionable Explanations and the Right to be Forgotten 3
On the Usefulness of Embeddings, Clusters and Strings for Text Generation Evaluation 4
On the Word Boundaries of Emergent Languages Based on Harris's Articulation Scheme 3
On the complexity of nonsmooth automatic differentiation 1
On the duality between contrastive and non-contrastive self-supervised learning 6
One Transformer Can Understand Both 2D & 3D Molecular Data 5
One-Pixel Shortcut: On the Learning Preference of Deep Neural Networks 6
Online Bias Correction for Task-Free Continual Learning 5
Online Boundary-Free Continual Learning by Scheduled Data Prior 5
Online Low Rank Matrix Completion 1
Open-Vocabulary Object Detection upon Frozen Vision and Language Models 3
Optimal Activation Functions for the Random Features Regression Model 5
Optimal Conservative Offline RL with General Function Approximation via Augmented Lagrangian 1
Optimal Transport for Offline Imitation Learning 5
Optimistic Exploration with Learned Features Provably Solves Markov Decision Processes with Neural Dynamics 1
Optimizing Bi-Encoder for Named Entity Recognition via Contrastive Learning 5
Optimizing Spca-based Continual Learning: A Theoretical Approach 4
Order Matters: Agent-by-agent Policy Optimization 4
Ordered GNN: Ordering Message Passing to Deal with Heterophily and Over-smoothing 6
Out-of-Distribution Detection and Selective Generation for Conditional Language Models 3
Out-of-Distribution Detection based on In-Distribution Data Patterns Memorization with Modern Hopfield Energy 6
Out-of-distribution Detection with Implicit Outlier Transformation 5
Out-of-distribution Representation Learning for Time Series Classification 4
Outcome-directed Reinforcement Learning by Uncertainty \& Temporal Distance-Aware Curriculum Goal Generation 4
Over-Training with Mixup May Hurt Generalization 3
Over-parameterized Model Optimization with Polyak-{\L}ojasiewicz Condition 4
PAC Reinforcement Learning for Predictive State Representations 1
PAC-NeRF: Physics Augmented Continuum Neural Radiance Fields for Geometry-Agnostic System Identification 2
PASHA: Efficient HPO and NAS with Progressive Resource Allocation 5
PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithm 5
PEER: A Collaborative Language Model 3
PGrad: Learning Principal Gradients For Domain Generalization 3
PINTO: Faithful Language Reasoning Using Prompt-Generated Rationales 4
PLOT: Prompt Learning with Optimal Transport for Vision-Language Models 7
POPGym: Benchmarking Partially Observable Reinforcement Learning 4
PV3D: A 3D Generative Model for Portrait Video Generation 4
PaLI: A Jointly-Scaled Multilingual Language-Image Model 4
Packed Ensembles for efficient uncertainty estimation 6
PandA: Unsupervised Learning of Parts and Appearances in the Feature Maps of GANs 5
Panning for Gold in Federated Learning: Targeted Text Extraction under Arbitrarily Large-Scale Aggregation 2
Parallel Deep Neural Networks Have Zero Duality Gap 0
Parameter-Efficient Fine-Tuning Design Spaces 5
Parametrizing Product Shape Manifolds by Composite Networks 3
Pareto Invariant Risk Minimization: Towards Mitigating the Optimization Dilemma in Out-of-Distribution Generalization 7
Part-Based Models Improve Adversarial Robustness 5
Partial Label Unsupervised Domain Adaptation with Class-Prototype Alignment 3
Partially Observable RL with B-Stability: Unified Structural Condition and Sharp Sample-Efficient Algorithms 1
Particle-based Variational Inference with Preconditioned Functional Gradient Flow 6
Patch-Level Contrasting without Patch Correspondence for Accurate and Dense Contrastive Representation Learning 5
PatchDCT: Patch Refinement for High Quality Instance Segmentation 5
PerFedMask: Personalized Federated Learning with Optimized Masking Vectors 6
Perfectly Secure Steganography Using Minimum Entropy Coupling 5
Performance Bounds for Model and Policy Transfer in Hidden-parameter MDPs 1
Personalized Federated Learning with Feature Alignment and Classifier Collaboration 6
Personalized Reward Learning with Interaction-Grounded Learning (IGL) 4
Pessimism in the Face of Confounders: Provably Efficient Offline Reinforcement Learning in Partially Observable Markov Decision Processes 1
Phase transition for detecting a small community in a large network 0
Phase2vec: dynamical systems embedding with a physics-informed convolutional network 6
Phenaki: Variable Length Video Generation from Open Domain Textual Descriptions 3
PiFold: Toward effective and efficient protein inverse folding 5
Pink Noise Is All You Need: Colored Noise Exploration in Deep Reinforcement Learning 6
Pitfalls of Gaussians as a noise distribution in NCE 0
Planckian Jitter: countering the color-crippling effects of color jitter on self-supervised training 4
Planning Goals for Exploration 4
Planning with Large Language Models for Code Generation 5
