Downloads 2022
Number of events: 2986
- α-ReQ : Assessing Representation Quality in Self-Supervised Learning by measuring eigenspectrum decay
- k-Sliced Mutual Information: A Quantitative Study of Scalability with Dimension
- 360-MLC: Multi-view Layout Consistency for Self-training and Hyper-parameter Tuning
- 3DB: A Framework for Debugging Computer Vision Models
- 3D Concept Grounding on Neural Fields
- 3DILG: Irregular Latent Grids for 3D Generative Modeling
- 3DOS: Towards 3D Open Set Learning - Benchmarking and Understanding Semantic Novelty Detection on Point Clouds
- 3rd Offline Reinforcement Learning Workshop: Offline RL as a "Launchpad"
- 4D Unsupervised Object Discovery
- 5th Robot Learning Workshop: Trustworthy Robotics
- A2: Efficient Automated Attacker for Boosting Adversarial Training
- A Benchmark for Compositional Visual Reasoning
- A Best-of-Both-Worlds Algorithm for Bandits with Delayed Feedback
- A Boosting Approach to Reinforcement Learning
- A Bregman Learning Framework for Sparse Neural Networks
- A Causal Analysis of Harm
- A causal view on dynamical systems
- Accelerated Linearized Laplace Approximation for Bayesian Deep Learning
- Accelerated Primal-Dual Gradient Method for Smooth and Convex-Concave Saddle-Point Problems with Bilinear Coupling
- Accelerated Projected Gradient Algorithms for Sparsity Constrained Optimization Problems
- Accelerated Training of Physics-Informed Neural Networks (PINNs) using Meshless Discretizations
- Accelerated Zeroth-Order and First-Order Momentum Methods from Mini to Minimax Optimization
- Accelerating Certified Robustness Training via Knowledge Transfer
- Accelerating SGD for Highly Ill-Conditioned Huge-Scale Online Matrix Completion
- Accelerating Sparse Convolution with Column Vector-Wise Sparsity
- Acceleration in Distributed Sparse Regression
- A Characterization of Semi-Supervised Adversarially Robust PAC Learnability
- A Character-Level Length-Control Algorithm for Non-Autoregressive Sentence Summarization
- ACIL: Analytic Class-Incremental Learning with Absolute Memorization and Privacy Protection
- A Classification of G-invariant Shallow Neural Networks
- A Closer Look at Learned Optimization: Stability, Robustness, and Inductive Biases
- A Closer Look at Offline RL Agents
- A Closer Look at Prototype Classifier for Few-shot Image Classification
- A Closer Look at the Adversarial Robustness of Deep Equilibrium Models
- A Closer Look at Weakly-Supervised Audio-Visual Source Localization
- A Combinatorial Perspective on the Optimization of Shallow ReLU Networks
- A Communication-efficient Algorithm with Linear Convergence for Federated Minimax Learning
- A Communication-Efficient Distributed Gradient Clipping Algorithm for Training Deep Neural Networks
- A composable machine-learning approach for steady-state simulations on high-resolution grids
- A Comprehensive Study on Large-Scale Graph Training: Benchmarking and Rethinking
- A Conditional Randomization Test for Sparse Logistic Regression in High-Dimension
- A Consistent and Differentiable Lp Canonical Calibration Error Estimator
- A consistently adaptive trust-region method
- A Consolidated Cross-Validation Algorithm for Support Vector Machines via Data Reduction
- A Continuous Time Framework for Discrete Denoising Models
- A Contrastive Framework for Neural Text Generation
- A contrastive rule for meta-learning
- A Coupled Design of Exploiting Record Similarity for Practical Vertical Federated Learning
- Action-modulated midbrain dopamine activity arises from distributed control policies
- ActionSense: A Multimodal Dataset and Recording Framework for Human Activities Using Wearable Sensors in a Kitchen Environment
- Active Bayesian Causal Inference
- Active Exploration for Inverse Reinforcement Learning
- Active Labeling: Streaming Stochastic Gradients
- Active Learning for Multiple Target Models
- Active Learning Helps Pretrained Models Learn the Intended Task
- Active Learning of Classifiers with Label and Seed Queries
- Active Learning Polynomial Threshold Functions
- Active Learning Through a Covering Lens
- Active Learning with Neural Networks: Insights from Nonparametric Statistics
- Active Learning with Safety Constraints
- Active-Passive SimStereo - Benchmarking the Cross-Generalization Capabilities of Deep Learning-based Stereo Methods
- Active Ranking without Strong Stochastic Transitivity
- Active Surrogate Estimators: An Active Learning Approach to Label-Efficient Model Evaluation
- AdaFocal: Calibration-aware Adaptive Focal Loss
- Adam Can Converge Without Any Modification On Update Rules
- A Damped Newton Method Achieves Global O(1k2) and Local Quadratic Convergence Rate
- Adaptation Accelerating Sampling-based Bayesian Inference in Attractor Neural Networks
- AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition
- Adapting Self-Supervised Vision Transformers by Probing Attention-Conditioned Masking Consistency
- Adapting to Online Label Shift with Provable Guarantees
- Adaptive Data Debiasing through Bounded Exploration
- Adaptive Distribution Calibration for Few-Shot Learning with Hierarchical Optimal Transport
- Adaptive Interest for Emphatic Reinforcement Learning
- Adaptively Exploiting d-Separators with Causal Bandits
- Adaptive Multi-stage Density Ratio Estimation for Learning Latent Space Energy-based Model
- Adaptive Oracle-Efficient Online Learning
- Adaptive Sampling for Discovery
- Adaptive Stochastic Variance Reduction for Non-convex Finite-Sum Minimization
- A Data-Augmentation Is Worth A Thousand Samples: Analytical Moments And Sampling-Free Training
- A Dataset for Efforts Towards Achieving the Sustainable Development Goal of Safe Working Environments
- ADBench: Anomaly Detection Benchmark
- Additive MIL: Intrinsically Interpretable Multiple Instance Learning for Pathology
- Addressing Leakage in Concept Bottleneck Models
- Addressing Resource Scarcity across Sign Languages with Multilingual Pretraining and Unified-Vocabulary Datasets
- AD-DROP: Attribution-Driven Dropout for Robust Language Model Fine-Tuning
- A Deep Learning Dataloader with Shared Data Preparation
- A Deep Reinforcement Learning Framework for Column Generation
- A Differentiable Semantic Metric Approximation in Probabilistic Embedding for Cross-Modal Retrieval
- A Differentially Private Linear-Time fPTAS for the Minimum Enclosing Ball Problem
- A Direct Approximation of AIXI Using Logical State Abstractions
- Adjoint-aided inference of Gaussian process driven differential equations
- Advances in Bayesian Optimization
- Advances in NLP and their Applications to Healthcare
- Advancing Model Pruning via Bi-level Optimization
- Adv-Attribute: Inconspicuous and Transferable Adversarial Attack on Face Recognition
- Adversarial Attack on Attackers: Post-Process to Mitigate Black-Box Score-Based Query Attacks
- Adversarial Auto-Augment with Label Preservation: A Representation Learning Principle Guided Approach
- Adversarially Robust Learning: A Generic Minimax Optimal Learner and Characterization
- Adversarial Reprogramming Revisited
- Adversarial Robustness is at Odds with Lazy Training
- Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentation
- Adversarial Task Up-sampling for Meta-learning
- Adversarial training for high-stakes reliability
- Adversarial Training with Complementary Labels: On the Benefit of Gradually Informative Attacks
- Adversarial Unlearning: Reducing Confidence Along Adversarial Directions
- A Fast Post-Training Pruning Framework for Transformers
- A Fast Scale-Invariant Algorithm for Non-negative Least Squares with Non-negative Data
- A Few Expert Queries Suffices for Sample-Efficient RL with Resets and Linear Value Approximation
- A Fourier Approach to Mixture Learning
- A framework for bilevel optimization that enables stochastic and global variance reduction algorithms
- A general approximation lower bound in Lp norm, with applications to feed-forward neural networks
- A General Framework for Auditing Differentially Private Machine Learning
- A Geometric Perspective on Variational Autoencoders
- A gradient estimator via L1-randomization for online zero-order optimization with two point feedback
- A gradient sampling method with complexity guarantees for Lipschitz functions in high and low dimensions
- AgraSSt: Approximate Graph Stein Statistics for Interpretable Assessment of Implicit Graph Generators
- A Greek Parliament Proceedings Dataset for Computational Linguistics and Political Analysis
- Agreement-on-the-line: Predicting the Performance of Neural Networks under Distribution Shift
- AI for Accelerated Materials Design (AI4Mat)
- AI for Science: Progress and Promises
- AirfRANS: High Fidelity Computational Fluid Dynamics Dataset for Approximating Reynolds-Averaged Navier–Stokes Solutions
- A Kernelised Stein Statistic for Assessing Implicit Generative Models
- A Lagrangian Duality Approach to Active Learning
- A Large Scale Search Dataset for Unbiased Learning to Rank
- Algorithmic fairness: at the intersections
- Algorithmic Fairness through the Lens of Causality and Privacy
- Algorithms and Hardness for Learning Linear Thresholds from Label Proportions
- Algorithms On the Bench: Examining Validity of ML Systems in the Public Sphere
- Algorithms that Approximate Data Removal: New Results and Limitations
- Algorithms with Prediction Portfolios
- ALIFE: Adaptive Logit Regularizer and Feature Replay for Incremental Semantic Segmentation
- Aligning individual brains with fused unbalanced Gromov Wasserstein
- Alignment-guided Temporal Attention for Video Action Recognition
- Align then Fusion: Generalized Large-scale Multi-view Clustering with Anchor Matching Correspondences
- Alleviating Adversarial Attacks on Variational Autoencoders with MCMC
- Alleviating "Posterior Collapse'' in Deep Topic Models via Policy Gradient
- Alleviating the Sample Selection Bias in Few-shot Learning by Removing Projection to the Centroid
- All Politics is Local: Redistricting via Local Fairness
- All Things Attention: Bridging Different Perspectives on Attention
- All You Need is a Good Functional Prior for Bayesian Deep Learning
- ALMA: Hierarchical Learning for Composite Multi-Agent Tasks
- A Lower Bound of Hash Codes' Performance
- Alternating Mirror Descent for Constrained Min-Max Games
- Ambiguous Images With Human Judgments for Robust Visual Event Classification
- A Mean-Field Game Approach to Cloud Resource Management with Function Approximation
- A Mixture Of Surprises for Unsupervised Reinforcement Learning
- Amortized Inference for Causal Structure Learning
- Amortized Inference for Heterogeneous Reconstruction in Cryo-EM
- Amortized Mixing Coupling Processes for Clustering
- Amortized Projection Optimization for Sliced Wasserstein Generative Models
- Amortized Proximal Optimization
- AMOS: A Large-Scale Abdominal Multi-Organ Benchmark for Versatile Medical Image Segmentation
- AMP: Automatically Finding Model Parallel Strategies with Heterogeneity Awareness
- Amplifying Membership Exposure via Data Poisoning
- A Multilabel Classification Framework for Approximate Nearest Neighbor Search
- A Multi-Resolution Framework for U-Nets with Applications to Hierarchical VAEs
- A Multi-Task Benchmark for Korean Legal Language Understanding and Judgement Prediction
- An α-No-Regret Algorithm For Graphical Bilinear Bandits
- An α-regret analysis of Adversarial Bilateral Trade
- An Adaptive Deep RL Method for Non-Stationary Environments with Piecewise Stable Context
- An Adaptive Kernel Approach to Federated Learning of Heterogeneous Causal Effects
- An Algorithm for Learning Switched Linear Dynamics from Data
- Analyzing Data-Centric Properties for Graph Contrastive Learning
- Analyzing Lottery Ticket Hypothesis from PAC-Bayesian Theory Perspective
- Analyzing Sharpness along GD Trajectory: Progressive Sharpening and Edge of Stability
- An Analysis of Ensemble Sampling
- An Analytical Theory of Curriculum Learning in Teacher-Student Networks
- An Asymptotically Optimal Batched Algorithm for the Dueling Bandit Problem
- Anchor-Changing Regularized Natural Policy Gradient for Multi-Objective Reinforcement Learning
- A Near-Optimal Best-of-Both-Worlds Algorithm for Online Learning with Feedback Graphs
- A Near-Optimal Primal-Dual Method for Off-Policy Learning in CMDP
- An efficient graph generative model for navigating ultra-large combinatorial synthesis libraries
- An Embarrassingly Simple Approach to Semi-Supervised Few-Shot Learning
- An empirical analysis of compute-optimal large language model training
- An Empirical Study on Disentanglement of Negative-free Contrastive Learning
- A Neural Corpus Indexer for Document Retrieval
- A Neural Pre-Conditioning Active Learning Algorithm to Reduce Label Complexity
- A new dataset for multilingual keyphrase generation
- A New Family of Generalization Bounds Using Samplewise Evaluated CMI
- AniFaceGAN: Animatable 3D-Aware Face Image Generation for Video Avatars
- AnimeRun: 2D Animation Visual Correspondence from Open Source 3D Movies
- AnimeSR: Learning Real-World Super-Resolution Models for Animation Videos
- An In-depth Study of Stochastic Backpropagation
- An Information-Theoretic Framework for Deep Learning
- An Investigation into Whitening Loss for Self-supervised Learning
- Annihilation of Spurious Minima in Two-Layer ReLU Networks
- A Non-asymptotic Analysis of Non-parametric Temporal-Difference Learning
- A Non-Asymptotic Moreau Envelope Theory for High-Dimensional Generalized Linear Models
- A Nonconvex Framework for Structured Dynamic Covariance Recovery
- Anonymized Histograms in Intermediate Privacy Models
- Anonymous Bandits for Multi-User Systems
- AnoShift: A Distribution Shift Benchmark for Unsupervised Anomaly Detection
- Anticipating Performativity by Predicting from Predictions
- Antigen-Specific Antibody Design and Optimization with Diffusion-Based Generative Models for Protein Structures
- Anytime-Valid Inference For Multinomial Count Data
- A PAC-Bayesian Generalization Bound for Equivariant Networks
- A permutation-free kernel two-sample test
- APG: Adaptive Parameter Generation Network for Click-Through Rate Prediction
- A Policy-Guided Imitation Approach for Offline Reinforcement Learning
- Approaching Quartic Convergence Rates for Quasi-Stochastic Approximation with Application to Gradient-Free Optimization
- Approximate Euclidean lengths and distances beyond Johnson-Lindenstrauss
- Approximate Secular Equations for the Cubic Regularization Subproblem
- Approximate Value Equivalence
- Approximation with CNNs in Sobolev Space: with Applications to Classification
- A Practical, Progressively-Expressive GNN
- A Primer for Neural Arithmetic Logic Modules
- A Probabilistic Graph Coupling View of Dimension Reduction
- A Projection-free Algorithm for Constrained Stochastic Multi-level Composition Optimization
- APT-36K: A Large-scale Benchmark for Animal Pose Estimation and Tracking
- A Quadrature Rule combining Control Variates and Adaptive Importance Sampling
- A Quantitative Geometric Approach to Neural-Network Smoothness
- Archimedes Meets Privacy: On Privately Estimating Quantiles in High Dimensions Under Minimal Assumptions
- Are all Frames Equal? Active Sparse Labeling for Video Action Detection
- Are All Losses Created Equal: A Neural Collapse Perspective
- Are AlphaZero-like Agents Robust to Adversarial Perturbations?
- Are Defenses for Graph Neural Networks Robust?
- A Reduction to Binary Approach for Debiasing Multiclass Datasets
- Are GANs overkill for NLP?
- A Regret-Variance Trade-Off in Online Learning
- A Reparametrization-Invariant Sharpness Measure Based on Information Geometry
- Are Two Heads the Same as One? Identifying Disparate Treatment in Fair Neural Networks
- Are You Stealing My Model? Sample Correlation for Fingerprinting Deep Neural Networks
- A Robust Phased Elimination Algorithm for Corruption-Tolerant Gaussian Process Bandits
- A Rotated Hyperbolic Wrapped Normal Distribution for Hierarchical Representation Learning
- A Scalable Deterministic Global Optimization Algorithm for Training Optimal Decision Tree
- A sharp NMF result with applications in network modeling
- A Simple and Optimal Policy Design for Online Learning with Safety against Heavy-tailed Risk
- A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits
- A Simple Approach to Automated Spectral Clustering
- A simple but strong baseline for online continual learning: Repeated Augmented Rehearsal
- A Simple Decentralized Cross-Entropy Method
- A Single-timescale Analysis for Stochastic Approximation with Multiple Coupled Sequences
- Ask4Help: Learning to Leverage an Expert for Embodied Tasks
- A Solver-free Framework for Scalable Learning in Neural ILP Architectures
- A Spectral Approach to Item Response Theory
- ASPiRe: Adaptive Skill Priors for Reinforcement Learning
- Assaying Out-Of-Distribution Generalization in Transfer Learning
- Assistive Teaching of Motor Control Tasks to Humans
- Associating Objects and Their Effects in Video through Coordination Games
- Association Graph Learning for Multi-Task Classification with Category Shifts
- A Statistical Online Inference Approach in Averaged Stochastic Approximation
- A Stochastic Linearized Augmented Lagrangian Method for Decentralized Bilevel Optimization
- A Survey and Datasheet Repository of Publicly Available US Criminal Justice Datasets
- Asymmetric Temperature Scaling Makes Larger Networks Teach Well Again
- Asymptotically Unbiased Instance-wise Regularized Partial AUC Optimization: Theory and Algorithm
- Asymptotic Behaviors of Projected Stochastic Approximation: A Jump Diffusion Perspective
- Asymptotic Properties for Bayesian Neural Network in Besov Space
- Asymptotics of ℓ2 Regularized Network Embeddings
- Asymptotics of smoothed Wasserstein distances in the small noise regime
- Asynchronous Actor-Critic for Multi-Agent Reinforcement Learning
- Asynchronous SGD Beats Minibatch SGD Under Arbitrary Delays
- ATD: Augmenting CP Tensor Decomposition by Self Supervision
- A Theoretical Framework for Inference Learning
- A Theoretical Study on Solving Continual Learning
- A Theoretical Understanding of Gradient Bias in Meta-Reinforcement Learning
- A Theoretical View on Sparsely Activated Networks
- A Theory of PAC Learnability under Transformation Invariances
- A theory of weight distribution-constrained learning
- A time-resolved theory of information encoding in recurrent neural networks
- A Transformer-Based Object Detector with Coarse-Fine Crossing Representations
- AttCAT: Explaining Transformers via Attentive Class Activation Tokens
- Attention-based Neural Cellular Automata
- Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptation
- Attraction-Repulsion Spectrum in Neighbor Embeddings
- Audio-Driven Co-Speech Gesture Video Generation
- Augmentations in Hypergraph Contrastive Learning: Fabricated and Generative
- Augmented RBMLE-UCB Approach for Adaptive Control of Linear Quadratic Systems
- Augmenting Online Algorithms with ε-Accurate Predictions
- A Unified Analysis of Federated Learning with Arbitrary Client Participation
- A Unified Analysis of Mixed Sample Data Augmentation: A Loss Function Perspective
- A Unified Convergence Theorem for Stochastic Optimization Methods
- A Unified Diversity Measure for Multiagent Reinforcement Learning
- A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks
- A Unified Framework for Alternating Offline Model Training and Policy Learning
- A Unified Framework for Deep Symbolic Regression
- A Unified Hard-Constraint Framework for Solving Geometrically Complex PDEs
- A Unified Model for Multi-class Anomaly Detection
- A Unified Sequence Interface for Vision Tasks
- A Unified Statistical Learning Model for Rankings and Scores with Application to Grant Panel Review
- A Unifying Framework for Online Optimization with Long-Term Constraints
- A Unifying Framework of Off-Policy General Value Function Evaluation
- A Universal Error Measure for Input Predictions Applied to Online Graph Problems
- Autoformalization with Large Language Models
- Autoinverse: Uncertainty Aware Inversion of Neural Networks
- AutoLink: Self-supervised Learning of Human Skeletons and Object Outlines by Linking Keypoints
- AUTOMATA: Gradient Based Data Subset Selection for Compute-Efficient Hyper-parameter Tuning
- Automatic differentiation of nonsmooth iterative algorithms
- Automatic Differentiation of Programs with Discrete Randomness
- AutoML Two-Sample Test
- AutoMS: Automatic Model Selection for Novelty Detection with Error Rate Control
- AutoMTL: A Programming Framework for Automating Efficient Multi-Task Learning
- Autoregressive Perturbations for Data Poisoning
- Autoregressive Search Engines: Generating Substrings as Document Identifiers
- AutoST: Towards the Universal Modeling of Spatio-temporal Sequences
- AutoWS-Bench-101: Benchmarking Automated Weak Supervision with 100 Labels
- Avalon: A Benchmark for RL Generalization Using Procedurally Generated Worlds
- A Variant of Anderson Mixing with Minimal Memory Size
- A Variational Edge Partition Model for Supervised Graph Representation Learning
- Average Sensitivity of Euclidean k-Clustering
- AVLEN: Audio-Visual-Language Embodied Navigation in 3D Environments
- A Win-win Deal: Towards Sparse and Robust Pre-trained Language Models
- AZ-whiteness test: a test for signal uncorrelation on spatio-temporal graphs
- BackdoorBench: A Comprehensive Benchmark of Backdoor Learning
- Back Razor: Memory-Efficient Transfer Learning by Self-Sparsified Backpropagation
- BadPrompt: Backdoor Attacks on Continuous Prompts
- BagFlip: A Certified Defense Against Data Poisoning
- Bandit Theory and Thompson Sampling-Guided Directed Evolution for Sequence Optimization
- Batch Bayesian optimisation via density-ratio estimation with guarantees
- Batch Bayesian Optimization on Permutations using the Acquisition Weighted Kernel
- Batch Multi-Fidelity Active Learning with Budget Constraints
- Batch-Size Independent Regret Bounds for Combinatorial Semi-Bandits with Probabilistically Triggered Arms or Independent Arms
- Batch size-invariance for policy optimization
- Bayesian Active Learning with Fully Bayesian Gaussian Processes
- Bayesian Clustering of Neural Spiking Activity Using a Mixture of Dynamic Poisson Factor Analyzers
- Bayesian inference via sparse Hamiltonian flows
- Bayesian Optimistic Optimization: Optimistic Exploration for Model-based Reinforcement Learning
- Bayesian Optimization over Discrete and Mixed Spaces via Probabilistic Reparameterization
- Bayesian Persuasion for Algorithmic Recourse
- Bayesian Risk Markov Decision Processes
- Bayesian Spline Learning for Equation Discovery of Nonlinear Dynamics with Quantified Uncertainty
- Bayesian subset selection and variable importance for interpretable prediction and classification
- BayesPCN: A Continually Learnable Predictive Coding Associative Memory
- BEER: Fast O(1/T) Rate for Decentralized Nonconvex Optimization with Communication Compression
- Behavior Transformers: Cloning k modes with one stone
- Bellman Residual Orthogonalization for Offline Reinforcement Learning
- Benchmarking and Analyzing 3D Human Pose and Shape Estimation Beyond Algorithms
- Benchmarking Heterogeneous Treatment Effect Models through the Lens of Interpretability
- Benchopt: Reproducible, efficient and collaborative optimization benchmarks
- Benefits of Additive Noise in Composing Classes with Bounded Capacity
- Benefits of Permutation-Equivariance in Auction Mechanisms
- Benign Overfitting in Two-layer Convolutional Neural Networks
- Benign, Tempered, or Catastrophic: Toward a Refined Taxonomy of Overfitting
- Benign Underfitting of Stochastic Gradient Descent
- Bessel Equivariant Networks for Inversion of Transmission Effects in Multi-Mode Optical Fibres
- Best of Both Worlds Model Selection
- Better Best of Both Worlds Bounds for Bandits with Switching Costs
- Better SGD using Second-order Momentum
- Better Uncertainty Calibration via Proper Scores for Classification and Beyond
- Between Stochastic and Adversarial Online Convex Optimization: Improved Regret Bounds via Smoothness
- BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework
- Beyond accuracy: generalization properties of bio-plausible temporal credit assignment rules
- Beyond Adult and COMPAS: Fair Multi-Class Prediction via Information Projection
- Beyond black box densities: Parameter learning for the deviated components
- Beyond IID: data-driven decision-making in heterogeneous environments
- Beyond L1: Faster and Better Sparse Models with skglm
- Beyond Mahalanobis Distance for Textual OOD Detection
- Beyond neural scaling laws: beating power law scaling via data pruning
- Beyond Not-Forgetting: Continual Learning with Backward Knowledge Transfer
- Beyond Real-world Benchmark Datasets: An Empirical Study of Node Classification with GNNs
- Beyond Rewards: a Hierarchical Perspective on Offline Multiagent Behavioral Analysis
- Beyond Separability: Analyzing the Linear Transferability of Contrastive Representations to Related Subpopulations
- Beyond spectral gap: the role of the topology in decentralized learning
- Beyond the Best: Distribution Functional Estimation in Infinite-Armed Bandits
- Beyond the Return: Off-policy Function Estimation under User-specified Error-measuring Distributions
- Beyond Time-Average Convergence: Near-Optimal Uncoupled Online Learning via Clairvoyant Multiplicative Weights Update
- Bezier Gaussian Processes for Tall and Wide Data
- Bidirectional Learning for Offline Infinite-width Model-based Optimization
- Bi-directional Weakly Supervised Knowledge Distillation for Whole Slide Image Classification
- BigBio: A Framework for Data-Centric Biomedical Natural Language Processing
- BILCO: An Efficient Algorithm for Joint Alignment of Time Series
- BiMLP: Compact Binary Architectures for Vision Multi-Layer Perceptrons
- BinauralGrad: A Two-Stage Conditional Diffusion Probabilistic Model for Binaural Audio Synthesis
- Biological Learning of Irreducible Representations of Commuting Transformations
- Biologically Inspired Dynamic Thresholds for Spiking Neural Networks
- Biologically-plausible backpropagation through arbitrary timespans via local neuromodulators
- Biologically-Plausible Determinant Maximization Neural Networks for Blind Separation of Correlated Sources
- Biologically plausible solutions for spiking networks with efficient coding
- BiT: Robustly Binarized Multi-distilled Transformer
- Bivariate Causal Discovery for Categorical Data via Classification with Optimal Label Permutation
- Blackbox Attacks via Surrogate Ensemble Search
- Black-box coreset variational inference
- Black-Box Generalization: Stability of Zeroth-Order Learning
- Blessing of Depth in Linear Regression: Deeper Models Have Flatter Landscape Around the True Solution
- Block-Recurrent Transformers
- BLOX: Macro Neural Architecture Search Benchmark and Algorithms
- Blueprint for an AI Bill of Rights Making Automated Systems Work for the American People
- BMU-MoCo: Bidirectional Momentum Update for Continual Video-Language Modeling
- BOME! Bilevel Optimization Made Easy: A Simple First-Order Approach
- BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphs
- Boosting Barely Robust Learners: A New Perspective on Adversarial Robustness
- Boosting Out-of-distribution Detection with Typical Features
- Boosting the Performance of Generic Deep Neural Network Frameworks with Log-supermodular CRFs
- Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation
- Bootstrapped Transformer for Offline Reinforcement Learning
- Bounded-Regret MPC via Perturbation Analysis: Prediction Error, Constraints, and Nonlinearity
- Bounding and Approximating Intersectional Fairness through Marginal Fairness
- Brain Network Transformer
- Branch & Learn for Recursively and Iteratively Solvable Problems in Predict+Optimize
- Breaking Bad: A Dataset for Geometric Fracture and Reassembly
- Bridge the Gap Between Architecture Spaces via A Cross-Domain Predictor
- Bridging Central and Local Differential Privacy in Data Acquisition Mechanisms
- Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection
- Bridging the Gap Between Vision Transformers and Convolutional Neural Networks on Small Datasets
- Bridging the Gap from Asymmetry Tricks to Decorrelation Principles in Non-contrastive Self-supervised Learning
- Bridging the Gap: Unifying the Training and Evaluation of Neural Network Binary Classifiers
- Bringing Image Scene Structure to Video via Frame-Clip Consistency of Object Tokens
- Bring Your Own Algorithm for Optimal Differentially Private Stochastic Minimax Optimization
- Broadening Research Collaborations
- Brownian Noise Reduction: Maximizing Privacy Subject to Accuracy Constraints
- BR-SNIS: Bias Reduced Self-Normalized Importance Sampling
- BYOL-Explore: Exploration by Bootstrapped Prediction
- Byzantine Spectral Ranking
- Byzantine-tolerant federated Gaussian process regression for streaming data
- C2FAR: Coarse-to-Fine Autoregressive Networks for Precise Probabilistic Forecasting
- Cache-Augmented Inbatch Importance Resampling for Training Recommender Retriever
- CAESAR: An Embodied Simulator for Generating Multimodal Referring Expression Datasets
- CageNeRF: Cage-based Neural Radiance Field for Generalized 3D Deformation and Animation
- CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Clouds
- CalFAT: Calibrated Federated Adversarial Training with Label Skewness
- Calibrated Data-Dependent Constraints with Exact Satisfaction Guarantees
- Can Adversarial Training Be Manipulated By Non-Robust Features?
- Can Hybrid Geometric Scattering Networks Help Solve the Maximum Clique Problem?
- Can Push-forward Generative Models Fit Multimodal Distributions?
- Capturing Failures of Large Language Models via Human Cognitive Biases
- Capturing Graphs with Hypo-Elliptic Diffusions
- CARD: Classification and Regression Diffusion Models
- CARLANE: A Lane Detection Benchmark for Unsupervised Domain Adaptation from Simulation to multiple Real-World Domains
- CASA: Category-agnostic Skeletal Animal Reconstruction
- CascadeXML: Rethinking Transformers for End-to-end Multi-resolution Training in Extreme Multi-label Classification
- Category-Level 6D Object Pose Estimation in the Wild: A Semi-Supervised Learning Approach and A New Dataset
- CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks
- Causal Discovery in Heterogeneous Environments Under the Sparse Mechanism Shift Hypothesis
- Causal Discovery in Linear Latent Variable Models Subject to Measurement Error
- Causal Identification under Markov equivalence: Calculus, Algorithm, and Completeness
- Causal Inference with Non-IID Data using Linear Graphical Models
- Causality-driven Hierarchical Structure Discovery for Reinforcement Learning
- Causality Preserving Chaotic Transformation and Classification using Neurochaos Learning
- Causally motivated multi-shortcut identification and removal
- Causal Machine Learning for Real-World Impact
- CCCP is Frank-Wolfe in disguise
- CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior
- CEDe: A collection of expert-curated datasets with atom-level entity annotations for Optical Chemical Structure Recognition
- CEIP: Combining Explicit and Implicit Priors for Reinforcement Learning with Demonstrations
- Censored Quantile Regression Neural Networks for Distribution-Free Survival Analysis
- Certifying Robust Graph Classification under Orthogonal Gromov-Wasserstein Threats
- Certifying Some Distributional Fairness with Subpopulation Decomposition
- CGLB: Benchmark Tasks for Continual Graph Learning
- Chain of Thought Imitation with Procedure Cloning
- Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- Challenges in Deploying and Monitoring Machine Learning Systems
- Challenging Common Assumptions in Convex Reinforcement Learning
- Change Event Dataset for Discovery from Spatio-temporal Remote Sensing Imagery
- Change-point Detection for Sparse and Dense Functional Data in General Dimensions
- Chaotic Dynamics are Intrinsic to Neural Network Training with SGD
- Chaotic Regularization and Heavy-Tailed Limits for Deterministic Gradient Descent
- Characteristics of Harmful Text: Towards Rigorous Benchmarking of Language Models
- Characterization of Excess Risk for Locally Strongly Convex Population Risk
- Characterizing Datapoints via Second-Split Forgetting
- Characterizing the Ventral Visual Stream with Response-Optimized Neural Encoding Models
- Chartalist: Labeled Graph Datasets for UTXO and Account-based Blockchains
- Chefs' Random Tables: Non-Trigonometric Random Features
- CHIMLE: Conditional Hierarchical IMLE for Multimodal Conditional Image Synthesis
- Chromatic Correlation Clustering, Revisited
- Chroma-VAE: Mitigating Shortcut Learning with Generative Classifiers
- Class-Aware Adversarial Transformers for Medical Image Segmentation
- Class-Dependent Label-Noise Learning with Cycle-Consistency Regularization
- CLEAR: Generative Counterfactual Explanations on Graphs
- CLEVRER-Humans: Describing Physical and Causal Events the Human Way
- CLiMB: A Continual Learning Benchmark for Vision-and-Language Tasks
- ClimbQ: Class Imbalanced Quantization Enabling Robustness on Efficient Inferences
- CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders
- Clipped Stochastic Methods for Variational Inequalities with Heavy-Tailed Noise
- CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP
- Cluster and Aggregate: Face Recognition with Large Probe Set
- Cluster Randomized Designs for One-Sided Bipartite Experiments
- C-Mixup: Improving Generalization in Regression
- Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone
- Coded Residual Transform for Generalizable Deep Metric Learning
- CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning
- CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers
- COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics
- Collaborative Decision Making Using Action Suggestions
- Collaborative Learning by Detecting Collaboration Partners
- Collaborative Learning of Discrete Distributions under Heterogeneity and Communication Constraints
- Collaborative Linear Bandits with Adversarial Agents: Near-Optimal Regret Bounds
- Combinatorial Bandits with Linear Constraints: Beyond Knapsacks and Fairness
- Combining Explicit and Implicit Regularization for Efficient Learning in Deep Networks
- ComENet: Towards Complete and Efficient Message Passing for 3D Molecular Graphs
- ComGAN: Unsupervised Disentanglement and Segmentation via Image Composition
- ComMU: Dataset for Combinatorial Music Generation
- Communicating Natural Programs to Humans and Machines
- Communication Acceleration of Local Gradient Methods via an Accelerated Primal-Dual Algorithm with an Inexact Prox
- Communication-efficient distributed eigenspace estimation with arbitrary node failures
- Communication Efficient Distributed Learning for Kernelized Contextual Bandits
- Communication Efficient Federated Learning for Generalized Linear Bandits
- Communication-Efficient Topologies for Decentralized Learning with O(1) Consensus Rate
- Co-Modality Graph Contrastive Learning for Imbalanced Node Classification
- Composite Feature Selection Using Deep Ensembles
- Compositional Generalization in Unsupervised Compositional Representation Learning: A Study on Disentanglement and Emergent Language
- Compositional generalization through abstract representations in human and artificial neural networks
- Composition Theorems for Interactive Differential Privacy
- Compressible-composable NeRF via Rank-residual Decomposition
- Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs
- Concentration of Data Encoding in Parameterized Quantum Circuits
- Concept Activation Regions: A Generalized Framework For Concept-Based Explanations
- Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off
- Concrete Score Matching: Generalized Score Matching for Discrete Data
- Conditional Diffusion Process for Inverse Halftoning
- Conditional Independence Testing with Heteroskedastic Data and Applications to Causal Discovery
- Conditional Meta-Learning of Linear Representations
- Confidence-based Reliable Learning under Dual Noises
- Confident Adaptive Language Modeling
- Confident Approximate Policy Iteration for Efficient Local Planning in qπ-realizable MDPs
- ConfLab: A Data Collection Concept, Dataset, and Benchmark for Machine Analysis of Free-Standing Social Interactions in the Wild
- Conformal Frequency Estimation with Sketched Data
- Conformalized Fairness via Quantile Regression
- Conformal Off-Policy Prediction in Contextual Bandits
- Conformal Prediction in 2022
- Conformal Prediction with Temporal Quantile Adjustments
- ConfounderGAN: Protecting Image Data Privacy with Causal Confounder
- Conservative Dual Policy Optimization for Efficient Model-Based Reinforcement Learning
- Consistency of Constrained Spectral Clustering under Graph Induced Fair Planted Partitions
- Consistent Interpolating Ensembles via the Manifold-Hilbert Kernel
- Consistent Sufficient Explanations and Minimal Local Rules for explaining the decision of any classifier or regressor
- CoNSoLe: Convex Neural Symbolic Learning
- Constants of motion network
- Constrained GPI for Zero-Shot Transfer in Reinforcement Learning
- Constrained Langevin Algorithms with L-mixing External Random Variables
- Constrained Predictive Coding as a Biologically Plausible Model of the Cortical Hierarchy
- Constrained Stochastic Nonconvex Optimization with State-dependent Markov Data
- Constrained Update Projection Approach to Safe Policy Optimization
- Constraining Gaussian Processes to Systems of Linear Ordinary Differential Equations
- Contact-aware Human Motion Forecasting
- CoNT: Contrastive Neural Text Generation
- Context-Based Dynamic Pricing with Partially Linear Demand Model
- Contextual Bandits with Knapsacks for a Conversion Model
- Contextual Dynamic Pricing with Unknown Noise: Explore-then-UCB Strategy and Improved Regrets
- Contextual Squeeze-and-Excitation for Efficient Few-Shot Image Classification
- Continual learning: a feature extraction formalization, an efficient algorithm, and fundamental obstructions
- Continual Learning In Environments With Polynomial Mixing Times
- Continual Learning with Evolving Class Ontologies
- Continuous Deep Q-Learning in Optimal Control Problems: Normalized Advantage Functions Analysis
- Continuously Tempered PDMP samplers
- Continuous MDP Homomorphisms and Homomorphic Policy Gradient
- Contrastive Adapters for Foundation Model Group Robustness
- Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methods
- Contrastive Graph Structure Learning via Information Bottleneck for Recommendation
- Contrastive Language-Image Pre-Training with Knowledge Graphs
- Contrastive Learning as Goal-Conditioned Reinforcement Learning
- Contrastive Neural Ratio Estimation
- Controllable 3D Face Synthesis with Conditional Generative Occupancy Fields
- Controllable Text Generation with Neurally-Decomposed Oracle
- Controlled Sparsity via Constrained Optimization or: How I Learned to Stop Tuning Penalties and Love Constraints
- Convergence beyond the over-parameterized regime using Rayleigh quotients
- Convergence for score-based generative modeling with polynomial complexity
- Convergent Representations of Computer Programs in Human and Artificial Neural Networks
- Convexity Certificates from Hessians
- Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisited
- Cooperative Distribution Alignment via JSD Upper Bound
- Coordinate Linear Variance Reduction for Generalized Linear Programming
- Coordinates Are NOT Lonely - Codebook Prior Helps Implicit Neural 3D representations
- CoPur: Certifiably Robust Collaborative Inference via Feature Purification
- Coreset for Line-Sets Clustering
- Coresets for Relational Data and The Applications
- Coresets for Vertical Federated Learning: Regularized Linear Regression and K-Means Clustering
- Coresets for Wasserstein Distributionally Robust Optimization Problems
- Cost-efficient Gaussian tensor network embeddings for tensor-structured inputs
- Cost-Sensitive Self-Training for Optimizing Non-Decomposable Metrics
- Could a Large Language Model be Conscious?