Planning with Sequence Models through Iterative Energy Minimization 3
Plateau in Monotonic Linear Interpolation --- A "Biased" View of Loss Landscape for Deep Networks 4
Policy Expansion for Bridging Offline-to-Online Reinforcement Learning 5
Policy Pre-training for Autonomous Driving via Self-supervised Geometric Modeling 4
Policy-Based Self-Competition for Planning Problems 5
Population-size-Aware Policy Optimization for Mean-Field Games 4
Post-hoc Concept Bottleneck Models 5
Powderworld: A Platform for Understanding Generalization via Rich Task Distributions 4
PowerQuant: Automorphism Search for Non-Uniform Quantization 3
Pre-training via Denoising for Molecular Property Prediction 5
Predicting Cellular Responses with Variational Causal Inference and Refined Relational Information 3
Predictive Inference with Feature Conformal Prediction 5
Predictor-corrector algorithms for stochastic optimization under gradual distribution shift 3
Preference Transformer: Modeling Human Preferences using Transformers for RL 4
Preserving Pre-trained Features Helps Calibrate Fine-tuned Language Models 6
Priors, Hierarchy, and Information Asymmetry for Skill Transfer in Reinforcement Learning 2
Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Losses 4
Proactive Multi-Camera Collaboration for 3D Human Pose Estimation 6
Probabilistically Robust Recourse: Navigating the Trade-offs between Costs and Robustness in Algorithmic Recourse 3
Programmatically Grounded, Compositionally Generalizable Robotic Manipulation 4
Progress measures for grokking via mechanistic interpretability 2
Progressive Mix-Up for Few-Shot Supervised Multi-Source Domain Transfer 4
Progressive Prompts: Continual Learning for Language Models 3
Progressive Voronoi Diagram Subdivision Enables Accurate Data-free Class-Incremental Learning 5
Progressively Compressed Auto-Encoder for Self-supervised Representation Learning 5
Projective Proximal Gradient Descent for Nonconvex Nonsmooth Optimization: Fast Convergence Without Kurdyka-Lojasiewicz (KL) Property 3
Prompt-to-Prompt Image Editing with Cross-Attention Control 2
Promptagator: Few-shot Dense Retrieval From 8 Examples 3
Prompting GPT-3 To Be Reliable 3
Proposal-Contrastive Pretraining for Object Detection from Fewer Data 4
Protein Representation Learning by Geometric Structure Pretraining 5
Protein Representation Learning via Knowledge Enhanced Primary Structure Reasoning 3
Protein Sequence and Structure Co-Design with Equivariant Translation 5
Proto-Value Networks: Scaling Representation Learning with Auxiliary Tasks 4
Prototypical Calibration for Few-shot Learning of Language Models 5
Provable Defense Against Geometric Transformations 6
Provable Memorization Capacity of Transformers 3
Provable Robustness against Wasserstein Distribution Shifts via Input Randomization 5
Provable Sim-to-real Transfer in Continuous Domain with Partial Observations 1
Provably Auditing Ordinary Least Squares in Low Dimensions 4
Provably Efficient Lifelong Reinforcement Learning with Linear Representation 2
Provably Efficient Risk-Sensitive Reinforcement Learning: Iterated CVaR and Worst Path 2
Pruning Deep Neural Networks from a Sparsity Perspective 4
Pseudo-label Training and Model Inertia in Neural Machine Translation 4
Pseudoinverse-Guided Diffusion Models for Inverse Problems 4
Pushing the Accuracy-Group Robustness Frontier with Introspective Self-play 4
Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: Graphcore 4
Q-Pensieve: Boosting Sample Efficiency of Multi-Objective RL Through Memory Sharing of Q-Snapshots 4
QAID: Question Answering Inspired Few-shot Intent Detection 4
QuAnt: Quantum Annealing with Learnt Couplings 6
Quality-Similar Diversity via Population Based Reinforcement Learning 4
Quantifying Memorization Across Neural Language Models 1
Quantifying and Mitigating the Impact of Label Errors on Model Disparity Metrics 2
Quantile Risk Control: A Flexible Framework for Bounding the Probability of High-Loss Predictions 3
Quantized Compressed Sensing with Score-Based Generative Models 5
Quasi-optimal Reinforcement Learning with Continuous Actions 5
REPAIR: REnormalizing Permuted Activations for Interpolation Repair 5
REVISITING PRUNING AT INITIALIZATION THROUGH THE LENS OF RAMANUJAN GRAPH 3
RGI: robust GAN-inversion for mask-free image inpainting and unsupervised pixel-wise anomaly detection 3
RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch 5
ROCO: A General Framework for Evaluating Robustness of Combinatorial Optimization Solvers on Graphs 6
ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoning 5
RPM: Generalizable Multi-Agent Policies for Multi-Agent Reinforcement Learning 5
RandProx: Primal-Dual Optimization Algorithms with Randomized Proximal Updates 1
Random Laplacian Features for Learning with Hyperbolic Space 5