- Could Giant Pre-trained Image Models Extract Universal Representations?
- Counterfactual Fairness with Partially Known Causal Graph
- Counterfactual harm
- Counterfactual Neural Temporal Point Process for Estimating Causal Influence of Misinformation on Social Media
- Counterfactual Temporal Point Processes
- CoupAlign: Coupling Word-Pixel with Sentence-Mask Alignments for Referring Image Segmentation
- coVariance Neural Networks
- Creative Culture and Machine Learning
- CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion
- Cross Aggregation Transformer for Image Restoration
- Cross-Image Context for Single Image Inpainting
- Cross-Linked Unified Embedding for cross-modality representation learning
- Cross-modal Learning for Image-Guided Point Cloud Shape Completion
- CryptoGCN: Fast and Scalable Homomorphically Encrypted Graph Convolutional Network Inference
- Cryptographic Hardness of Learning Halfspaces with Massart Noise
- CS-Shapley: Class-wise Shapley Values for Data Valuation in Classification
- Cultures of AI and AI for Culture
- CUP: Critic-Guided Policy Reuse
- Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation
- Curriculum Reinforcement Learning using Optimal Transport via Gradual Domain Adaptation
- CyCLIP: Cyclic Contrastive Language-Image Pretraining
- D^2NeRF: Self-Supervised Decoupling of Dynamic and Static Objects from a Monocular Video
- DABS 2.0: Improved Datasets and Algorithms for Universal Self-Supervision
- DaDA: Distortion-aware Domain Adaptation for Unsupervised Semantic Segmentation
- DAGMA: Learning DAGs via M-matrices and a Log-Determinant Acyclicity Characterization
- Dance of SNN and ANN: Solving binding problem by combining spike timing and reconstructive attention
- DARE: Disentanglement-Augmented Rationale Extraction
- DART: Articulated Hand Model with Diverse Accessories and Rich Textures
- DASCO: Dual-Generator Adversarial Support Constrained Offline Reinforcement Learning
- Data Augmentation for Compositional Data: Advancing Predictive Models of the Microbiome
- Data augmentation for efficient learning from parametric experts
- Data Augmentation MCMC for Bayesian Inference from Privatized Data
- Data Compression with Machine Learning
- Data Distributional Properties Drive Emergent In-Context Learning in Transformers
- Data-Driven Conditional Robust Optimization
- Data-Driven Offline Decision-Making via Invariant Representation Learning
- Data-Efficient Augmentation for Training Neural Networks
- Data-Efficient Pipeline for Offline Reinforcement Learning with Limited Data
- Data-Efficient Structured Pruning via Submodular Optimization
- Data-IQ: Characterizing subgroups with heterogeneous outcomes in tabular data
- DataMUX: Data Multiplexing for Neural Networks
- Dataset Distillation using Neural Feature Regression
- Dataset Distillation via Factorization
- Dataset Inference for Self-Supervised Models
- DC-BENCH: Dataset Condensation Benchmark
- DDXPlus: A New Dataset For Automatic Medical Diagnosis
- Debiased Causal Tree: Heterogeneous Treatment Effects Estimation with Unmeasured Confounding
- Debiased, Longitudinal and Coordinated Drug Recommendation through Multi-Visit Clinic Records
- Debiased Machine Learning without Sample-Splitting for Stable Estimators
- Debiased Self-Training for Semi-Supervised Learning
- Debiasing Graph Neural Networks via Learning Disentangled Causal Substructure
- Debugging and Explaining Metric Learning Approaches: An Influence Function Based Perspective
- Decentralization and Trustworthy Machine Learning in Web3: Methodologies, Platforms, and Applications
- Decentralized, Communication- and Coordination-free Learning in Structured Matching Markets
- Decentralized Gossip-Based Stochastic Bilevel Optimization over Communication Networks
- Decentralized Local Stochastic Extra-Gradient for Variational Inequalities
- Decentralized Training of Foundation Models in Heterogeneous Environments
- Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning
- Decimated Framelet System on Graphs and Fast G-Framelet Transforms
- Decision-based Black-box Attack Against Vision Transformers via Patch-wise Adversarial Removal
- Decision-Focused Learning without Decision-Making: Learning Locally Optimized Decision Losses
- Decision Trees with Short Explainable Rules
- Decomposable Non-Smooth Convex Optimization with Nearly-Linear Gradient Oracle Complexity
- Decomposed Knowledge Distillation for Class-Incremental Semantic Segmentation
- Decomposing NeRF for Editing via Feature Field Distillation
- Deconfounded Representation Similarity for Comparison of Neural Networks
- Decoupled Context Processing for Context Augmented Language Modeling
- Decoupled Self-supervised Learning for Graphs
- Decoupling Classifier for Boosting Few-shot Object Detection and Instance Segmentation
- Decoupling Features in Hierarchical Propagation for Video Object Segmentation
- Decoupling Knowledge from Memorization: Retrieval-augmented Prompt Learning
- Deep Active Learning by Leveraging Training Dynamics
- Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis
- Deep Attentive Belief Propagation: Integrating Reasoning and Learning for Solving Constraint Optimization Problems
- Deep Bidirectional Language-Knowledge Graph Pretraining
- Deep Combinatorial Aggregation
- Deep Compression of Pre-trained Transformer Models
- Deep Counterfactual Estimation with Categorical Background Variables
- Deep Differentiable Logic Gate Networks
- Deep Ensembles Work, But Are They Necessary?
- Deep Equilibrium Approaches to Diffusion Models
- DeepFoids: Adaptive Bio-Inspired Fish Simulation with Deep Reinforcement Learning
- Deep Fourier Up-Sampling
- Deep Generalized Schrödinger Bridge
- Deep Generative Model for Periodic Graphs
- Deep Hierarchical Planning from Pixels
- DeepInteraction: 3D Object Detection via Modality Interaction
- Deep invariant networks with differentiable augmentation layers
- Deep Learning Methods for Proximal Inference via Maximum Moment Restriction
- Deep Limits and a Cut-Off Phenomenon for Neural Networks
- DeepMed: Semiparametric Causal Mediation Analysis with Debiased Deep Learning
- Deep Model Reassembly
- Deep Multi-Modal Structural Equations For Causal Effect Estimation With Unstructured Proxies
- Deep Reinforcement Learning Workshop
- Deep Surrogate Assisted Generation of Environments
- DeepTOP: Deep Threshold-Optimal Policy for MDPs and RMABs
- Defending Against Adversarial Attacks via Neural Dynamic System
- Defining and Characterizing Reward Gaming
- Degradation-Aware Unfolding Half-Shuffle Transformer for Spectral Compressive Imaging
- Deliberated Domain Bridging for Domain Adaptive Semantic Segmentation
- Delving into Out-of-Distribution Detection with Vision-Language Representations
- Delving into Sequential Patches for Deepfake Detection
- Denoising Diffusion Restoration Models
- DENSE: Data-Free One-Shot Federated Learning
- Dense Interspecies Face Embedding
- Density-driven Regularization for Out-of-distribution Detection
- Depth is More Powerful than Width with Prediction Concatenation in Deep Forest
- (De-)Randomized Smoothing for Decision Stump Ensembles
- Descent Steps of a Relation-Aware Energy Produce Heterogeneous Graph Neural Networks
- DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detection
- Detecting Abrupt Changes in Sequential Pairwise Comparison Data
- Detection and Localization of Changes in Conditional Distributions
- Deterministic Langevin Monte Carlo with Normalizing Flows for Bayesian Inference
- DevFly: Bio-Inspired Development of Binary Connections for Locality Preserving Sparse Codes
- DeVRF: Fast Deformable Voxel Radiance Fields for Dynamic Scenes
- D-GCCA: Decomposition-based Generalized Canonical Correlation Analysis for Multi-view High-dimensional Data
- DGD^2: A Linearly Convergent Distributed Algorithm For High-dimensional Statistical Recovery
- DGraph: A Large-Scale Financial Dataset for Graph Anomaly Detection
- DHRL: A Graph-Based Approach for Long-Horizon and Sparse Hierarchical Reinforcement Learning
- Diagnosing failures of fairness transfer across distribution shift in real-world medical settings
- Diagonal State Spaces are as Effective as Structured State Spaces
- Dict-TTS: Learning to Pronounce with Prior Dictionary Knowledge for Text-to-Speech
- Differentiable Analog Quantum Computing for Optimization and Control
- Differentiable hierarchical and surrogate gradient search for spiking neural networks
- Differentially Private Covariance Revisited
- Differentially Private Generalized Linear Models Revisited
- Differentially Private Graph Learning via Sensitivity-Bounded Personalized PageRank
- Differentially Private Learning Needs Hidden State (Or Much Faster Convergence)
- Differentially Private Learning with Margin Guarantees
- Differentially Private Linear Sketches: Efficient Implementations and Applications
- Differentially Private Model Compression
- Differentially Private Online-to-batch for Smooth Losses
- Diffusion-based Molecule Generation with Informative Prior Bridges
- Diffusion Curvature for Estimating Local Curvature in High Dimensional Data
- Diffusion-LM Improves Controllable Text Generation
- Diffusion Models as Plug-and-Play Priors
- Diffusion Visual Counterfactual Explanations
- DigGAN: Discriminator gradIent Gap Regularization for GAN Training with Limited Data
- DIMES: A Differentiable Meta Solver for Combinatorial Optimization Problems
- Direct Advantage Estimation
- DiSC: Differential Spectral Clustering of Features
- DISCO: Adversarial Defense with Local Implicit Functions
- Discovered Policy Optimisation
- Discovering and Overcoming Limitations of Noise-engineered Data-free Knowledge Distillation
- Discovering Design Concepts for CAD Sketches
- Discovery of Single Independent Latent Variable
- Discrete Compositional Representations as an Abstraction for Goal Conditioned Reinforcement Learning
- Discrete-Convex-Analysis-Based Framework for Warm-Starting Algorithms with Predictions
- Disentangling Causal Effects from Sets of Interventions in the Presence of Unobserved Confounders
- Disentangling the Predictive Variance of Deep Ensembles through the Neural Tangent Kernel
- Disentangling Transfer in Continual Reinforcement Learning
- Distilled Gradient Aggregation: Purify Features for Input Attribution in the Deep Neural Network
- Distilling Representations from GAN Generator via Squeeze and Span
- Distinguishing discrete and continuous behavioral variability using warped autoregressive HMMs
- Distinguishing Learning Rules with Brain Machine Interfaces
- Distributed Distributionally Robust Optimization with Non-Convex Objectives
- Distributed Influence-Augmented Local Simulators for Parallel MARL in Large Networked Systems
- Distributed Inverse Constrained Reinforcement Learning for Multi-agent Systems
- Distributed Learning of Conditional Quantiles in the Reproducing Kernel Hilbert Space
- Distributed Learning of Finite Gaussian Mixtures
- Distributed Methods with Compressed Communication for Solving Variational Inequalities, with Theoretical Guarantees
- Distributed Online Convex Optimization with Compressed Communication
- Distributed Optimization for Overparameterized Problems: Achieving Optimal Dimension Independent Communication Complexity
- Distributional Convergence of the Sliced Wasserstein Process
- Distributionally Adaptive Meta Reinforcement Learning
- Distributionally Robust Optimization via Ball Oracle Acceleration
- Distributionally Robust Optimization with Data Geometry
- Distributionally robust weighted k-nearest neighbors
- Distributional Reinforcement Learning for Risk-Sensitive Policies
- Distributional Reward Estimation for Effective Multi-agent Deep Reinforcement Learning
- Distribution-Informed Neural Networks for Domain Adaptation Regression
- DivBO: Diversity-aware CASH for Ensemble Learning
- Diverse Weight Averaging for Out-of-Distribution Generalization
- Diversified Recommendations for Agents with Adaptive Preferences
- Diversity vs. Recognizability: Human-like generalization in one-shot generative models
- Divert More Attention to Vision-Language Tracking
- Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning
- DMAP: a Distributed Morphological Attention Policy for learning to locomote with a changing body
- DNA: Proximal Policy Optimization with a Dual Network Architecture
- Do Current Multi-Task Optimization Methods in Deep Learning Even Help?
- Does GNN Pretraining Help Molecular Representation?
- Does Momentum Change the Implicit Regularization on Separable Data?
- Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels?
- Domain Adaptation meets Individual Fairness. And they get along.
- Domain Adaptation under Open Set Label Shift
- Domain Generalization by Learning and Removing Domain-specific Features
- Domain Generalization without Excess Empirical Risk
- DOMINO: Decomposed Mutual Information Optimization for Generalized Context in Meta-Reinforcement Learning
- Don't Pour Cereal into Coffee: Differentiable Temporal Logic for Temporal Action Segmentation
- Don't Roll the Dice, Ask Twice: The Two-Query Distortion of Matching Problems and Beyond
- DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learning
- Do Residual Neural Networks discretize Neural Ordinary Differential Equations?
- Double Bubble, Toil and Trouble: Enhancing Certified Robustness through Transitivity
- Double Check Your State Before Trusting It: Confidence-Aware Bidirectional Offline Model-Based Imagination
- Doubly-Asynchronous Value Iteration: Making Value Iteration Asynchronous in Actions
- Doubly Robust Counterfactual Classification
- DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps
- DP-PCA: Statistically Optimal and Differentially Private PCA
- Draft-and-Revise: Effective Image Generation with Contextual RQ-Transformer
- Drawing out of Distribution with Neuro-Symbolic Generative Models
- DreamShard: Generalizable Embedding Table Placement for Recommender Systems
- DReS-FL: Dropout-Resilient Secure Federated Learning for Non-IID Clients via Secret Data Sharing
- DropCov: A Simple yet Effective Method for Improving Deep Architectures
- DTG-SSOD: Dense Teacher Guidance for Semi-Supervised Object Detection
- DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotations
- Dual-Curriculum Contrastive Multi-Instance Learning for Cancer Prognosis Analysis with Whole Slide Images
- Dual-discriminative Graph Neural Network for Imbalanced Graph-level Anomaly Detection
- Dungeons and Data: A Large-Scale NetHack Dataset
- Dynamic Fair Division with Partial Information
- Dynamic Graph Neural Networks Under Spatio-Temporal Distribution Shift
- Dynamic Inverse Reinforcement Learning for Characterizing Animal Behavior
- Dynamic Learning in Large Matching Markets
- Dynamic pricing and assortment under a contextual MNL demand
- Dynamic Pricing with Monotonicity Constraint under Unknown Parametric Demand Model
- Dynamics of SGD with Stochastic Polyak Stepsizes: Truly Adaptive Variants and Convergence to Exact Solution
- Dynamic Sparse Network for Time Series Classification: Learning What to “See”
- Dynamic Tensor Product Regression
- EAGER: Asking and Answering Questions for Automatic Reward Shaping in Language-guided RL
- Early Stage Convergence and Global Convergence of Training Mildly Parameterized Neural Networks
- Earthformer: Exploring Space-Time Transformers for Earth System Forecasting
- EcoFormer: Energy-Saving Attention with Linear Complexity
- EF-BV: A Unified Theory of Error Feedback and Variance Reduction Mechanisms for Biased and Unbiased Compression in Distributed Optimization
- Effective Adaptation in Multi-Task Co-Training for Unified Autonomous Driving
- Effective Backdoor Defense by Exploiting Sensitivity of Poisoned Samples
- Effective Dimension in Bandit Problems under Censorship
- Effectiveness of Vision Transformer for Fast and Accurate Single-Stage Pedestrian Detection
- Effects of Data Geometry in Early Deep Learning
- Efficiency Ordering of Stochastic Gradient Descent
- Efficient Active Learning with Abstention
- Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning
- Efficient Aggregated Kernel Tests using Incomplete U-statistics
- Efficient and Effective Augmentation Strategy for Adversarial Training
- Efficient and Effective Multi-task Grouping via Meta Learning on Task Combinations
- Efficient and Effective Optimal Transport-Based Biclustering
- Efficient and Modular Implicit Differentiation
- Efficient and Near-Optimal Smoothed Online Learning for Generalized Linear Functions
- Efficient and Stable Fully Dynamic Facility Location
- Efficient Architecture Search for Diverse Tasks
- Efficient Change-Point Detection for Tackling Piecewise-Stationary Bandits
- Efficient coding, channel capacity, and the emergence of retinal mosaics
- Efficient Dataset Distillation using Random Feature Approximation
- EfficientFormer: Vision Transformers at MobileNet Speed
- Efficient Frameworks for Generalized Low-Rank Matrix Bandit Problems
- Efficient Graph Similarity Computation with Alignment Regularization
- Efficient identification of informative features in simulation-based inference
- Efficient Knowledge Distillation from Model Checkpoints
- Efficient learning of nonlinear prediction models with time-series privileged information
- Efficiently Computing Local Lipschitz Constants of Neural Networks via Bound Propagation
- Efficiently Factorizing Boolean Matrices using Proximal Gradient Descent
- Efficient Meta Reinforcement Learning for Preference-based Fast Adaptation
- Efficient Methods for Non-stationary Online Learning
- Efficient Multi-agent Communication via Self-supervised Information Aggregation
- Efficient Non-Parametric Optimizer Search for Diverse Tasks
- Efficient Phi-Regret Minimization in Extensive-Form Games via Online Mirror Descent
- Efficient Risk-Averse Reinforcement Learning
- Efficient Sampling on Riemannian Manifolds via Langevin MCMC
- Efficient Scheduling of Data Augmentation for Deep Reinforcement Learning
- Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models
- Efficient Submodular Optimization under Noise: Local Search is Robust
- Efficient Training of Low-Curvature Neural Networks
- Egocentric Video-Language Pretraining
- EgoTaskQA: Understanding Human Tasks in Egocentric Videos
- EGSDE: Unpaired Image-to-Image Translation via Energy-Guided Stochastic Differential Equations
- EHRSQL: A Practical Text-to-SQL Benchmark for Electronic Health Records
- ElasticMVS: Learning elastic part representation for self-supervised multi-view stereopsis
- ELASTIC: Numerical Reasoning with Adaptive Symbolic Compiler
- ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models
- ELIAS: End-to-End Learning to Index and Search in Large Output Spaces
- Eliciting Thinking Hierarchy without a Prior
- ELIGN: Expectation Alignment as a Multi-Agent Intrinsic Reward
- Elucidating the Design Space of Diffusion-Based Generative Models
- E-MAPP: Efficient Multi-Agent Reinforcement Learning with Parallel Program Guidance
- Embed and Emulate: Learning to estimate parameters of dynamical systems with uncertainty quantification
- Embodied Scene-aware Human Pose Estimation
- Embrace the Gap: VAEs Perform Independent Mechanism Analysis
- Embracing Consistency: A One-Stage Approach for Spatio-Temporal Video Grounding
- Emergence of Hierarchical Layers in a Single Sheet of Self-Organizing Spiking Neurons
- Emergent Communication: Generalization and Overfitting in Lewis Games
- Emergent Graphical Conventions in a Visual Communication Game
- Empirical Gateaux Derivatives for Causal Inference
- Empirical Phase Diagram for Three-layer Neural Networks with Infinite Width
- Empowering Communities: A Participatory Approach to AI for Mental Health
- Enabling Detailed Action Recognition Evaluation Through Video Dataset Augmentation
- End-to-end Algorithm Synthesis with Recurrent Networks: Extrapolation without Overthinking
- End-to-end Stochastic Optimization with Energy-based Model
- End-to-end Symbolic Regression with Transformers
- Energy-Based Contrastive Learning of Visual Representations
- Enhanced Bilevel Optimization via Bregman Distance
- Enhanced Latent Space Blind Model for Real Image Denoising via Alternative Optimization
- Enhanced Meta Reinforcement Learning via Demonstrations in Sparse Reward Environments
- Enhance the Visual Representation via Discrete Adversarial Training
- Enhancing Safe Exploration Using Safety State Augmentation
- ENS-10: A Dataset For Post-Processing Ensemble Weather Forecasts
- Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization
- Entropy-Driven Mixed-Precision Quantization for Deep Network Design
- Environment Diversification with Multi-head Neural Network for Invariant Learning
- EnvPool: A Highly Parallel Reinforcement Learning Environment Execution Engine
- Envy-free Policy Teaching to Multiple Agents
- EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations
- EpiGRAF: Rethinking training of 3D GANs
- Equivariant Graph Hierarchy-Based Neural Networks
- Equivariant Networks for Crystal Structures
- Equivariant Networks for Zero-Shot Coordination
- Error Analysis of Tensor-Train Cross Approximation
- Error Correction Code Transformer
- ESCADA: Efficient Safety and Context Aware Dose Allocation for Precision Medicine
- Escaping from the Barren Plateau via Gaussian Initializations in Deep Variational Quantum Circuits
- Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data
- Escaping Saddle Points with Bias-Variance Reduced Local Perturbed SGD for Communication Efficient Nonconvex Distributed Learning
- Estimating and Explaining Model Performance When Both Covariates and Labels Shift
- Estimating graphical models for count data with applications to single-cell gene network
- Estimating Noise Transition Matrix with Label Correlations for Noisy Multi-Label Learning
- Estimating the Arc Length of the Optimal ROC Curve and Lower Bounding the Maximal AUC
- Estimation of Entropy in Constant Space with Improved Sample Complexity
- ETAB: A Benchmark Suite for Visual Representation Learning in Echocardiography
- Evaluated CMI Bounds for Meta Learning: Tightness and Expressiveness
- Evaluating Graph Generative Models with Contrastively Learned Features
- Evaluating Latent Space Robustness and Uncertainty of EEG-ML Models under Realistic Distribution Shifts
- Evaluating Out-of-Distribution Performance on Document Image Classifiers
- Evaluating Robustness to Dataset Shift via Parametric Robustness Sets
- Evaluation beyond Task Performance: Analyzing Concepts in AlphaZero in Hex
- EvenNet: Ignoring Odd-Hop Neighbors Improves Robustness of Graph Neural Networks
- Evolution of Neural Tangent Kernels under Benign and Adversarial Training
- Exact learning dynamics of deep linear networks with prior knowledge
- Exact Shape Correspondence via 2D graph convolution
- Exact Solutions of a Deep Linear Network
- Expansion and Shrinkage of Localization for Weakly-Supervised Semantic Segmentation
- Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations
- Expected Frequency Matrices of Elections: Computation, Geometry, and Preference Learning
- Expected Improvement for Contextual Bandits
- Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuning
- Experimental Design for Linear Functionals in Reproducing Kernel Hilbert Spaces
- Explainability Via Causal Self-Talk
- Explainable Reinforcement Learning via Model Transforms
- Explaining Preferences with Shapley Values
- Explain My Surprise: Learning Efficient Long-Term Memory by predicting uncertain outcomes
- Explicable Policy Search
- Explicit Tradeoffs between Adversarial and Natural Distributional Robustness
- Exploitability Minimization in Games and Beyond
- Exploiting Semantic Relations for Glass Surface Detection
- Exploiting the Relationship Between Kendall's Rank Correlation and Cosine Similarity for Attribution Protection
- Exploit Reward Shifting in Value-Based Deep-RL: Optimistic Curiosity-Based Exploration and Conservative Exploitation via Linear Reward Shaping
- Exploration-Guided Reward Shaping for Reinforcement Learning under Sparse Rewards
- Exploration via Elliptical Episodic Bonuses
- Exploration via Planning for Information about the Optimal Trajectory
- Exploring evolution-aware & -free protein language models as protein function predictors
- Exploring Example Influence in Continual Learning
- Exploring Figure-Ground Assignment Mechanism in Perceptual Organization
- Exploring Length Generalization in Large Language Models
- Exploring the Algorithm-Dependent Generalization of AUPRC Optimization with List Stability
- Exploring the Latent Space of Autoencoders with Interventional Assays
- Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Models
- Exploring the Whole Rashomon Set of Sparse Decision Trees
- Exploring through Random Curiosity with General Value Functions
- Exponential Family Model-Based Reinforcement Learning via Score Matching
- Exponentially Improving the Complexity of Simulating the Weisfeiler-Lehman Test with Graph Neural Networks
- Exponential Separations in Symmetric Neural Networks
- Exposing and Exploiting Fine-Grained Block Structures for Fast and Accurate Sparse Training
- Extracting computational mechanisms from neural data using low-rank RNNs
- Extra-Newton: A First Approach to Noise-Adaptive Accelerated Second-Order Methods
- Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study
- Extrapolative Continuous-time Bayesian Neural Network for Fast Training-free Test-time Adaptation
- EZNAS: Evolving Zero-Cost Proxies For Neural Architecture Scoring
- FACT: Learning Governing Abstractions Behind Integer Sequences
- Factored Adaptation for Non-Stationary Reinforcement Learning
- Factored DRO: Factored Distributionally Robust Policies for Contextual Bandits
- Factorized-FL: Personalized Federated Learning with Parameter Factorization & Similarity Matching
- Factuality Enhanced Language Models for Open-Ended Text Generation
- Fair and Efficient Allocations Without Obvious Manipulations
- Fair and Optimal Decision Trees: A Dynamic Programming Approach
- Fair and Socially Responsible ML for Recommendations: Challenges and Perspectives
- Fair Bayes-Optimal Classifiers Under Predictive Parity
- Fair Infinitesimal Jackknife: Mitigating the Influence of Biased Training Data Points Without Refitting
- Fairness-Aware PAC Learning from Corrupted Data
- Fairness in Federated Learning via Core-Stability
- Fairness Reprogramming
- Fairness Transferability Subject to Bounded Distribution Shift
- Fairness without Demographics through Knowledge Distillation
- Fair Rank Aggregation
- Fair Ranking with Noisy Protected Attributes
- FairVFL: A Fair Vertical Federated Learning Framework with Contrastive Adversarial Learning
- Fair Wrapping for Black-box Predictions
- Falconn++: A Locality-sensitive Filtering Approach for Approximate Nearest Neighbor Search
- Falsification before Extrapolation in Causal Effect Estimation
- Fast Algorithms for Packing Proportional Fairness and its Dual
- Fast and Robust Rank Aggregation against Model Misspecification
- Fast Bayesian Coresets via Subsampling and Quasi-Newton Refinement
- Fast Bayesian Estimation of Point Process Intensity as Function of Covariates
- Fast Bayesian Inference with Batch Bayesian Quadrature via Kernel Recombination
- Fast Distance Oracles for Any Symmetric Norm
- Faster and Scalable Algorithms for Densest Subgraph and Decomposition
- Faster Deep Reinforcement Learning with Slower Online Network
- Faster Linear Algebra for Distance Matrices
- FasterRisk: Fast and Accurate Interpretable Risk Scores
- Faster Stochastic Algorithms for Minimax Optimization under Polyak-{\L}ojasiewicz Condition
- Fast Instrument Learning with Faster Rates
- Fast Mixing of Stochastic Gradient Descent with Normalization and Weight Decay
- Fast Neural Kernel Embeddings for General Activations
- Fast Stochastic Composite Minimization and an Accelerated Frank-Wolfe Algorithm under Parallelization
- Fast Vision Transformers with HiLo Attention
- Fault-Aware Neural Code Rankers
- Feature Learning in L2-regularized DNNs: Attraction/Repulsion and Sparsity
- Feature-Proxy Transformer for Few-Shot Segmentation
- FedAvg with Fine Tuning: Local Updates Lead to Representation Learning
- Federated Learning from Pre-Trained Models: A Contrastive Learning Approach
- Federated Learning: Recent Advances and New Challenges
- Federated Submodel Optimization for Hot and Cold Data Features
- FedPop: A Bayesian Approach for Personalised Federated Learning
- FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction
- FedSR: A Simple and Effective Domain Generalization Method for Federated Learning
- FeLMi : Few shot Learning with hard Mixup
- FETA: Towards Specializing Foundational Models for Expert Task Applications
- Few-Shot Audio-Visual Learning of Environment Acoustics
- Few-Shot Continual Active Learning by a Robot
- Few-Shot Fast-Adaptive Anomaly Detection
- Few-shot Image Generation via Adaptation-Aware Kernel Modulation
- Few-shot Learning for Feature Selection with Hilbert-Schmidt Independence Criterion
- Few-Shot Non-Parametric Learning with Deep Latent Variable Model
- Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning
- Few-shot Relational Reasoning via Connection Subgraph Pretraining
- Few-shot Task-agnostic Neural Architecture Search for Distilling Large Language Models
- (f,Gamma)-Divergences: Interpolating between f-Divergences and Integral Probability Metrics
- FiLM-Ensemble: Probabilistic Deep Learning via Feature-wise Linear Modulation
- FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecasting
- Finding and Listing Front-door Adjustment Sets
- Finding Correlated Equilibrium of Constrained Markov Game: A Primal-Dual Approach
- Finding Differences Between Transformers and ConvNets Using Counterfactual Simulation Testing
- Finding Naturally Occurring Physical Backdoors in Image Datasets
- Finding Optimal Arms in Non-stochastic Combinatorial Bandits with Semi-bandit Feedback and Finite Budget
- Finding Second-Order Stationary Points in Nonconvex-Strongly-Concave Minimax Optimization
- Fine-Grained Analysis of Stability and Generalization for Modern Meta Learning Algorithms
- Fine-Grained Semantically Aligned Vision-Language Pre-Training
- Fine-tuning Language Models over Slow Networks using Activation Quantization with Guarantees
- Fine-tuning language models to find agreement among humans with diverse preferences
- Fine-Tuning Pre-Trained Language Models Effectively by Optimizing Subnetworks Adaptively
- Finite Sample Analysis Of Dynamic Regression Parameter Learning
- Finite-Sample Maximum Likelihood Estimation of Location
- Finite-Time Analysis of Adaptive Temporal Difference Learning with Deep Neural Networks
- Finite-Time Last-Iterate Convergence for Learning in Multi-Player Games
- Finite-Time Regret of Thompson Sampling Algorithms for Exponential Family Multi-Armed Bandits
- FinRL-Meta: Market Environments and Benchmarks for Data-Driven Financial Reinforcement Learning
- FIRE: Semantic Field of Words Represented as Non-Linear Functions
- First Contact: Unsupervised Human-Machine Co-Adaptation via Mutual Information Maximization
- First Hitting Diffusion Models for Generating Manifold, Graph and Categorical Data
- First is Better Than Last for Language Data Influence
- First-Order Algorithms for Min-Max Optimization in Geodesic Metric Spaces
- Fixed-Distance Hamiltonian Monte Carlo
- FLAIR: Federated Learning Annotated Image Repository
- FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings
- Flamingo: a Visual Language Model for Few-Shot Learning
- Flare7K: A Phenomenological Nighttime Flare Removal Dataset
- FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
- Flexible Diffusion Modeling of Long Videos
- Flexible Neural Image Compression via Code Editing
- FlowHMM: Flow-based continuous hidden Markov models
- Flowification: Everything is a normalizing flow
- FlyView: a bio-informed optical flow truth dataset for visual navigation using panoramic stereo vision
- FNeVR: Neural Volume Rendering for Face Animation
- Focal Modulation Networks
- FOF: Learning Fourier Occupancy Field for Monocular Real-time Human Reconstruction
- Follow-the-Perturbed-Leader for Adversarial Markov Decision Processes with Bandit Feedback
- Foolish Crowds Support Benign Overfitting
- Forecasting Future World Events With Neural Networks
- Forecasting Human Trajectory from Scene History
- Formalizing Consistency and Coherence of Representation Learning
- Formulating Robustness Against Unforeseen Attacks
- Forward-Backward Latent State Inference for Hidden Continuous-Time semi-Markov Chains
- Foundational Robustness of Foundation Models
- Foundation Models for Decision Making
- Foundation Posteriors for Approximate Probabilistic Inference
- FourierFormer: Transformer Meets Generalized Fourier Integral Theorem
- FourierNets enable the design of highly non-local optical encoders for computational imaging
- FP8 Quantization: The Power of the Exponent
- Frank-Wolfe-based Algorithms for Approximating Tyler's M-estimator
- Free Probability for predicting the performance of feed-forward fully connected neural networks
- FreGAN: Exploiting Frequency Components for Training GANs under Limited Data
- FR: Folded Rationalization with a Unified Encoder
- Friendly Noise against Adversarial Noise: A Powerful Defense against Data Poisoning Attack
- From Gradient Flow on Population Loss to Learning with Stochastic Gradient Descent
- Fully Convolutional One-Stage 3D Object Detection on LiDAR Range Images
- Fully Sparse 3D Object Detection
- Functional Ensemble Distillation
- Functional Indirection Neural Estimator for Better Out-of-distribution Generalization
- Function Classes for Identifiable Nonlinear Independent Component Analysis
- Fused Orthogonal Alternating Least Squares for Tensor Clustering
- Fuzzy Learning Machine
- GAGA: Deciphering Age-path of Generalized Self-paced Regularizer
- GAL: Gradient Assisted Learning for Decentralized Multi-Organization Collaborations
- GALOIS: Boosting Deep Reinforcement Learning via Generalizable Logic Synthesis
- GAMA: Generative Adversarial Multi-Object Scene Attacks
- GAPX: Generalized Autoregressive Paraphrase-Identification X
- GAR: Generalized Autoregression for Multi-Fidelity Fusion
- GAUDI: A Neural Architect for Immersive 3D Scene Generation
- Gaussian Copula Embeddings
- Gaussian Processes, Spatiotemporal Modeling, and Decision-making Systems
- Gaze meets ML
- GBA: A Tuning-free Approach to Switch between Synchronous and Asynchronous Training for Recommendation Models
- General Cutting Planes for Bound-Propagation-Based Neural Network Verification
- Generalised Implicit Neural Representations
- Generalised Mutual Information for Discriminative Clustering
- Generalization Analysis of Message Passing Neural Networks on Large Random Graphs
- Generalization Analysis on Learning with a Concurrent Verifier
- Generalization Bounds for Estimating Causal Effects of Continuous Treatments
- Generalization Bounds for Gradient Methods via Discrete and Continuous Prior
- Generalization Bounds for Stochastic Gradient Descent via Localized ε-Covers
- Generalization Bounds with Minimal Dependency on Hypothesis Class via Distributionally Robust Optimization
- Generalization Error Bounds on Deep Learning with Markov Datasets
- Generalization for multiclass classification with overparameterized linear models
- Generalization Gap in Amortized Inference
- Generalization Properties of NAS under Activation and Skip Connection Search
- Generalized Delayed Feedback Model with Post-Click Information in Recommender Systems
- Generalized Laplacian Eigenmaps
- Generalized One-shot Domain Adaptation of Generative Adversarial Networks
- Generalized Variational Inference in Function Spaces: Gaussian Measures meet Bayesian Deep Learning
- Generalizing Bayesian Optimization with Decision-theoretic Entropies
- Generalizing Consistent Multi-Class Classification with Rejection to be Compatible with Arbitrary Losses
- Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoning
- Generating Long Videos of Dynamic Scenes
- Generating multivariate time series with COmmon Source CoordInated GAN (COSCI-GAN)
- Generating Training Data with Language Models: Towards Zero-Shot Language Understanding
- Generative multitask learning mitigates target-causing confounding
- Generative Neural Articulated Radiance Fields
- Generative Status Estimation and Information Decoupling for Image Rain Removal
- Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglement
- Generative Visual Prompt: Unifying Distributional Control of Pre-Trained Generative Models
- Generic bounds on the approximation error for physics-informed (and) operator learning
- GenerSpeech: Towards Style Transfer for Generalizable Out-Of-Domain Text-to-Speech
- GENIE: Higher-Order Denoising Diffusion Solvers
- GenSDF: Two-Stage Learning of Generalizable Signed Distance Functions
- Geoclidean: Few-Shot Generalization in Euclidean Geometry
- Geodesic Graph Neural Network for Efficient Graph Representation Learning
- Geodesic Self-Attention for 3D Point Clouds
- Geometric Knowledge Distillation: Topology Compression for Graph Neural Networks
- Geometric Order Learning for Rank Estimation
- Geometry-aware Two-scale PIFu Representation for Human Reconstruction
- Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstruction
- Geo-SIC: Learning Deformable Geometric Shapes in Deep Image Classifiers
- GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images
- Get More at Once: Alternating Sparse Training with Gradient Correction
- GhostNetV2: Enhance Cheap Operation with Long-Range Attention
- Giga-scale Kernel Matrix-Vector Multiplication on GPU
- Giving Feedback on Interactive Student Programs with Meta-Exploration
- GlanceNets: Interpretable, Leak-proof Concept-based Models
- GLIF: A Unified Gated Leaky Integrate-and-Fire Neuron for Spiking Neural Networks
- GLIPv2: Unifying Localization and Vision-Language Understanding
- Global Convergence and Stability of Stochastic Gradient Descent
- Global Convergence of Direct Policy Search for State-Feedback H∞ Robust Control: A Revisit of Nonsmooth Synthesis with Goldstein Subdifferential
- Global Convergence of Federated Learning for Mixed Regression
- Global Linear and Local Superlinear Convergence of IRLS for Non-Smooth Robust Regression
- Globally Convergent Policy Search for Output Estimation
- Globally Gated Deep Linear Networks
- Global Normalization for Streaming Speech Recognition in a Modular Framework
- Global Optimal K-Medoids Clustering of One Million Samples
- GLOBEM Dataset: Multi-Year Datasets for Longitudinal Human Behavior Modeling Generalization
- GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Models
- Gold-standard solutions to the Schrödinger equation using deep learning: How much physics do we need?