Rarity Score : A New Metric to Evaluate the Uncommonness of Synthesized Images 3
Re-Imagen: Retrieval-Augmented Text-to-Image Generator 4
Re-calibrating Feature Attributions for Model Interpretation 7
Re-parameterizing Your Optimizers rather than Architectures 5
Re-weighting Based Group Fairness Regularization via Classwise Robust Optimization 4
ReAct: Synergizing Reasoning and Acting in Language Models 3
Real-Time Image Demoir$\acute{e}$ing on Mobile Devices 5
Real-time variational method for learning neural trajectory and its dynamics 4
Recitation-Augmented Language Models 6
Recon: Reducing Conflicting Gradients From the Root For Multi-Task Learning 4
Recursive Time Series Data Augmentation 5
Red PANDA: Disambiguating Image Anomaly Detection by Removing Nuisance Factors 5
Regression with Label Differential Privacy 3
Relational Attention: Generalizing Transformers for Graph-Structured Tasks 5
Relative Behavioral Attributes: Filling the Gap between Symbolic Goal Specification and Reward Learning from Human Preferences 3
Relative representations enable zero-shot latent space communication 4
Reliability of CKA as a Similarity Measure in Deep Learning 3
Reparameterization through Spatial Gradient Scaling 6
Replay Memory as An Empirical MDP: Combining Conservative Estimation with Experience Replay 4
Replicable Bandits 2
Represent to Control Partially Observed Systems: Representation Learning with Provable Sample Efficiency 1
Representation Learning for Low-rank General-sum Markov Games 3
Representational Dissimilarity Metric Spaces for Stochastic Neural Networks 4
ResAct: Reinforcing Long-term Engagement in Sequential Recommendation with Residual Actor 5
Restricted Strong Convexity of Deep Learning Models with Smooth Activations 2
Rethinking Graph Lottery Tickets: Graph Sparsity Matters 4
Rethinking Self-Supervised Visual Representation Learning in Pre-training for 3D Human Pose and Shape Estimation 4
Rethinking Symbolic Regression: Morphology and Adaptability in the Context of Evolutionary Algorithms 4
Rethinking skip connection model as a learnable Markov chain 5
Rethinking the Effect of Data Augmentation in Adversarial Contrastive Learning 5
Rethinking the Expressive Power of GNNs via Graph Biconnectivity 6
Retrieval-based Controllable Molecule Generation 6
Reversible Column Networks 5
Revisit Finetuning strategy for Few-Shot Learning to Transfer the Emdeddings 4
Revisiting Graph Adversarial Attack and Defense From a Data Distribution Perspective 5
Revisiting Intrinsic Reward for Exploration in Procedurally Generated Environments 4
Revisiting Populations in multi-agent Communication 4
Revisiting Robustness in Graph Machine Learning 4
Revisiting adapters with adversarial training 4
Revisiting the Assumption of Latent Separability for Backdoor Defenses 4
Revisiting the Entropy Semiring for Neural Speech Recognition 4
Revocable Deep Reinforcement Learning with Affinity Regularization for Outlier-Robust Graph Matching 5
Reward Design with Language Models 3
Rhino: Deep Causal Temporal Relationship Learning with History-dependent Noise 4
Riemannian Metric Learning via Optimal Transport 4
Risk-Aware Reinforcement Learning with Coherent Risk Measures and Non-linear Function Approximation 3
RoPAWS: Robust Semi-supervised Representation Learning from Uncurated Data 5
Robust Active Distillation 5
Robust Algorithms on Adaptive Inputs from Bounded Adversaries 4
Robust Explanation Constraints for Neural Networks 2
Robust Fair Clustering: A Novel Fairness Attack and Defense Framework 3
Robust Graph Dictionary Learning 5
Robust Multivariate Time-Series Forecasting: Adversarial Attacks and Defense Mechanisms 4
Robust Scheduling with GFlowNets 2
Robust and Controllable Object-Centric Learning through Energy-based Models 5
Robustness to corruption in pre-trained Bayesian neural networks 6
Rotamer Density Estimator is an Unsupervised Learner of the Effect of Mutations on Protein-Protein Interaction 6
S-NeRF: Neural Radiance Fields for Street Views 5
SAM as an Optimal Relaxation of Bayes 3
SCALE-UP: An Efficient Black-box Input-level Backdoor Detection via Analyzing Scaled Prediction Consistency 4
SCoMoE: Efficient Mixtures of Experts with Structured Communication 5
SGDA with shuffling: faster convergence for nonconvex-PŁ minimax optimization 2
SIMPLE: A Gradient Estimator for k-Subset Sampling 5
SIMPLE: Specialized Model-Sample Matching for Domain Generalization 5
SLTUNET: A Simple Unified Model for Sign Language Translation 4
SMART: Self-supervised Multi-task pretrAining with contRol Transformers 4
SMART: Sentences as Basic Units for Text Evaluation 4
SP2 : A Second Order Stochastic Polyak Method 2
SQA3D: Situated Question Answering in 3D Scenes 4
STREET: A MULTI-TASK STRUCTURED REASONING AND EXPLANATION BENCHMARK 7
STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tables 5