- GOOD: A Graph Out-of-Distribution Benchmark
- GPT3.int8(): 8-bit Matrix Multiplication for Transformers at Scale
- GraB: Finding Provably Better Data Permutations than Random Reshuffling
- Gradient Descent Is Optimal Under Lower Restricted Secant Inequality And Upper Error Bound
- Gradient Descent: The Ultimate Optimizer
- Gradient Estimation with Discrete Stein Operators
- Gradient flow dynamics of shallow ReLU networks for square loss and orthogonal inputs
- Gradient-Free Methods for Deterministic and Stochastic Nonsmooth Nonconvex Optimization
- Gradient Methods Provably Converge to Non-Robust Networks
- Graph Coloring via Neural Networks for Haplotype Assembly and Viral Quasispecies Reconstruction
- Graph Convolution Network based Recommender Systems: Learning Guarantee and Item Mixture Powered Strategy
- GraphDE: A Generative Framework for Debiased Learning and Out-of-Distribution Detection on Graphs
- Graphein - a Python Library for Geometric Deep Learning and Network Analysis on Biomolecular Structures and Interaction Networks
- Graph Few-shot Learning with Task-specific Structures
- Graph Learning Assisted Multi-Objective Integer Programming
- Graph Learning for Industrial Applications: Finance, Crime Detection, Medicine and Social Media
- Graph Neural Network Bandits
- Graph Neural Networks are Dynamic Programmers
- Graph Neural Networks with Adaptive Readouts
- GraphQNTK: Quantum Neural Tangent Kernel for Graph Data
- Graph Reordering for Cache-Efficient Near Neighbor Search
- Graph Scattering beyond Wavelet Shackles
- Graph Self-supervised Learning with Accurate Discrepancy Learning
- GRASP: Navigating Retrosynthetic Planning with Goal-driven Policy
- GREED: A Neural Framework for Learning Graph Distance Functions
- Green Hierarchical Vision Transformer for Masked Image Modeling
- GriddlyJS: A Web IDE for Reinforcement Learning
- Grounded Reinforcement Learning: Learning to Win the Game under Human Commands
- Grounded Video Situation Recognition
- Grounding Aleatoric Uncertainty for Unsupervised Environment Design
- Group Meritocratic Fairness in Linear Contextual Bandits
- Grow and Merge: A Unified Framework for Continuous Categories Discovery
- GStarX: Explaining Graph Neural Networks with Structure-Aware Cooperative Games
- GT-GAN: General Purpose Time Series Synthesis with Generative Adversarial Networks
- Guaranteed Conservation of Momentum for Learning Particle-based Fluid Dynamics
- GULP: a prediction-based metric between representations
- Hamiltonian Latent Operators for content and motion disentanglement in image sequences
- Handcrafted Backdoors in Deep Neural Networks
- HandMeThat: Human-Robot Communication in Physical and Social Environments
- Hand-Object Interaction Image Generation
- HAPI: A Large-scale Longitudinal Dataset of Commercial ML API Predictions
- Hard ImageNet: Segmentations for Objects with Strong Spurious Cues
- Hardness in Markov Decision Processes: Theory and Practice
- Hardness of Noise-Free Learning for Two-Hidden-Layer Neural Networks
- Harmonizing the object recognition strategies of deep neural networks with humans
- Has it Trained Yet? A Workshop for Algorithmic Efficiency in Practical Neural Network Training
- HCAI@NeurIPS 2022, Human Centered AI
- Heatmap Distribution Matching for Human Pose Estimation
- Hedging as Reward Augmentation in Probabilistic Graphical Models
- Heterogeneous Skill Learning for Multi-agent Tasks
- HF-NeuS: Improved Surface Reconstruction Using High-Frequency Details
- Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit
- Hiding Images in Deep Probabilistic Models
- Hierarchical Agglomerative Graph Clustering in Poly-Logarithmic Depth
- Hierarchical Channel-spatial Encoding for Communication-efficient Collaborative Learning
- Hierarchical classification at multiple operating points
- Hierarchical Graph Transformer with Adaptive Node Sampling
- Hierarchical Lattice Layer for Partially Monotone Neural Networks
- Hierarchical Normalization for Robust Monocular Depth Estimation
- HierSpeech: Bridging the Gap between Text and Speech by Hierarchical Variational Inference using Self-supervised Representations for Speech Synthesis
- High-dimensional Additive Gaussian Processes under Monotonicity Constraints
- High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation
- High-dimensional limit theorems for SGD: Effective dynamics and critical scaling
- High-Order Pooling for Graph Neural Networks with Tensor Decomposition
- Hilbert Distillation for Cross-Dimensionality Networks
- Holomorphic Equilibrium Propagation Computes Exact Gradients Through Finite Size Oscillations
- Homomorphic Matrix Completion
- Honor of Kings Arena: an Environment for Generalization in Competitive Reinforcement Learning
- HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutions
- House of Cans: Covert Transmission of Internal Datasets via Capacity-Aware Neuron Steganography
- How and Why to Manipulate Your Own Agent: On the Incentives of Users of Learning Agents
- How Mask Matters: Towards Theoretical Understandings of Masked Autoencoders
- How Powerful are K-hop Message Passing Graph Neural Networks
- How Sampling Impacts the Robustness of Stochastic Neural Networks
- How to talk so AI will learn: Instructions, descriptions, and autonomy
- How Transferable are Video Representations Based on Synthetic Data?
- How Well Do Unsupervised Learning Algorithms Model Human Real-time and Life-long Learning?
- How Would The Viewer Feel? Estimating Wellbeing From Video Scenarios
- HSDF: Hybrid Sign and Distance Field for Modeling Surfaces with Arbitrary Topologies
- HSurf-Net: Normal Estimation for 3D Point Clouds by Learning Hyper Surfaces
- Hub-Pathway: Transfer Learning from A Hub of Pre-trained Models
- Human-AI Collaborative Bayesian Optimisation
- Human-AI Shared Control via Policy Dissection
- Human Evaluation of Generative Models
- Human in the Loop Learning (HiLL) Workshop at NeurIPS 2022
- HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes
- HumanLiker: A Human-like Object Detector to Model the Manual Labeling Process
- Human-Robotic Prosthesis as Collaborating Agents for Symmetrical Walking
- HUMUS-Net: Hybrid Unrolled Multi-scale Network Architecture for Accelerated MRI Reconstruction
- Hybrid Neural Autoencoders for Stimulus Encoding in Visual and Other Sensory Neuroprostheses
- Hyperbolic Embedding Inference for Structured Multi-Label Prediction
- Hyperbolic Feature Augmentation via Distribution Estimation and Infinite Sampling on Manifolds
- HyperDomainNet: Universal Domain Adaptation for Generative Adversarial Networks
- HyperMiner: Topic Taxonomy Mining with Hyperbolic Embedding
- Hyperparameter Sensitivity in Deep Outlier Detection: Analysis and a Scalable Hyper-Ensemble Solution
- Hyper-Representations as Generative Models: Sampling Unseen Neural Network Weights
- HyperTree Proof Search for Neural Theorem Proving
- Hypothesis Testing for Differentially Private Linear Regression
- HYPRO: A Hybridly Normalized Probabilistic Model for Long-Horizon Prediction of Event Sequences
- I2DFormer: Learning Image to Document Attention for Zero-Shot Image Classification
- I2Q: A Fully Decentralized Q-Learning Algorithm
- IALE: Imitating Active Learner Ensembles
- I Can’t Believe It’s Not Better: Understanding Deep Learning Through Empirical Falsification
- Identifiability and generalizability from multiple experts in Inverse Reinforcement Learning
- Identifiability of deep generative models without auxiliary information
- Identification, Amplification and Measurement: A bridge to Gaussian Differential Privacy
- Identifying good directions to escape the NTK regime and efficiently learn low-degree plus sparse polynomials
- If Influence Functions are the Answer, Then What is the Question?
- IKEA-Manual: Seeing Shape Assembly Step by Step
- Imbalance Trouble: Revisiting Neural-Collapse Geometry
- IMED-RL: Regret optimal learning of ergodic Markov decision processes
- Imitating Past Successes can be Very Suboptimal
- IM-Loss: Information Maximization Loss for Spiking Neural Networks
- Implications of Model Indeterminacy for Explanations of Automated Decisions
- Implicit Bias of Gradient Descent on Reparametrized Models: On Equivalence to Mirror Descent
- Implicit Neural Representations with Levels-of-Experts
- Implicit Regularization or Implicit Conditioning? Exact Risk Trajectories of SGD in High Dimensions
- Implicit Warping for Animation with Image Sets
- Improved Algorithms for Neural Active Learning
- Improved Bounds on Neural Complexity for Representing Piecewise Linear Functions
- Improved Convergence Rate of Stochastic Gradient Langevin Dynamics with Variance Reduction and its Application to Optimization
- Improved Coresets for Euclidean k-Means
- Improved Differential Privacy for SGD via Optimal Private Linear Operators on Adaptive Streams
- Improved Feature Distillation via Projector Ensemble
- Improved Fine-Tuning by Better Leveraging Pre-Training Data
- Improved Imaging by Invex Regularizers with Global Optima Guarantees
- Improved Regret Analysis for Variance-Adaptive Linear Bandits and Horizon-Free Linear Mixture MDPs
- Improved techniques for deterministic l2 robustness
- Improved Utility Analysis of Private CountSketch
- Improving 3D-aware Image Synthesis with A Geometry-aware Discriminator
- Improving Barely Supervised Learning by Discriminating Unlabeled Samples with Super-Class
- Improving Certified Robustness via Statistical Learning with Logical Reasoning
- Improving Diffusion Models for Inverse Problems using Manifold Constraints
- Improving GANs with A Dynamic Discriminator
- Improving Generative Adversarial Networks via Adversarial Learning in Latent Space
- Improving Intrinsic Exploration with Language Abstractions
- Improving Multi-Task Generalization via Regularizing Spurious Correlation
- Improving Neural Ordinary Differential Equations with Nesterov's Accelerated Gradient Method
- Improving Out-of-Distribution Generalization by Adversarial Training with Structured Priors
- Improving Policy Learning via Language Dynamics Distillation
- Improving Self-Supervised Learning by Characterizing Idealized Representations
- Improving Task-Specific Generalization in Few-Shot Learning via Adaptive Vicinal Risk Minimization
- Improving Transformer with an Admixture of Attention Heads
- Improving Variational Autoencoders with Density Gap-based Regularization
- Improving Zero-Shot Generalization in Offline Reinforcement Learning using Generalized Similarity Functions
- Incentive-Aware Machine Learning: A Tale of Robustness, Fairness, Improvement, and Performativity
- Incentivizing Combinatorial Bandit Exploration
- Inception Transformer
- Incorporating Bias-aware Margins into Contrastive Loss for Collaborative Filtering
- Increasing Confidence in Adversarial Robustness Evaluations
- Increasing the Scope as You Learn: Adaptive Bayesian Optimization in Nested Subspaces
- Incrementality Bidding via Reinforcement Learning under Mixed and Delayed Rewards
- In Defense of the Unitary Scalarization for Deep Multi-Task Learning
- Independence Testing-Based Approach to Causal Discovery under Measurement Error and Linear Non-Gaussian Models
- Independence Testing for Bounded Degree Bayesian Networks
- Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examples
- In Differential Privacy, There is Truth: on Vote-Histogram Leakage in Ensemble Private Learning
- Inducing Equilibria via Incentives: Simultaneous Design-and-Play Ensures Global Convergence
- Inducing Neural Collapse in Imbalanced Learning: Do We Really Need a Learnable Classifier at the End of Deep Neural Network?
- Inductive Logical Query Answering in Knowledge Graphs
- Inference and Sampling for Archimax Copulas
- Infinite-Fidelity Coregionalization for Physical Simulation
- Infinite Recommendation Networks: A Data-Centric Approach
- Influencing Long-Term Behavior in Multiagent Reinforcement Learning
- Information bottleneck theory of high-dimensional regression: relevancy, efficiency and optimality
- Information-Theoretic GAN Compression with Variational Energy-based Model
- Information-Theoretic Principles in Cognitive Systems
- Information-Theoretic Safe Exploration with Gaussian Processes
- Inherently Explainable Reinforcement Learning in Natural Language
- Injecting Domain Knowledge from Empirical Interatomic Potentials to Neural Networks for Predicting Material Properties
- INRAS: Implicit Neural Representation for Audio Scenes
- Insights into Pre-training via Simpler Synthetic Tasks
- InsNet: An Efficient, Flexible, and Performant Insertion-based Text Generation Model
- InsPro: Propagating Instance Query and Proposal for Online Video Instance Segmentation
- Instability and Local Minima in GAN Training with Kernel Discriminators
- Instance-based Learning for Knowledge Base Completion
- Instance-Based Uncertainty Estimation for Gradient-Boosted Regression Trees
- Instance-Dependent Near-Optimal Policy Identification in Linear MDPs via Online Experiment Design
- Instance-optimal PAC Algorithms for Contextual Bandits
- Integral Probability Metrics PAC-Bayes Bounds
- Interaction-Centric AI
- Interaction-Grounded Learning with Action-Inclusive Feedback
- Interaction Modeling with Multiplex Attention
- Intermediate Prototype Mining Transformer for Few-Shot Semantic Segmentation
- InterNLP: Workshop on Interactive Learning for Natural Language Processing
- INTERPOLATE — First Workshop on Interpolation Regularizers and Beyond
- Interpolation and Regularization for Causal Learning
- InterpretDL: Explaining Deep Models in PaddlePaddle
- Interpreting Operation Selection in Differentiable Architecture Search: A Perspective from Influence-Directed Explanations
- Interventions, Where and How? Experimental Design for Causal Models at Scale
- In the Eye of the Beholder: Robust Prediction with Causal User Modeling
- Intra-agent speech permits zero-shot task acquisition
- Intrinsic dimensionality estimation using Normalizing Flows
- Introspective Learning : A Two-Stage approach for Inference in Neural Networks
- Invariance-Aware Randomized Smoothing Certificates
- Invariance Learning based on Label Hierarchy
- Invariance Learning in Deep Neural Networks with Differentiable Laplace Approximations
- Invariant and Transportable Representations for Anti-Causal Domain Shifts
- Inverse Design for Fluid-Structure Interactions using Graph Network Simulators
- Inverse Game Theory for Stackelberg Games: the Blessing of Bounded Rationality
- Invertible Monotone Operators for Normalizing Flows
- In What Ways Are Deep Neural Networks Invariant and How Should We Measure This?
- Iron: Private Inference on Transformers
- Is L2 Physics Informed Loss Always Suitable for Training Physics Informed Neural Network?
- Is a Modular Architecture Enough?
- Is Integer Arithmetic Enough for Deep Learning Training?
- Iso-Dream: Isolating and Leveraging Noncontrollable Visual Dynamics in World Models
- Isometric 3D Adversarial Examples in the Physical World
- Is one annotation enough? - A data-centric image classification benchmark for noisy and ambiguous label estimation
- Is Out-of-Distribution Detection Learnable?