STaSy: Score-based Tabular data Synthesis 7
SWIFT: Rapid Decentralized Federated Learning via Wait-Free Model Communication 5
SYNC: SAFETY-AWARE NEURAL CONTROL FOR STABILIZING STOCHASTIC DELAY-DIFFERENTIAL EQUATIONS 3
Safe Exploration Incurs Nearly No Additional Sample Complexity for Reward-Free RL 1
Safe Reinforcement Learning From Pixels Using a Stochastic Latent Representation 4
Sample Complexity of Nonparametric Off-Policy Evaluation on Low-Dimensional Manifolds using Deep Networks 3
Sample-Efficient Reinforcement Learning by Breaking the Replay Ratio Barrier 3
Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions 0
Sampling with Mollified Interaction Energy Descent 5
Sampling-based inference for large linear models, with application to linearised Laplace 6
Sampling-free Inference for Ab-Initio Potential Energy Surface Networks 5
Scaffolding a Student to Instill Knowledge 5
Scalable Batch-Mode Deep Bayesian Active Learning via Equivalence Class Annealing 5
Scalable Subset Sampling with Neural Conditional Poisson Networks 4
Scalable and Equivariant Spherical CNNs by Discrete-Continuous (DISCO) Convolutions 5
Scale-invariant Bayesian Neural Networks with Connectivity Tangent Kernel 6
Scaleformer: Iterative Multi-scale Refining Transformers for Time Series Forecasting 5
Scaling Forward Gradient With Local Losses 4
Scaling Laws For Deep Learning Based Image Reconstruction 5
Scaling Laws for a Multi-Agent Reinforcement Learning Model 2
Scaling Pareto-Efficient Decision Making via Offline Multi-Objective RL 4
Scaling Up Probabilistic Circuits by Latent Variable Distillation 6
Scaling up and Stabilizing Differentiable Planning with Implicit Differentiation 3
Scenario-based Question Answering with Interacting Contextual Properties 4
Schema Inference for Interpretable Image Classification 6
Score-based Continuous-time Discrete Diffusion Models 4
SeaFormer: Squeeze-enhanced Axial Transformer for Mobile Semantic Segmentation 5
Searching Lottery Tickets in Graph Neural Networks: A Dual Perspective 5
Seeing Differently, Acting Similarly: Heterogeneously Observable Imitation Learning 4
Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning 4
Selective Annotation Makes Language Models Better Few-Shot Learners 5
Selective Frequency Network for Image Restoration 4
Self-Consistency Improves Chain of Thought Reasoning in Language Models 4
Self-Distillation for Further Pre-training of Transformers 4
Self-Ensemble Protection: Training Checkpoints Are Good Data Protectors 6
Self-Guided Noise-Free Data Generation for Efficient Zero-Shot Learning 5
Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability 4
Self-Supervised Category-Level Articulated Object Pose Estimation with Part-Level SE(3) Equivariance 4
Self-Supervised Geometric Correspondence for Category-Level 6D Object Pose Estimation in the Wild 3
Self-Supervised Set Representation Learning for Unsupervised Meta-Learning 5
Self-supervised learning with rotation-invariant kernels 5
Self-supervision through Random Segments with Autoregressive Coding (RandSAC) 3
SemPPL: Predicting Pseudo-Labels for Better Contrastive Representations 6
Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation 5
Semi-Implicit Variational Inference via Score Matching 5
Semi-Parametric Inducing Point Networks and Neural Processes 5
Semi-supervised Community Detection via Structural Similarity Metrics 5
Semi-supervised learning with a principled likelihood from a generative model of data curation 4
Sequential Attention for Feature Selection 4
Sequential Gradient Coding For Straggler Mitigation 5
Sequential Latent Variable Models for Few-Shot High-Dimensional Time-Series Forecasting 5
Sequential Learning of Neural Networks for Prequential MDL 4
Serving Graph Compression for Graph Neural Networks 4
Share Your Representation Only: Guaranteed Improvement of the Privacy-Utility Tradeoff in Federated Learning 5
Sharper Bounds for Uniformly Stable Algorithms with Stationary Mixing Process 1
Short-Term Memory Convolutions 3
Sign and Basis Invariant Networks for Spectral Graph Representation Learning 6
SimPer: Simple Self-Supervised Learning of Periodic Targets 5
Simple Emergent Action Representations from Multi-Task Policy Training 4
Simple and Scalable Nearest Neighbor Machine Translation 5
Simple initialization and parametrization of sinusoidal networks via their kernel bandwidth 3
Simplicial Embeddings in Self-Supervised Learning and Downstream Classification 5
Simplicial Hopfield networks 3
Simplified State Space Layers for Sequence Modeling 6
Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective 4
Single-shot General Hyper-parameter Optimization for Federated Learning 5
SketchKnitter: Vectorized Sketch Generation with Diffusion Models 3
SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models 5
SmartFRZ: An Efficient Training Framework using Attention-Based Layer Freezing 3
Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language 4
Soft Neighbors are Positive Supporters in Contrastive Visual Representation Learning 4
SoftMatch: Addressing the Quantity-Quality Tradeoff in Semi-supervised Learning 6
SoftZoo: A Soft Robot Co-design Benchmark For Locomotion In Diverse Environments 2
Softened Symbol Grounding for Neuro-symbolic Systems 4
Solving Constrained Variational Inequalities via a First-order Interior Point-based Method 5
Solving Continuous Control via Q-learning 3
Solving stochastic weak Minty variational inequalities without increasing batch size 2
Sound Randomized Smoothing in Floating-Point Arithmetic 5
Spacetime Representation Learning 5
Sparse Distributed Memory is a Continual Learner 5
Sparse Mixture-of-Experts are Domain Generalizable Learners 4
Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers 5
Sparse Random Networks for Communication-Efficient Federated Learning 6
Sparse Token Transformer with Attention Back Tracking 4
Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints 6
Sparse tree-based Initialization for Neural Networks 5
Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together! 5
Sparsity-Constrained Optimal Transport 4
Spatial Attention Kinetic Networks with E(n)-Equivariance 6
Spatio-temporal point processes with deep non-stationary kernels 4
Specformer: Spectral Graph Neural Networks Meet Transformers 6
Spectral Augmentation for Self-Supervised Learning on Graphs 5
Spectral Decomposition Representation for Reinforcement Learning 3
SpeedyZero: Mastering Atari with Limited Data and Time 3
Spherical Sliced-Wasserstein 4
Spikformer: When Spiking Neural Network Meets Transformer 3
Spiking Convolutional Neural Networks for Text Classification 4
Spotlight: Mobile UI Understanding using Vision-Language Models with a Focus 5
Squeeze Training for Adversarial Robustness 5
Stable Target Field for Reduced Variance Score Estimation in Diffusion Models 5
StableDR: Stabilized Doubly Robust Learning for Recommendation on Data Missing Not at Random 5
Stateful Active Facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learning 4
Static Prediction of Runtime Errors by Learning to Execute Programs with External Resource Descriptions 6
Statistical Efficiency of Score Matching: The View from Isoperimetry 1
Statistical Guarantees for Consensus Clustering 2
Statistical Inference for Fisher Market Equilibrium 1
Statistical Theory of Differentially Private Marginal-based Data Synthesis Algorithms 1
Stay Moral and Explore: Learn to Behave Morally in Text-based Games 4
Stochastic Differentially Private and Fair Learning 4
Stochastic Multi-Person 3D Motion Forecasting 3
Stochastic No-regret Learning for General Games with Variance Reduction 1
Strategic Classification with Graph Neural Networks 4
Strong inductive biases provably prevent harmless interpolation 3
StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training 5
Structure by Architecture: Structured Representations without Regularization 5
StyleMorph: Disentangled 3D-Aware Image Synthesis with a 3D Morphable StyleGAN 1
Sub-Task Decomposition Enables Learning in Sequence to Sequence Tasks 4
Subquadratic Algorithms for Kernel Matrices via Kernel Density Estimation 2
Subsampling in Large Graphs Using Ricci Curvature 4
Summarization Programs: Interpretable Abstractive Summarization with Neural Modular Trees 6
Supervision Complexity and its Role in Knowledge Distillation 3
Suppressing the Heterogeneity: A Strong Feature Extractor for Few-shot Segmentation 4
Surgical Fine-Tuning Improves Adaptation to Distribution Shifts 3
Switch-NeRF: Learning Scene Decomposition with Mixture of Experts for Large-scale Neural Radiance Fields 5
Symbolic Physics Learner: Discovering governing equations via Monte Carlo tree search 5
Symmetric Pruning in Quantum Neural Networks 2
Symmetries, Flat Minima, and the Conserved Quantities of Gradient Flow 3
Synthetic Data Generation of Many-to-Many Datasets via Random Graph Generation 6
Systematic Rectification of Language Models via Dead-end Analysis 4
TANGOS: Regularizing Tabular Neural Networks through Gradient Orthogonalization and Specialization 6
TDR-CL: Targeted Doubly Robust Collaborative Learning for Debiased Recommendations 5
TEMPERA: Test-Time Prompt Editing via Reinforcement Learning 5
TILP: Differentiable Learning of Temporal Logical Rules on Knowledge Graphs 3
TTN: A Domain-Shift Aware Batch Normalization in Test-Time Adaptation 3
TVSPrune - Pruning Non-discriminative filters via Total Variation separability of intermediate representations without fine tuning 6
TabCaps: A Capsule Neural Network for Tabular Data Classification with BoW Routing 6
TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second 6
Tailoring Language Generation Models under Total Variation Distance 4