- Is Sortition Both Representative and Fair?
- Is this the Right Neighborhood? Accurate and Query Efficient Model Agnostic Explanations
- Iterative Feature Matching: Toward Provable Domain Generalization with Logarithmic Environments
- Iterative Scene Graph Generation
- Iterative Structural Inference of Directed Graphs
- JAHS-Bench-201: A Foundation For Research On Joint Architecture And Hyperparameter Search
- JAWS: Auditing Predictive Uncertainty Under Covariate Shift
- Joint Entropy Search For Maximally-Informed Bayesian Optimization
- Joint Entropy Search for Multi-Objective Bayesian Optimization
- Joint Estimation and Inference for Data Integration Problems based on Multiple Multi-layered Gaussian Graphical Models
- Joint Learning of 2D-3D Weakly Supervised Semantic Segmentation
- Jump Self-attention: Capturing High-order Statistics in Transformers
- Kantorovich Strikes Back! Wasserstein GANs are not Optimal Transport?
- Kernel Interpolation with Sparse Grids
- Kernel Memory Networks: A Unifying Framework for Memory Modeling
- Kernel Multimodal Continuous Attention
- Kernel similarity matching with Hebbian networks
- KERPLE: Kernelized Relative Positional Embedding for Length Extrapolation
- Keypoint-Guided Optimal Transport with Applications in Heterogeneous Domain Adaptation
- K-LITE: Learning Transferable Visual Models with External Knowledge
- Knowledge-Aware Bayesian Deep Topic Model
- Knowledge Distillation: Bad Models Can Be Good Role Models
- Knowledge Distillation from A Stronger Teacher
- Knowledge Distillation Improves Graph Structure Augmentation for Graph Neural Networks
- K-Radar: 4D Radar Object Detection for Autonomous Driving in Various Weather Conditions
- KSD Aggregated Goodness-of-fit Test
- Label-Aware Global Consistency for Multi-Label Learning with Single Positive Labels
- Label-invariant Augmentation for Semi-Supervised Graph Classification
- Label Noise in Adversarial Training: A Novel Perspective to Study Robust Overfitting
- LAION-5B: An open large-scale dataset for training next generation image-text models
- LAMP: Extracting Text from Gradients with Language Model Priors
- Langevin Autoencoders for Learning Deep Latent Variable Models
- Language Conditioned Spatial Relation Reasoning for 3D Object Grounding
- Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners
- Laplacian Autoencoders for Learning Stochastic Representations
- LAPO: Latent-Variable Advantage-Weighted Policy Optimization for Offline Reinforcement Learning
- LaReL: Language and Reinforcement Learning
- Large-batch Optimization for Dense Visual Predictions: Training Faster R-CNN in 4.2 Minutes
- Large Language Models are Zero-Shot Reasoners
- Large-Scale Differentiable Causal Discovery of Factor Graphs
- Large-scale Optimization of Partial AUC in a Range of False Positive Rates
- Large-Scale Retrieval for Reinforcement Learning
- LASSIE: Learning Articulated Shapes from Sparse Image Ensemble via 3D Part Discovery
- Last-Iterate Convergence of Optimistic Gradient Method for Monotone Variational Inequalities
- LasUIE: Unifying Information Extraction with Latent Adaptive Structure-aware Generative Language Model
- Latency-aware Spatial-wise Dynamic Networks
- Latent Hierarchical Causal Structure Discovery with Rank Constraints
- Latent Planning via Expansive Tree Search
- Layer Freezing & Data Sieving: Missing Pieces of a Generic Framework for Sparse Training
- Lazy and Fast Greedy MAP Inference for Determinantal Point Process
- LBD: Decouple Relevance and Observation for Individual-Level Unbiased Learning to Rank
- LDSA: Learning Dynamic Subtask Assignment in Cooperative Multi-Agent Reinforcement Learning
- Learnable Polyphase Sampling for Shift Invariant and Equivariant Convolutional Networks
- Learning a Condensed Frame for Memory-Efficient Video Class-Incremental Learning
- Learning Active Camera for Multi-Object Navigation
- Learning and Covering Sums of Independent Random Variables with Unbounded Support
- Learning Articulated Rigid Body Dynamics with Lagrangian Graph Neural Network
- Learning Audio-Visual Dynamics Using Scene Graphs for Audio Source Separation
- Learning-Augmented Algorithms for Online Linear and Semidefinite Programming
- Learning-based Motion Planning in Dynamic Environments Using GNNs and Temporal Encoding
- Learning Best Combination for Efficient N:M Sparsity
- Learning Bipartite Graphs: Heavy Tails and Multiple Components
- Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphs
- Learning Chaotic Dynamics in Dissipative Systems
- Learning Concept Credible Models for Mitigating Shortcuts
- Learning Consistency-Aware Unsigned Distance Functions Progressively from Raw Point Clouds
- Learning Contrastive Embedding in Low-Dimensional Space
- Learning Debiased Classifier with Biased Committee
- Learning Deep Input-Output Stable Dynamics
- Learning Dense Object Descriptors from Multiple Views for Low-shot Category Generalization
- Learning Distinct and Representative Modes for Image Captioning
- Learning Distributed and Fair Policies for Network Load Balancing as Markov Potential Game
- Learning Distributions Generated by Single-Layer ReLU Networks in the Presence of Arbitrary Outliers
- Learning Dynamical Systems via Koopman Operator Regression in Reproducing Kernel Hilbert Spaces
- Learning dynamics of deep linear networks with multiple pathways
- Learning Efficient Vision Transformers via Fine-Grained Manifold Distillation
- Learning Energy Networks with Generalized Fenchel-Young Losses
- Learning Enhanced Representation for Tabular Data via Neighborhood Propagation
- Learning Equivariant Segmentation with Instance-Unique Querying
- Learning Expressive Meta-Representations with Mixture of Expert Neural Processes
- Learning Fractional White Noises in Neural Stochastic Differential Equations
- Learning from a Sample in Online Algorithms
- Learning from Distributed Users in Contextual Linear Bandits Without Sharing the Context
- Learning from Few Samples: Transformation-Invariant SVMs with Composition and Locality at Multiple Scales
- Learning from Future: A Novel Self-Training Framework for Semantic Segmentation
- Learning from Label Proportions by Learning with Label Noise
- Learning from Stochastically Revealed Preference
- Learning from Time Series for Health
- Learning Generalizable Models for Vehicle Routing Problems via Knowledge Distillation
- Learning Generalizable Part-based Feature Representation for 3D Point Clouds
- Learning Generalized Policy Automata for Relational Stochastic Shortest Path Problems
- Learning General World Models in a Handful of Reward-Free Deployments
- Learning Graph-embedded Key-event Back-tracing for Object Tracking in Event Clouds
- Learning in Congestion Games with Bandit Feedback
- Learning Individualized Treatment Rules with Many Treatments: A Supervised Clustering Approach Using Adaptive Fusion
- Learning Infinite-Horizon Average-Reward Restless Multi-Action Bandits via Index Awareness
- Learning in Observable POMDPs, without Computationally Intractable Oracles
- Learning interacting dynamical systems with latent Gaussian process ODEs
- Learning Interface Conditions in Domain Decomposition Solvers
- Learning Invariant Graph Representations for Out-of-Distribution Generalization
- Learning Latent Seasonal-Trend Representations for Time Series Forecasting
- Learning Long-Term Crop Management Strategies with CyclesGym
- Learning low-dimensional generalizable natural features from retina using a U-net
- Learning Manifold Dimensions with Conditional Variational Autoencoders
- Learning Meaningful Representations of Life
- Learning Mixed Multinomial Logits with Provable Guarantees
- Learning Modular Simulations for Homogeneous Systems
- Learning Multi-resolution Functional Maps with Spectral Attention for Robust Shape Matching
- Learning Neural Acoustic Fields
- Learning Neural Set Functions Under the Optimal Subset Oracle
- Learning NP-Hard Multi-Agent Assignment Planning using GNN: Inference on a Random Graph and Provable Auction-Fitted Q-learning
- Learning on Arbitrary Graph Topologies via Predictive Coding
- Learning on the Edge: Online Learning with Stochastic Feedback Graphs
- Learning Operators with Coupled Attention
- Learning Optical Flow from Continuous Spike Streams
- Learning Optimal Flows for Non-Equilibrium Importance Sampling
- Learning Options via Compression
- Learning Partial Equivariances From Data
- Learning Physical Dynamics with Subequivariant Graph Neural Networks
- Learning Physics Constrained Dynamics Using Autoencoders
- Learning Predictions for Algorithms with Predictions
- Learning Probabilistic Models from Generator Latent Spaces with Hat EBM
- Learning Recourse on Instance Environment to Enhance Prediction Accuracy
- Learning Representations via a Robust Behavioral Metric for Deep Reinforcement Learning
- Learning Robust Dynamics through Variational Sparse Gating
- Learning Robust Rule Representations for Abstract Reasoning via Internal Inferences
- Learning single-index models with shallow neural networks
- Learning sparse features can lead to overfitting in neural networks
- Learning State-Aware Visual Representations from Audible Interactions
- Learning Structure from the Ground up---Hierarchical Representation Learning by Chunking
- Learning Substructure Invariance for Out-of-Distribution Molecular Representations
- Learning Superpoint Graph Cut for 3D Instance Segmentation
- Learning Symmetric Rules with SATNet
- Learning the Structure of Large Networked Systems Obeying Conservation Laws
- Learning to Accelerate Partial Differential Equations via Latent Global Evolution
- Learning to Attack Federated Learning: A Model-based Reinforcement Learning Attack Framework
- Learning to Branch with Tree MDPs
- Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generation
- Learning to Compare Nodes in Branch and Bound with Graph Neural Networks
- Learning to Configure Computer Networks with Neural Algorithmic Reasoning
- Learning to Constrain Policy Optimization with Virtual Trust Region
- Learning to Discover and Detect Objects
- Learning to Drop Out: An Adversarial Approach to Training Sequence VAEs
- Learning to Find Proofs and Theorems by Learning to Refine Search Strategies: The Case of Loop Invariant Synthesis
- Learning to Follow Instructions in Text-Based Games
- Learning to Generate Inversion-Resistant Model Explanations
- Learning to Mitigate AI Collusion on Economic Platforms
- Learning to Navigate Wikipedia by Taking Random Walks
- Learning to Reason with Neural Networks: Generalization, Unseen Data and Boolean Measures
- Learning to Reconstruct Missing Data from Spatiotemporal Graphs with Sparse Observations
- Learning to Re-weight Examples with Optimal Transport for Imbalanced Classification
- Learning to Sample and Aggregate: Few-shot Reasoning over Temporal Knowledge Graphs
- Learning to Scaffold: Optimizing Model Explanations for Teaching
- Learning to Share in Networked Multi-Agent Reinforcement Learning
- Learning Tractable Probabilistic Models from Inconsistent Local Estimates
- Learning Two-Player Markov Games: Neural Function Approximation and Correlated Equilibrium
- Learning (Very) Simple Generative Models Is Hard
- Learning Viewpoint-Agnostic Visual Representations by Recovering Tokens in 3D Space
- Learning with convolution and pooling operations in kernel methods
- Learning with little mixing
- Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering
- Learn to Match with No Regret: Reinforcement Learning in Markov Matching Markets
- Learn what matters: cross-domain imitation learning with task-relevant embeddings
- LECO: Learnable Episodic Count for Task-Specific Intrinsic Reward
- Left Heavy Tails and the Effectiveness of the Policy and Value Networks in DNN-based best-first search for Sokoban Planning
- Less-forgetting Multi-lingual Fine-tuning
- Lethal Dose Conjecture on Data Poisoning
- Let Images Give You More: Point Cloud Cross-Modal Training for Shape Analysis
- Leveraging Factored Action Spaces for Efficient Offline Reinforcement Learning in Healthcare
- Leveraging Inter-Layer Dependency for Post -Training Quantization
- Leveraging the Hints: Adaptive Bidding in Repeated First-Price Auctions
- LGDN: Language-Guided Denoising Network for Video-Language Modeling
- LieGG: Studying Learned Lie Group Generators
- Lifelong Learning Machines
- Lifelong Neural Predictive Coding: Learning Cumulatively Online without Forgetting
- Lifting the Information Ratio: An Information-Theoretic Analysis of Thompson Sampling for Contextual Bandits
- Lifting Weak Supervision To Structured Prediction
- LIFT: Language-Interfaced Fine-Tuning for Non-language Machine Learning Tasks
- Linear Label Ranking with Bounded Noise
- Linear tree shap
- LION: Latent Point Diffusion Models for 3D Shape Generation
- Lipschitz Bandits with Batched Feedback
- LIPS - Learning Industrial Physical Simulation benchmark suite
- LISA: Learning Interpretable Skill Abstractions from Language
- List-Decodable Sparse Mean Estimation
- List-Decodable Sparse Mean Estimation via Difference-of-Pairs Filtering
- Listen to Interpret: Post-hoc Interpretability for Audio Networks with NMF
- LiteTransformerSearch: Training-free Neural Architecture Search for Efficient Language Models
- LobsDICE: Offline Learning from Observation via Stationary Distribution Correction Estimation
- Local Bayesian optimization via maximizing probability of descent
- Local-Global MCMC kernels: the best of both worlds
- Local Identifiability of Deep ReLU Neural Networks: the Theory
- Local Latent Space Bayesian Optimization over Structured Inputs
- Local Linear Convergence of Gradient Methods for Subspace Optimization via Strict Complementarity
- Locally Hierarchical Auto-Regressive Modeling for Image Generation
- Local Metric Learning for Off-Policy Evaluation in Contextual Bandits with Continuous Actions
- Local Spatiotemporal Representation Learning for Longitudinally-consistent Neuroimage Analysis
- Locating and Editing Factual Associations in GPT
- LOG: Active Model Adaptation for Label-Efficient OOD Generalization
- Log-Concave and Multivariate Canonical Noise Distributions for Differential Privacy
- Logical Activation Functions: Logit-space equivalents of Probabilistic Boolean Operators
- Logical Credal Networks
- LogiGAN: Learning Logical Reasoning via Adversarial Pre-training
- Log-Linear-Time Gaussian Processes Using Binary Tree Kernels
- Log-Polar Space Convolution Layers
- Long-Form Video-Language Pre-Training with Multimodal Temporal Contrastive Learning
- Long Range Graph Benchmark
- Look Around and Refer: 2D Synthetic Semantics Knowledge Distillation for 3D Visual Grounding
- Look More but Care Less in Video Recognition
- Look where you look! Saliency-guided Q-networks for generalization in visual Reinforcement Learning
- Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Speech Processing
- "Lossless" Compression of Deep Neural Networks: A High-dimensional Neural Tangent Kernel Approach
- Lost in Latent Space: Examining failures of disentangled models at combinatorial generalisation
- LOT: Layer-wise Orthogonal Training on Improving l2 Certified Robustness
- Lottery Tickets on a Data Diet: Finding Initializations with Sparse Trainable Networks
- Lower Bounds and Nearly Optimal Algorithms in Distributed Learning with Communication Compression
- Lower Bounds on Randomly Preconditioned Lasso via Robust Sparse Designs
- Low-rank lottery tickets: finding efficient low-rank neural networks via matrix differential equations
- Low-Rank Modular Reinforcement Learning via Muscle Synergy
- Low-rank Optimal Transport: Approximation, Statistics and Debiasing
- LSAR: Efficient Leverage Score Sampling Algorithm for the Analysis of Big Time Series Data
- LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learning
- LTMD: Learning Improvement of Spiking Neural Networks with Learnable Thresholding Neurons and Moderate Dropout
- Luckiness in Multiscale Online Learning
- M4I: Multi-modal Models Membership Inference
- M2N: Mesh Movement Networks for PDE Solvers
- M³ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design
- M4Singer: A Multi-Style, Multi-Singer and Musical Score Provided Mandarin Singing Corpus
- MABSplit: Faster Forest Training Using Multi-Armed Bandits
- MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields
- Machine Learning and the Physical Sciences
- Machine Learning for Autonomous Driving
- Machine Learning for Systems
- Machine Learning in Structural Biology Workshop
- Machine Learning on Graphs: A Model and Comprehensive Taxonomy
- MACK: Multimodal Aligned Conceptual Knowledge for Unpaired Image-text Matching
- MAgNet: Mesh Agnostic Neural PDE Solver
- Make an Omelette with Breaking Eggs: Zero-Shot Learning for Novel Attribute Synthesis
- Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation Approach
- Make Some Noise: Reliable and Efficient Single-Step Adversarial Training
- Making Look-Ahead Active Learning Strategies Feasible with Neural Tangent Kernels
- Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measure
- Manifold Interpolating Optimal-Transport Flows for Trajectory Inference
- Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigation
- Markov Chain Score Ascent: A Unifying Framework of Variational Inference with Markovian Gradients
- Markovian Interference in Experiments
- Marksman Backdoor: Backdoor Attacks with Arbitrary Target Class
- Mask-based Latent Reconstruction for Reinforcement Learning
- Masked Autoencoders As Spatiotemporal Learners
- Masked Autoencoders that Listen
- Masked Autoencoding for Scalable and Generalizable Decision Making
- Masked Generative Adversarial Networks are Data-Efficient Generation Learners
- Masked Prediction: A Parameter Identifiability View
- Mask Matching Transformer for Few-Shot Segmentation
- MaskPlace: Fast Chip Placement via Reinforced Visual Representation Learning
- MaskTune: Mitigating Spurious Correlations by Forcing to Explore
- Matching in Multi-arm Bandit with Collision
- MATE: Benchmarking Multi-Agent Reinforcement Learning in Distributed Target Coverage Control
- MATH-AI: Toward Human-Level Mathematical Reasoning
- Matrix Multiplicative Weights Updates in Quantum Zero-Sum Games: Conservation Laws & Recurrence
- Matryoshka Representation Learning
- MAtt: A Manifold Attention Network for EEG Decoding
- Maximizing and Satisficing in Multi-armed Bandits with Graph Information
- Maximizing Revenue under Market Shrinkage and Market Uncertainty
- Maximum a posteriori natural scene reconstruction from retinal ganglion cells with deep denoiser priors
- Maximum Class Separation as Inductive Bias in One Matrix
- Maximum Common Subgraph Guided Graph Retrieval: Late and Early Interaction Networks
- Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees
- Maximum Likelihood Training of Implicit Nonlinear Diffusion Model
- Max-Min Off-Policy Actor-Critic Method Focusing on Worst-Case Robustness to Model Misspecification
- MBW: Multi-view Bootstrapping in the Wild
- MCL-GAN: Generative Adversarial Networks with Multiple Specialized Discriminators
- MCMAE: Masked Convolution Meets Masked Autoencoders
- MCVD - Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation
- Mean Estimation in High-Dimensional Binary Markov Gaussian Mixture Models
- Mean Estimation with User-level Privacy under Data Heterogeneity
- Measures of Information Reflect Memorization Patterns
- Measuring and Reducing Model Update Regression in Structured Prediction for NLP
- Measuring Data Reconstruction Defenses in Collaborative Inference Systems
- Medical Imaging meets NeurIPS
- Memorization and Optimization in Deep Neural Networks with Minimum Over-parameterization
- Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models
- Memory Efficient Continual Learning with Transformers
- Memory in Artificial and Real Intelligence (MemARI)
- Memory safe computations with XLA compiler
- MEMO: Test Time Robustness via Adaptation and Augmentation
- Merging Models with Fisher-Weighted Averaging
- Mesoscopic modeling of hidden spiking neurons
- Meta-Album: Multi-domain Meta-Dataset for Few-Shot Image Classification
- Meta-Auto-Decoder for Solving Parametric Partial Differential Equations
- Meta-Complementing the Semantics of Short Texts in Neural Topic Models
- Meta-DMoE: Adapting to Domain Shift by Meta-Distillation from Mixture-of-Experts
- Meta-Learning Dynamics Forecasting Using Task Inference
- Meta-Learning with Self-Improving Momentum Target
- MetaMask: Revisiting Dimensional Confounder for Self-Supervised Learning
- Meta-Query-Net: Resolving Purity-Informativeness Dilemma in Open-set Active Learning
- Meta Reinforcement Learning with Finite Training Tasks - a Density Estimation Approach
- Meta-Reinforcement Learning with Self-Modifying Networks
- Meta-Reward-Net: Implicitly Differentiable Reward Learning for Preference-based Reinforcement Learning
- MetaTeacher: Coordinating Multi-Model Domain Adaptation for Medical Image Classification
- Meta-ticket: Finding optimal subnetworks for few-shot learning within randomly initialized neural networks
- MetricFormer: A Unified Perspective of Correlation Exploring in Similarity Learning
- METS-CoV: A Dataset of Medical Entity and Targeted Sentiment on COVID-19 Related Tweets
- MExMI: Pool-based Active Model Extraction Crossover Membership Inference
- MGNNI: Multiscale Graph Neural Networks with Implicit Layers
- Micro and Macro Level Graph Modeling for Graph Variational Auto-Encoders
- Mildly Conservative Q-Learning for Offline Reinforcement Learning
- Mind Reader: Reconstructing complex images from brain activities
- Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning
- MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge
- Mingling Foresight with Imagination: Model-Based Cooperative Multi-Agent Reinforcement Learning
- Minimax Optimal Algorithms for Fixed-Budget Best Arm Identification
- Minimax Optimal Fixed-Budget Best Arm Identification in Linear Bandits
- Minimax-Optimal Multi-Agent RL in Markov Games With a Generative Model
- Minimax Optimal Online Imitation Learning via Replay Estimation
- Minimax Regret for Cascading Bandits
- Mining Multi-Label Samples from Single Positive Labels
- Mining Unseen Classes via Regional Objectness: A Simple Baseline for Incremental Segmentation
- MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Training
- Mirror Descent Maximizes Generalized Margin and Can Be Implemented Efficiently
- Mirror Descent with Relative Smoothness in Measure Spaces, with application to Sinkhorn and EM
- Mismatched No More: Joint Model-Policy Optimization for Model-Based RL
- MissDAG: Causal Discovery in the Presence of Missing Data with Continuous Additive Noise Models
- Missing Data Imputation and Acquisition with Deep Hierarchical Models and Hamiltonian Monte Carlo
- Misspecified Phase Retrieval with Generative Priors
- Mix and Reason: Reasoning over Semantic Topology with Data Mixing for Domain Generalization
- Mixture-of-Experts with Expert Choice Routing
- MoCapAct: A Multi-Task Dataset for Simulated Humanoid Control
- MoCoDA: Model-based Counterfactual Data Augmentation
- Model-Based Imitation Learning for Urban Driving
- Model-based Lifelong Reinforcement Learning with Bayesian Exploration
- Model-Based Offline Reinforcement Learning with Pessimism-Modulated Dynamics Belief
- Model-Based Opponent Modeling
- Model-based RL with Optimistic Posterior Sampling: Structural Conditions and Sample Complexity
- Model-based Safe Deep Reinforcement Learning via a Constrained Proximal Policy Optimization Algorithm
- Modeling Human Exploration Through Resource-Rational Reinforcement Learning
- Modeling the Machine Learning Multiverse
- Modeling Transitivity and Cyclicity in Directed Graphs via Binary Code Box Embeddings
- Model Preserving Compression for Neural Networks
- Models Out of Line: A Fourier Lens on Distribution Shift Robustness
- Model Zoos: A Dataset of Diverse Populations of Neural Network Models
- Moderate-fitting as a Natural Backdoor Defender for Pre-trained Language Models
- Modular Flows: Differential Molecular Generation
- Module-Aware Optimization for Auxiliary Learning
- MoGDE: Boosting Mobile Monocular 3D Object Detection with Ground Depth Estimation
- Molecule Generation by Principal Subgraph Mining and Assembling
- MOMA-LRG: Language-Refined Graphs for Multi-Object Multi-Actor Activity Parsing
- Moment Distributionally Robust Tree Structured Prediction
- Momentum Adversarial Distillation: Handling Large Distribution Shifts in Data-Free Knowledge Distillation
- Momentum Aggregation for Private Non-convex ERM
- Monocular Dynamic View Synthesis: A Reality Check
- MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction
- Monte Carlo Augmented Actor-Critic for Sparse Reward Deep Reinforcement Learning from Suboptimal Demonstrations
- Monte Carlo Tree Descent for Black-Box Optimization
- Monte Carlo Tree Search based Variable Selection for High Dimensional Bayesian Optimization
- MORA: Improving Ensemble Robustness Evaluation with Model Reweighing Attack
- MorphTE: Injecting Morphology in Tensorized Embeddings
- Most Activation Functions Can Win the Lottery Without Excessive Depth
- Motion Transformer with Global Intention Localization and Local Movement Refinement
- Movement Penalized Bayesian Optimization with Application to Wind Energy Systems
- MOVE: Unsupervised Movable Object Segmentation and Detection
- MoVQ: Modulating Quantized Vectors for High-Fidelity Image Generation
- mRI: Multi-modal 3D Human Pose Estimation Dataset using mmWave, RGB-D, and Inertial Sensors
- MSDS: A Large-Scale Chinese Signature and Token Digit String Dataset for Handwriting Verification
- MsSVT: Mixed-scale Sparse Voxel Transformer for 3D Object Detection on Point Clouds
- MTNeuro: A Benchmark for Evaluating Representations of Brain Structure Across Multiple Levels of Abstraction
- Muffliato: Peer-to-Peer Privacy Amplification for Decentralized Optimization and Averaging
- Multi-agent Dynamic Algorithm Configuration
- Multi-Agent Multi-Armed Bandits with Limited Communication
- Multi-agent Performative Prediction with Greedy Deployment and Consensus Seeking Agents
- Multiagent Q-learning with Sub-Team Coordination
- Multi-Agent Reinforcement Learning is a Sequence Modeling Problem
- Multi-block Min-max Bilevel Optimization with Applications in Multi-task Deep AUC Maximization
- Multi-block-Single-probe Variance Reduced Estimator for Coupled Compositional Optimization
- Multi-Class H-Consistency Bounds
- Multiclass Learnability Beyond the PAC Framework: Universal Rates and Partial Concept Classes
- Multi-dataset Training of Transformers for Robust Action Recognition
- Multi-Fidelity Best-Arm Identification
- Multi-fidelity Monte Carlo: a pseudo-marginal approach
- Multi-Game Decision Transformers
- Multi-Granularity Cross-modal Alignment for Generalized Medical Visual Representation Learning
- MultiGuard: Provably Robust Multi-label Classification against Adversarial Examples
- Multi-Instance Causal Representation Learning for Instance Label Prediction and Out-of-Distribution Generalization
- Multi-layer State Evolution Under Random Convolutional Design
- Multi-LexSum: Real-world Summaries of Civil Rights Lawsuits at Multiple Granularities
- Multilingual Abusive Comment Detection at Scale for Indic Languages
- Multi-Lingual Acquisition on Multimodal Pre-training for Cross-modal Retrieval
- Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts
- Multi-modal Grouping Network for Weakly-Supervised Audio-Visual Video Parsing
- Multi-objective Deep Data Generation with Correlated Property Control
- Multi-Objective Deep Learning with Adaptive Reference Vectors
- Multi-Sample Training for Neural Image Compression
- Multi-Scale Adaptive Network for Single Image Denoising
- MultiScan: Scalable RGBD scanning for 3D environments with articulated objects
- Multitasking Models are Robust to Structural Failure: A Neural Model for Bilingual Cognitive Reserve
- Multivariate Time-Series Forecasting with Temporal Polynomial Graph Neural Networks
- Multiview Human Body Reconstruction from Uncalibrated Cameras
- Multi-view Subspace Clustering on Topological Manifold
- Museformer: Transformer with Fine- and Coarse-Grained Attention for Music Generation
- Mutual Information Divergence: A Unified Metric for Multimodal Generative Models
- MVP-N: A Dataset and Benchmark for Real-World Multi-View Object Classification
- Myriad: a real-world testbed to bridge trajectory optimization and deep learning
- NAS-Bench-360: Benchmarking Neural Architecture Search on Diverse Tasks
- NAS-Bench-Graph: Benchmarking Graph Neural Architecture Search
- NAS-Bench-Suite-Zero: Accelerating Research on Zero Cost Proxies
- Natural Color Fool: Towards Boosting Black-box Unrestricted Attacks
- Natural gradient enables fast sampling in spiking neural networks
- Natural image synthesis for the retina with variational information bottleneck representation
- NaturalProver: Grounded Mathematical Proof Generation with Language Models
- Navigating Memory Construction by Global Pseudo-Task Simulation for Continual Learning
- NCP: Neural Correspondence Prior for Effective Unsupervised Shape Matching
- Near Instance-Optimal PAC Reinforcement Learning for Deterministic MDPs
- Near-Isometric Properties of Kronecker-Structured Random Tensor Embeddings
- Nearly Optimal Algorithms for Linear Contextual Bandits with Adversarial Corruptions
- Nearly Optimal Best-of-Both-Worlds Algorithms for Online Learning with Feedback Graphs
- Nearly-Tight Bounds for Testing Histogram Distributions
- Near-Optimal Collaborative Learning in Bandits
- Near-Optimal Correlation Clustering with Privacy
- Near-Optimal Goal-Oriented Reinforcement Learning in Non-Stationary Environments
- Near-Optimal Multi-Agent Learning for Safe Coverage Control
- Near-Optimal No-Regret Learning Dynamics for General Convex Games
- Near-Optimal Private and Scalable k-Clustering
- Near-Optimal Randomized Exploration for Tabular Markov Decision Processes
- Near-Optimal Regret Bounds for Multi-batch Reinforcement Learning
- Near-Optimal Regret for Adversarial MDP with Delayed Bandit Feedback
- Near-Optimal Sample Complexity Bounds for Constrained MDPs
- NeMF: Neural Motion Fields for Kinematic Animation
- NeoRL: A Near Real-World Benchmark for Offline Reinforcement Learning
- Nest Your Adaptive Algorithm for Parameter-Agnostic Nonconvex Minimax Optimization
- Network change point localisation under local differential privacy
- NeuForm: Adaptive Overfitting for Neural Shape Editing
- NeuPhysics: Editable Neural Geometry and Physics from Monocular Videos
- Neur2SP: Neural Two-Stage Stochastic Programming
- Neural Abstractions
- Neural Approximation of Graph Topological Features
- Neural Attentive Circuits
- Neural Basis Models for Interpretability
- Neural Circuit Architectural Priors for Embodied Control
- Neural Collapse with Normalized Features: A Geometric Analysis over the Riemannian Manifold
- Neural Conservation Laws: A Divergence-Free Perspective
- Neural Differential Equations for Learning to Program Neural Nets Through Continuous Learning Rules
- Neural Estimation of Submodular Functions with Applications to Differentiable Subset Selection
- Neural Lyapunov Control of Unknown Nonlinear Systems with Stability Guarantees
- Neural Matching Fields: Implicit Representation of Matching Fields for Visual Correspondence
- Neural Network Architecture Beyond Width and Depth
- Neural Payoff Machines: Predicting Fair and Stable Payoff Allocations Among Team Members
- Neural Set Function Extensions: Learning with Discrete Functions in High Dimensions
- Neural Shape Deformation Priors
- Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
- Neural Stochastic Control
- Neural Stochastic PDEs: Resolution-Invariant Learning of Continuous Spatiotemporal Dynamics
- Neural Surface Reconstruction of Dynamic Scenes with Monocular RGB-D Camera
- Neural-Symbolic Entangled Framework for Complex Query Answering
- Neural Temporal Walks: Motif-Aware Representation Learning on Continuous-Time Dynamic Graphs
- Neural Topological Ordering for Computation Graphs
- Neural Transmitted Radiance Fields
- NeurIPS 2022 Workshop on Meta-Learning
- NeurIPS 2022 Workshop on Score-Based Methods
- NeurOLight: A Physics-Agnostic Neural Operator Enabling Parametric Photonic Device Simulation
- Neuron with Steady Response Leads to Better Generalization
- NeuroSchedule: A Novel Effective GNN-based Scheduling Method for High-level Synthesis
- Neurosymbolic Deep Generative Models for Sequence Data with Relational Constraints
- Neurosymbolic Programming
- New Definitions and Evaluations for Saliency Methods: Staying Intrinsic, Complete and Sound
- New Frontiers in Graph Learning
- New Lower Bounds for Private Estimation and a Generalized Fingerprinting Lemma
- Nocturne: a scalable driving benchmark for bringing multi-agent learning one step closer to the real world
- NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification
- No Free Lunch from Deep Learning in Neuroscience: A Case Study through Models of the Entorhinal-Hippocampal Circuit
- Noise Attention Learning: Enhancing Noise Robustness by Gradient Scaling
- NOMAD: Nonlinear Manifold Decoders for Operator Learning
- Non-asymptotic and Accurate Learning of Nonlinear Dynamical Systems
- Non-Convex Bilevel Games with Critical Point Selection Maps
- Non-convex online learning via algorithmic equivalence
- Non-deep Networks
- Non-Gaussian Tensor Programs
- Non-identifiability and the Blessings of Misspecification in Models of Molecular Fitness
- Non-Linear Coordination Graphs
- Nonlinear MCMC for Bayesian Machine Learning
- Nonlinear Sufficient Dimension Reduction with a Stochastic Neural Network
- Non-Linguistic Supervision for Contrastive Learning of Sentence Embeddings
- Non-Markovian Reward Modelling from Trajectory Labels via Interpretable Multiple Instance Learning
- Non-Monotonic Latent Alignments for CTC-Based Non-Autoregressive Machine Translation
- Non-monotonic Resource Utilization in the Bandits with Knapsacks Problem
- Nonnegative Tensor Completion via Integer Optimization
- Nonparametric Uncertainty Quantification for Single Deterministic Neural Network
- Non-rigid Point Cloud Registration with Neural Deformation Pyramid
- Non-Stationary Bandits under Recharging Payoffs: Improved Planning with Sublinear Regret
- Non-stationary Bandits with Knapsacks
- Nonstationary Dual Averaging and Online Fair Allocation
- Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting
- No-regret learning in games with noisy feedback: Faster rates and adaptivity via learning rate separation
- Normalizing Flows for Knockoff-free Controlled Feature Selection
- Not All Bits have Equal Value: Heterogeneous Precisions via Trainable Noise
- NOTE: Robust Continual Test-time Adaptation Against Temporal Correlation
- Not too little, not too much: a theoretical analysis of graph (over)smoothing
- NS3: Neuro-symbolic Semantic Code Search
- NSNet: A General Neural Probabilistic Framework for Satisfiability Problems
- NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesis
- Obj2Seq: Formatting Objects as Sequences with Class Prompt for Visual Tasks
- Object-Category Aware Reinforcement Learning
- Object Representations as Fixed Points: Training Iterative Refinement Algorithms with Implicit Differentiation
- Object Scene Representation Transformer
- OccGen: Selection of Real-world Multilingual Parallel Data Balanced in Gender within Occupations
- Offline Goal-Conditioned Reinforcement Learning via f-Advantage Regression
- Offline Multi-Agent Reinforcement Learning with Knowledge Distillation
- Off-Policy Evaluation for Action-Dependent Non-stationary Environments
- Off-Policy Evaluation for Episodic Partially Observable Markov Decision Processes under Non-Parametric Models
- Off-Policy Evaluation with Deficient Support Using Side Information
- Off-Policy Evaluation with Policy-Dependent Optimization Response
- Off-Team Learning
- OGC: Unsupervised 3D Object Segmentation from Rigid Dynamics of Point Clouds
- Okapi: Generalising Better by Making Statistical Matches Match
- Old can be Gold: Better Gradient Flow can Make Vanilla-GCNs Great Again
- OLIVES Dataset: Ophthalmic Labels for Investigating Visual Eye Semantics
- OmniVL: One Foundation Model for Image-Language and Video-Language Tasks
- On A Mallows-type Model For (Ranked) Choices
- On Analyzing Generative and Denoising Capabilities of Diffusion-based Deep Generative Models
- On Batch Teaching with Sample Complexity Bounded by VCD
- On Computing Probabilistic Explanations for Decision Trees
- On Convergence of FedProx: Local Dissimilarity Invariant Bounds, Non-smoothness and Beyond
- On Deep Generative Models for Approximation and Estimation of Distributions on Manifolds
- On-Demand Sampling: Learning Optimally from Multiple Distributions
- On-Device Training Under 256KB Memory
- On Divergence Measures for Bayesian Pseudocoresets
- On Efficient Online Imitation Learning via Classification
- One for All: Simultaneous Metric and Preference Learning over Multiple Users
- One-Inlier is First: Towards Efficient Position Encoding for Point Cloud Registration
- On Elimination Strategies for Bandit Fixed-Confidence Identification
- On Embeddings for Numerical Features in Tabular Deep Learning
- One Model to Edit Them All: Free-Form Text-Driven Image Manipulation with Semantic Modulations