Taking a Step Back with KCal: Multi-Class Kernel-Based Calibration for Deep Neural Networks 5
Targeted Hyperparameter Optimization with Lexicographic Preferences Over Multiple Objectives 5
Task Ambiguity in Humans and Language Models 4
Task-Aware Information Routing from Common Representation Space in Lifelong Learning 3
Task-customized Masked Autoencoder via Mixture of Cluster-conditional Experts 3
TaskPrompter: Spatial-Channel Multi-Task Prompting for Dense Scene Understanding 4
Teacher Guided Training: An Efficient Framework for Knowledge Transfer 2
TempCLR: Temporal Alignment Representation with Contrastive Learning 5
Temperature Schedules for self-supervised contrastive methods on long-tail data 5
Temporal Coherent Test Time Optimization for Robust Video Classification 2
Temporal Dependencies in Feature Importance for Time Series Prediction 6
Temporal Disentanglement of Representations for Improved Generalisation in Reinforcement Learning 5
Temporal Domain Generalization with Drift-Aware Dynamic Neural Networks 5
Tensor-Based Sketching Method for the Low-Rank Approximation of Data Streams. 4
Test-Time Adaptation via Self-Training with Nearest Neighbor Information 6
Test-Time Robust Personalization for Federated Learning 5
Text Summarization with Oracle Expectation 6
TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven Optimization 5
TextShield: Beyond Successfully Detecting Adversarial Sentences in text classification 4
Thalamus: a brain-inspired algorithm for biologically-plausible continual learning and disentangled representations 4
That Label's got Style: Handling Label Style Bias for Uncertain Image Segmentation 3
The Asymmetric Maximum Margin Bias of Quasi-Homogeneous Neural Networks 3
The Augmented Image Prior: Distilling 1000 Classes by Extrapolating from a Single Image 5
The Best of Both Worlds: Accurate Global and Personalized Models through Federated Learning with Data-Free Hyper-Knowledge Distillation 4
The Curious Case of Benign Memorization 3
The Dark Side of AutoML: Towards Architectural Backdoor Search 4
The Devil is in the Wrongly-classified Samples: Towards Unified Open-set Recognition 5
The Implicit Bias of Minima Stability in Multivariate Shallow ReLU Networks 3
The In-Sample Softmax for Offline Reinforcement Learning 4
The Influence of Learning Rule on Representation Dynamics in Wide Neural Networks 2
The KFIoU Loss for Rotated Object Detection 5
The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers 3
The Lie Derivative for Measuring Learned Equivariance 5
The Modality Focusing Hypothesis: Towards Understanding Crossmodal Knowledge Distillation 5
The Onset of Variance-Limited Behavior for Networks in the Lazy and Rich Regimes 3
The Power of Regularization in Solving Extensive-Form Games 2
The Provable Benefit of Unsupervised Data Sharing for Offline Reinforcement Learning 3
The Role of Coverage in Online Reinforcement Learning 1
The Role of ImageNet Classes in Fréchet Inception Distance 6
The Surprising Computational Power of Nondeterministic Stack RNNs 4
The Surprising Effectiveness of Equivariant Models in Domains with Latent Symmetry 5
The Symmetric Generalized Eigenvalue Problem as a Nash Equilibrium 5
The Tilted Variational Autoencoder: Improving Out-of-Distribution Detection 4
The Trade-off between Universality and Label Efficiency of Representations from Contrastive Learning 4
The hidden uniform cluster prior in self-supervised learning 4
Theoretical Characterization of the Generalization Performance of Overfitted Meta-Learning 3
This Looks Like It Rather Than That: ProtoKNN For Similarity-Based Classifiers 3
TiAda: A Time-scale Adaptive Algorithm for Nonconvex Minimax Optimization 3
Tier Balancing: Towards Dynamic Fairness over Underlying Causal Factors 2
Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detection 5
Time to augment self-supervised visual representation learning 5
TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis 6
Timing is Everything: Learning to Act Selectively with Costly Actions and Budgetary Constraints 3
Toeplitz Neural Network for Sequence Modeling 5
Token Merging: Your ViT But Faster 6
Topology-aware Robust Optimization for Out-of-Distribution Generalization 5
Toward Adversarial Training on Contextualized Language Representation 6
Towards Addressing Label Skews in One-Shot Federated Learning 6
Towards Better Selective Classification 5
Towards Effective and Interpretable Human-Agent Collaboration in MOBA Games: A Communication Perspective 2
Towards Inferential Reproducibility of Machine Learning Research 4
Towards Interpretable Deep Reinforcement Learning with Human-Friendly Prototypes 4
Towards Lightweight, Model-Agnostic and Diversity-Aware Active Anomaly Detection 4
Towards Minimax Optimal Reward-free Reinforcement Learning in Linear MDPs 1
Towards One-shot Neural Combinatorial Solvers: Theoretical and Empirical Notes on the Cardinality-Constrained Case 6
Towards Open Temporal Graph Neural Networks 5
Towards Robust Object Detection Invariant to Real-World Domain Shifts 4
Towards Robustness Certification Against Universal Perturbations 5
Towards Smooth Video Composition 4
Towards Stable Test-time Adaptation in Dynamic Wild World 5
Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning 1
Towards Understanding GD with Hard and Conjugate Pseudo-labels for Test-Time Adaptation 2
Towards Understanding Why Mask Reconstruction Pretraining Helps in Downstream Tasks 1
Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning 5
Towards a Unified Theoretical Understanding of Non-contrastive Learning via Rank Differential Mechanism 5
Towards convergence to Nash equilibria in two-team zero-sum games 2
Towards the Generalization of Contrastive Self-Supervised Learning 2
Trading Information between Latents in Hierarchical Variational Autoencoders 4
Trainability Preserving Neural Pruning 6
Trainable Weight Averaging: Efficient Training by Optimizing Historical Solutions 5
Training language models to summarize narratives improves brain alignment 5
Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis 4
TranSpeech: Speech-to-Speech Translation With Bilateral Perturbation 3
Transfer Learning with Deep Tabular Models 5
Transfer NAS with Meta-learned Bayesian Surrogates 5
Transferable Unlearnable Examples 4
Transformer Meets Boundary Value Inverse Problems 5
Transformer-Patcher: One Mistake Worth One Neuron 5
Transformer-based World Models Are Happy With 100k Interactions 5
Transformer-based model for symbolic regression via joint supervised learning 5
Transformers Learn Shortcuts to Automata 3
Transformers are Sample-Efficient World Models 5
Treeformer: Dense Gradient Trees for Efficient Attention Computation 4
TrojText: Test-time Invisible Textual Trojan Insertion 5
Truncated Diffusion Probabilistic Models and Diffusion-based Adversarial Auto-Encoders 6
Truthful Self-Play 3
Tuning Frequency Bias in Neural Network Training with Nonuniform Data 2
Turning the Curse of Heterogeneity in Federated Learning into a Blessing for Out-of-Distribution Detection 3
TypeT5: Seq2seq Type Inference using Static Analysis 5
UL2: Unifying Language Learning Paradigms 6
UNICORN: A Unified Backdoor Trigger Inversion Framework 5
UNIFIED-IO: A Unified Model for Vision, Language, and Multi-modal Tasks 3
Unbiased Stochastic Proximal Solver for Graph Neural Networks with Equilibrium States 5
Unbiased Supervised Contrastive Learning 5
Understanding DDPM Latent Codes Through Optimal Transport 3
Understanding Edge-of-Stability Training Dynamics with a Minimalist Example 2
Understanding Embodied Reference with Touch-Line Transformer 5
Understanding Influence Functions and Datamodels via Harmonic Analysis 3
Understanding Neural Coding on Latent Manifolds by Sharing Features and Dividing Ensembles 3
Understanding The Robustness of Self-supervised Learning Through Topic Modeling 4
Understanding Train-Validation Split in Meta-Learning with Neural Networks 3
Understanding Why Generalized Reweighting Does Not Improve Over ERM 2
Understanding Zero-shot Adversarial Robustness for Large-Scale Models 4
Understanding and Adopting Rational Behavior by Bellman Score Estimation 2
Understanding new tasks through the lens of training data via exponential tilting 5
Understanding the Covariance Structure of Convolutional Filters 3
Understanding the Generalization of Adam in Learning Neural Networks with Proper Regularization 2
Understanding the Role of Nonlinearity in Training Dynamics of Contrastive Learning 2
Understanding weight-magnitude hyperparameters in training binary networks 4
Uni-Mol: A Universal 3D Molecular Representation Learning Framework 6
UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph 4
UniMax: Fairer and More Effective Language Sampling for Large-Scale Multilingual Pretraining 6
Unicom: Universal and Compact Representation Learning for Image Retrieval 5
Unified Detoxifying and Debiasing in Language Generation via Inference-time Adaptive Optimization 4
Unified Discrete Diffusion for Simultaneous Vision-Language Generation 4
Uniform-in-time propagation of chaos for the mean-field gradient Langevin dynamics 1
Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matching 4
Universal Vision-Language Dense Retrieval: Learning A Unified Representation Space for Multi-Modal Retrieval 4
Unmasking the Lottery Ticket Hypothesis: What's Encoded in a Winning Ticket's Mask? 3
Unsupervised 3D Object Learning through Neuron Activity aware Plasticity 2
Unsupervised Learning for Combinatorial Optimization Needs Meta Learning 7
Unsupervised Manifold Alignment with Joint Multidimensional Scaling 5
Unsupervised Meta-learning via Few-shot Pseudo-supervised Contrastive Learning 6
Unsupervised Model Selection for Time Series Anomaly Detection 6
Unsupervised Semantic Segmentation with Self-supervised Object-centric Representations 6
Unsupervised visualization of image datasets using contrastive learning 6
Unveiling the sampling density in non-uniform geometric graphs 3
User-Interactive Offline Reinforcement Learning 6
Using Both Demonstrations and Language Instructions to Efficiently Learn Robotic Tasks 5
Using Language to Extend to Unseen Domains 5
VA-DepthNet: A Variational Approach to Single Image Depth Prediction 6
VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training 4
VIPeR: Provably Efficient Algorithm for Offline RL with Neural Function Approximation 5
Valid P-Value for Deep Learning-driven Salient Region 4
Value Memory Graph: A Graph-Structured World Model for Offline Reinforcement Learning 5
Variance Reduction is an Antidote to Byzantines: Better Rates, Weaker Assumptions and Communication Compression as a Cherry on the Top 6
Variance-Aware Sparse Linear Bandits 1
Variational Information Pursuit for Interpretable Predictions 5
Variational Latent Branching Model for Off-Policy Evaluation 5
Verifying the Union of Manifolds Hypothesis for Image Data 5
Versatile Neural Processes for Learning Implicit Neural Representations 2
Video Scene Graph Generation from Single-Frame Weak Supervision 3
View Synthesis with Sculpted Neural Points 5
ViewCo: Discovering Text-Supervised Segmentation Masks via Multi-View Semantic Consistency 4
Vision Transformer Adapter for Dense Predictions 4
Visual Classification via Description from Large Language Models 3
Visual Imitation Learning with Patch Rewards 4
Visual Recognition with Deep Nearest Centroids 6
Visually-Augmented Language Modeling 4
VoGE: A Differentiable Volume Renderer using Gaussian Ellipsoids for Analysis-by-Synthesis 4
Voint Cloud: Multi-View Point Cloud Representation for 3D Understanding 5
Volumetric Optimal Transportation by Fast Fourier Transform 3
Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstruction 3
Warping the Space: Weight Space Rotation for Class-Incremental Few-Shot Learning 5
Wasserstein Auto-encoded MDPs: Formal Verification of Efficiently Distilled RL Policies with Many-sided Guarantees 6
Weakly Supervised Explainable Phrasal Reasoning with Neural Fuzzy Logic 4
Weakly Supervised Knowledge Transfer with Probabilistic Logical Reasoning for Object Detection 5
Weakly-supervised HOI Detection via Prior-guided Bi-level Representation Learning 5
Weighted Clock Logic Point Process 7
Weighted Ensemble Self-Supervised Learning 5
What Can we Learn From The Selective Prediction And Uncertainty Estimation Performance Of 523 Imagenet Classifiers? 5
What Do Self-Supervised Vision Transformers Learn? 5
What Is Missing in IRM Training and Evaluation? Challenges and Solutions 4
What Makes Convolutional Models Great on Long Sequence Modeling? 5
What shapes the loss landscape of self supervised learning? 2
When Data Geometry Meets Deep Function: Generalizing Offline Reinforcement Learning 5
When Source-Free Domain Adaptation Meets Learning with Noisy Labels 3
When and Why Vision-Language Models Behave like Bags-Of-Words, and What to Do About It? 5
When to Make and Break Commitments? 3
Where to Begin? On the Impact of Pre-Training and Initialization in Federated Learning 4
Where to Diffuse, How to Diffuse, and How to Get Back: Automated Learning for Multivariate Diffusions 3
Which Layer is Learning Faster? A Systematic Exploration of Layer-wise Convergence Rate for Deep Neural Networks 2
Why (and When) does Local SGD Generalize Better than SGD? 6
Why adversarial training can hurt robust accuracy 3
WiNeRT: Towards Neural Ray Tracing for Wireless Channel Modelling and Differentiable Simulations 4
WikiWhy: Answering and Explaining Cause-and-Effect Questions 4
Win: Weight-Decay-Integrated Nesterov Acceleration for Adaptive Gradient Algorithms 4
Winning Both the Accuracy of Floating Point Activation and the Simplicity of Integer Arithmetic 3
Words are all you need? Language as an approximation for human similarity judgments 4
Write and Paint: Generative Vision-Language Models are Unified Modal Learners 5
Your Contrastive Learning Is Secretly Doing Stochastic Neighbor Embedding 3
Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model 5
Zeroth-Order Optimization with Trajectory-Informed Derivative Estimation 4
ZiCo: Zero-shot NAS via inverse Coefficient of Variation on Gradients 6
f-DM: A Multi-stage Diffusion Model via Progressive Signal Transformation 3
gDDIM: Generalized denoising diffusion implicit models 5
kNN-Diffusion: Image Generation via Large-Scale Retrieval 5
simpleKT: A Simple But Tough-to-Beat Baseline for Knowledge Tracing 5
wav2tok: Deep Sequence Tokenizer for Audio Retrieval 4
​​What learning algorithm is in-context learning? Investigations with linear models 3