- On Enforcing Better Conditioned Meta-Learning for Rapid Few-Shot Adaptation
- OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Models
- One Positive Label is Sufficient: Single-Positive Multi-Label Learning with Label Enhancement
- One-shot Neural Backdoor Erasing via Adversarial Weight Masking
- On Feature Learning in the Presence of Spurious Correlations
- On Gap-dependent Bounds for Offline Reinforcement Learning
- On global convergence of ResNets: From finite to infinite width using linear parameterization
- On Image Segmentation With Noisy Labels: Characterization and Volume Properties of the Optimal Solutions to Accuracy and Dice
- On Infinite Separations Between Simple and Optimal Mechanisms
- On Kernelized Multi-Armed Bandits with Constraints
- On Learning and Refutation in Noninteractive Local Differential Privacy
- On Learning Fairness and Accuracy on Multiple Subgroups
- On Leave-One-Out Conditional Mutual Information For Generalization
- Online Agnostic Multiclass Boosting
- Online Algorithms for the Santa Claus Problem
- Online Allocation and Learning in the Presence of Strategic Agents
- Online Bipartite Matching with Advice: Tight Robustness-Consistency Tradeoffs for the Two-Stage Model
- Online Convex Optimization with Hard Constraints: Towards the Best of Two Worlds and Beyond
- Online Decision Mediation
- Online Deep Equilibrium Learning for Regularization by Denoising
- Online Frank-Wolfe with Arbitrary Delays
- Online Learning and Pricing for Network Revenue Management with Reusable Resources
- Online Minimax Multiobjective Optimization: Multicalibeating and Other Applications
- Online Neural Sequence Detection with Hierarchical Dirichlet Point Process
- Online Nonnegative CP-dictionary Learning for Markovian Data
- Online PAC-Bayes Learning
- Online Reinforcement Learning for Mixed Policy Scopes
- Online Training Through Time for Spiking Neural Networks
- On Margin Maximization in Linear and ReLU Networks
- On Margins and Generalisation for Voting Classifiers
- On Measuring Excess Capacity in Neural Networks
- On Non-Linear operators for Geometric Deep Learning
- On Optimal Learning Under Targeted Data Poisoning
- On Privacy and Personalization in Cross-Silo Federated Learning
- On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting
- On Robust Multiclass Learnability
- On Sample Optimality in Personalized Collaborative and Federated Learning
- On Scalable Testing of Samplers
- On Scrambling Phenomena for Randomly Initialized Recurrent Networks
- On the Adversarial Robustness of Mixture of Experts
- On the Approximation of Cooperative Heterogeneous Multi-Agent Reinforcement Learning (MARL) using Mean Field Control (MFC)
- On the Complexity of Adversarial Decision Making
- On the consistent estimation of optimal Receiver Operating Characteristic (ROC) curve
- On the convergence of policy gradient methods to Nash equilibria in general stochastic games
- On the Convergence of Stochastic Multi-Objective Gradient Manipulation and Beyond
- On the Convergence Theory for Hessian-Free Bilevel Algorithms
- On the detrimental effect of invariances in the likelihood for variational inference
- On the difficulty of learning chaotic dynamics with RNNs
- On the Discrimination Risk of Mean Aggregation Feature Imputation in Graphs
- On the Double Descent of Random Features Models Trained with SGD
- On the Effectiveness of Fine-tuning Versus Meta-reinforcement Learning
- On the Effectiveness of Lipschitz-Driven Rehearsal in Continual Learning
- On the Effectiveness of Persistent Homology
- On the Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias
- On the Effect of Pre-training for Transformer in Different Modality on Offline Reinforcement Learning
- On the Efficient Implementation of High Accuracy Optimality of Profile Maximum Likelihood
- On the Epistemic Limits of Personalized Prediction
- On the Frequency-bias of Coordinate-MLPs
- On the Generalizability and Predictability of Recommender Systems
- On the generalization of learning algorithms that do not converge
- On the Generalization Power of the Overfitted Three-Layer Neural Tangent Kernel Model
- On the Global Convergence Rates of Decentralized Softmax Gradient Play in Markov Potential Games
- On the Identifiability of Nonlinear ICA: Sparsity and Beyond
- On the Importance of Gradient Norm in PAC-Bayesian Bounds
- On the inability of Gaussian process regression to optimally learn compositional functions
- On the Interpretability of Regularisation for Neural Networks Through Model Gradient Similarity
- On the Learning Mechanisms in Physical Reasoning
- On the Limitations of Stochastic Pre-processing Defenses
- On the non-universality of deep learning: quantifying the cost of symmetry
- On the Parameterization and Initialization of Diagonal State Space Models
- On the relationship between variational inference and auto-associative memory
- On the Representation Collapse of Sparse Mixture of Experts
- On the Robustness of Deep Clustering Models: Adversarial Attacks and Defenses
- On the Robustness of Graph Neural Diffusion to Topology Perturbations
- On the role of overparameterization in off-policy Temporal Difference learning with linear function approximation
- On the Safety of Interpretable Machine Learning: A Maximum Deviation Approach
- On the Sample Complexity of Stabilizing LTI Systems on a Single Trajectory
- On the SDEs and Scaling Rules for Adaptive Gradient Algorithms
- On the Spectral Bias of Convolutional Neural Tangent and Gaussian Process Kernels
- On the Stability and Scalability of Node Perturbation Learning
- On the Statistical Efficiency of Reward-Free Exploration in Non-Linear RL
- On the Strong Correlation Between Model Invariance and Generalization
- On the Symmetries of Deep Learning Models and their Internal Representations
- On the symmetries of the synchronization problem in Cryo-EM: Multi-Frequency Vector Diffusion Maps on the Projective Plane
- On the Theoretical Properties of Noise Correlation in Stochastic Optimization
- On the Tradeoff Between Robustness and Fairness
- Ontologue: Declarative Benchmark Construction for Ontological Multi-Label Classification
- On Translation and Reconstruction Guarantees of the Cycle-Consistent Generative Adversarial Networks
- On Uncertainty, Tempering, and Data Augmentation in Bayesian Classification
- OOD Link Prediction Generalization Capabilities of Message-Passing GNNs in Larger Test Graphs
- OpenAUC: Towards AUC-Oriented Open-Set Recognition
- Open-Ended Reinforcement Learning with Neural Reward Functions
- OpenFilter: A Framework to Democratize Research Access to Social Media AR Filters
- OpenFWI: Large-scale Multi-structural Benchmark Datasets for Full Waveform Inversion
- Open High-Resolution Satellite Imagery: The WorldStrat Dataset – With Application to Super-Resolution
- OpenOOD: Benchmarking Generalized Out-of-Distribution Detection
- OPEN: Orthogonal Propagation with Ego-Network Modeling
- OpenSRH: optimizing brain tumor surgery using intraoperative stimulated Raman histology
- OpenXAI: Towards a Transparent Evaluation of Model Explanations
- Operative dimensions in unconstrained connectivity of recurrent neural networks
- Operator Splitting Value Iteration
- OPT 2022: Optimization for Machine Learning
- Optimal Algorithms for Decentralized Stochastic Variational Inequalities
- Optimal and Adaptive Monteiro-Svaiter Acceleration
- Optimal Binary Classification Beyond Accuracy
- Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning
- Optimal Comparator Adaptive Online Learning with Switching Cost
- Optimal Dynamic Regret in LQR Control
- Optimal Efficiency-Envy Trade-Off via Optimal Transport
- Optimal-er Auctions through Attention
- Optimal Gradient Sliding and its Application to Optimal Distributed Optimization Under Similarity
- Optimality and Stability in Non-Convex Smooth Games
- (Optimal) Online Bipartite Matching with Degree Information
- Optimal Positive Generation via Latent Transformation for Contrastive Learning
- Optimal Query Complexities for Dynamic Trace Estimation
- Optimal Rates for Regularized Conditional Mean Embedding Learning
- Optimal Scaling for Locally Balanced Proposals in Discrete Spaces
- Optimal Transport-based Identity Matching for Identity-invariant Facial Expression Recognition
- Optimal Transport of Classifiers to Fairness
- Optimal Weak to Strong Learning
- Optimistic Mirror Descent Either Converges to Nash or to Strong Coarse Correlated Equilibria in Bimatrix Games
- Optimistic Posterior Sampling for Reinforcement Learning with Few Samples and Tight Guarantees
- Optimistic Tree Searches for Combinatorial Black-Box Optimization
- Optimizing Data Collection for Machine Learning
- Optimizing Relevance Maps of Vision Transformers Improves Robustness
- Oracle-Efficient Online Learning for Smoothed Adversaries
- Oracle Inequalities for Model Selection in Offline Reinforcement Learning
- Ordered Subgraph Aggregation Networks
- Order-Invariant Cardinality Estimators Are Differentially Private
- Order up! The Benefits of Higher-Order Optimization in Machine Learning
- OrdinalCLIP: Learning Rank Prompts for Language-Guided Ordinal Regression
- ORIENT: Submodular Mutual Information Measures for Data Subset Selection under Distribution Shift
- Orthogonal Transformer: An Efficient Vision Transformer Backbone with Token Orthogonalization
- Oscillatory Tracking of Continuous Attractor Neural Networks Account for Phase Precession and Procession of Hippocampal Place Cells
- OST: Improving Generalization of DeepFake Detection via One-Shot Test-Time Training
- OTKGE: Multi-modal Knowledge Graph Embeddings via Optimal Transport
- Outlier-Robust Sparse Estimation via Non-Convex Optimization
- Outlier-Robust Sparse Mean Estimation for Heavy-Tailed Distributions
- Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models
- Out-of-Distribution Detection via Conditional Kernel Independence Model
- Out-of-Distribution Detection with An Adaptive Likelihood Ratio on Informative Hierarchical VAE
- Outsourcing Training without Uploading Data via Efficient Collaborative Open-Source Sampling
- Overparameterization from Computational Constraints
- P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Prompting
- PAC: Assisted Value Factorization with Counterfactual Predictions in Multi-Agent Reinforcement Learning
- PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization
- PaCo: Parameter-Compositional Multi-task Reinforcement Learning
- PAC Prediction Sets for Meta-Learning
- PALBERT: Teaching ALBERT to Ponder
- PALMER: Perception - Action Loop with Memory for Long-Horizon Planning
- Palm up: Playing in the Latent Manifold for Unsupervised Pretraining
- Panchromatic and Multispectral Image Fusion via Alternating Reverse Filtering Network
- Para-CFlows: Ck-universal diffeomorphism approximators as superior neural surrogates
- Parallel Tempering With a Variational Reference
- Parameter-Efficient Masking Networks
- Parameter-free Dynamic Graph Embedding for Link Prediction
- Parameter-free Regret in High Probability with Heavy Tails
- Parameters or Privacy: A Provable Tradeoff Between Overparameterization and Membership Inference
- Parameter tuning and model selection in Optimal Transport with semi-dual Brenier formulation
- Parametrically Retargetable Decision-Makers Tend To Seek Power
- Paraphrasing Is All You Need for Novel Object Captioning
- Pareto Set Learning for Expensive Multi-Objective Optimization
- Partial Identification of Treatment Effects with Implicit Generative Models
- PatchComplete: Learning Multi-Resolution Patch Priors for 3D Shape Completion on Unseen Categories
- Patching open-vocabulary models by interpolating weights
- Path Independent Equilibrium Models Can Better Exploit Test-Time Computation
- Pay attention to your loss : understanding misconceptions about Lipschitz neural networks
- PDEBench: An Extensive Benchmark for Scientific Machine Learning
- PDSketch: Integrated Domain Programming, Learning, and Planning
- PEER: A Comprehensive and Multi-Task Benchmark for Protein Sequence Understanding
- Peer Prediction for Learning Agents
- Perceptual Attacks of No-Reference Image Quality Models with Human-in-the-Loop
- PeRFception: Perception using Radiance Fields
- PerfectDou: Dominating DouDizhu with Perfect Information Distillation
- Perfect Sampling from Pairwise Comparisons
- Performative Power
- Periodic Graph Transformers for Crystal Material Property Prediction
- Peripheral Vision Transformer
- Personalized Federated Learning towards Communication Efficiency, Robustness and Fairness
- Personalized Online Federated Learning with Multiple Kernels
- Perturbation Learning Based Anomaly Detection
- Pessimism for Offline Linear Contextual Bandits using ℓp Confidence Sets
- pFL-Bench: A Comprehensive Benchmark for Personalized Federated Learning
- Phase diagram of Stochastic Gradient Descent in high-dimensional two-layer neural networks
- Phase Transition from Clean Training to Adversarial Training
- Phase transitions in when feedback is useful
- Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding
- PhysGNN: A Physics--Driven Graph Neural Network Based Model for Predicting Soft Tissue Deformation in Image--Guided Neurosurgery
- Physically-Based Face Rendering for NIR-VIS Face Recognition
- Physics-Embedded Neural Networks: Graph Neural PDE Solvers with Mixed Boundary Conditions
- Physics-Informed Implicit Representations of Equilibrium Network Flows
- Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization?
- Pile of Law: Learning Responsible Data Filtering from the Law and a 256GB Open-Source Legal Dataset
- Pitfalls of Epistemic Uncertainty Quantification through Loss Minimisation
- PKD: General Distillation Framework for Object Detectors via Pearson Correlation Coefficient
- Planning for Sample Efficient Imitation Learning
- Planning to the Information Horizon of BAMDPs via Epistemic State Abstraction
- Plan To Predict: Learning an Uncertainty-Foreseeing Model For Model-Based Reinforcement Learning
- PlasticityNet: Learning to Simulate Metal, Sand, and Snow for Optimization Time Integration
- Pluralistic Image Completion with Gaussian Mixture Models
- Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training
- PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies
- PointTAD: Multi-Label Temporal Action Detection with Learnable Query Points
- Point Transformer V2: Grouped Vector Attention and Partition-based Pooling
- Poisson Flow Generative Models
- PolarMix: A General Data Augmentation Technique for LiDAR Point Clouds
- Policy Gradient With Serial Markov Chain Reasoning
- Policy Optimization for Markov Games: Unified Framework and Faster Convergence
- Policy Optimization with Advantage Regularization for Long-Term Fairness in Decision Systems
- Policy Optimization with Linear Temporal Logic Constraints
- Polyhistor: Parameter-Efficient Multi-Task Adaptation for Dense Vision Tasks
- Polynomial Neural Fields for Subband Decomposition and Manipulation
- Polynomial time guarantees for the Burer-Monteiro method
- Polynomial-Time Optimal Equilibria with a Mediator in Extensive-Form Games
- PopArt: Efficient Sparse Regression and Experimental Design for Optimal Sparse Linear Bandits
- Positively Weighted Kernel Quadrature via Subsampling
- Positive-Unlabeled Learning using Random Forests via Recursive Greedy Risk Minimization
- Posted Pricing and Dynamic Prior-independent Mechanisms with Value Maximizers
- Posterior and Computational Uncertainty in Gaussian Processes
- Posterior Collapse of a Linear Latent Variable Model
- Posterior Matching for Arbitrary Conditioning
- Posterior Refinement Improves Sample Efficiency in Bayesian Neural Networks
- Post-hoc estimators for learning to defer to an expert
- Power and limitations of single-qubit native quantum neural networks
- Practical Adversarial Attacks on Spatiotemporal Traffic Forecasting Models
- Practical Adversarial Multivalid Conformal Prediction
- Pragmatically Learning from Pedagogical Demonstrations in Multi-Goal Environments
- Pre-activation Distributions Expose Backdoor Neurons
- Precise Learning Curves and Higher-Order Scalings for Dot-product Kernel Regression
- Precise Regret Bounds for Log-loss via a Truncated Bayesian Algorithm
- Predicting Cellular Responses to Novel Drug Perturbations at a Single-Cell Resolution
- Predicting Label Distribution from Multi-label Ranking
- Predictive Coding beyond Gaussian Distributions
- Predictive Querying for Autoregressive Neural Sequence Models
- Preservation of the Global Knowledge by Not-True Distillation in Federated Learning
- Pre-trained Adversarial Perturbations
- Pre-Trained Image Encoder for Generalizable Visual Reinforcement Learning
- Pre-Trained Language Models for Interactive Decision-Making
- Pre-Trained Model Reusability Evaluation for Small-Data Transfer Learning
- Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors
- Privacy Induces Robustness: Information-Computation Gaps and Sparse Mean Estimation
- Privacy of Noisy Stochastic Gradient Descent: More Iterations without More Privacy Loss
- Private and Communication-Efficient Algorithms for Entropy Estimation
- Private Estimation with Public Data
- Private Graph All-Pairwise-Shortest-Path Distance Release with Improved Error Rate
- Private Isotonic Regression
- Private Multiparty Perception for Navigation
- Private Set Generation with Discriminative Information
- Private Synthetic Data for Multitask Learning and Marginal Queries
- Probabilistic Circuits: Representations, Inference, Learning and Applications
- Probabilistic Missing Value Imputation for Mixed Categorical and Ordered Data
- Probabilistic Transformer: Modelling Ambiguities and Distributions for RNA Folding and Molecule Design
- Probable Domain Generalization via Quantile Risk Minimization
- Probing Classifiers are Unreliable for Concept Removal and Detection
- Procedural Image Programs for Representation Learning
- 🏘️ ProcTHOR: Large-Scale Embodied AI Using Procedural Generation
- Product Ranking for Revenue Maximization with Multiple Purchases
- Progress and Challenges in Building Trustworthy Embodied AI
- projUNN: efficient method for training deep networks with unitary matrices
- Promising or Elusive? Unsupervised Object Segmentation from Real-world Single Images
- Prompt Certified Machine Unlearning with Randomized Gradient Smoothing and Quantization
- Proppo: a Message Passing Framework for Customizable and Composable Learning Algorithms
- PROSPECT: Labeled Tandem Mass Spectrometry Dataset for Machine Learning in Proteomics
- Prototypical VoteNet for Few-Shot 3D Point Cloud Object Detection
- ProtoVAE: A Trustworthy Self-Explainable Prototypical Variational Model
- ProtoX: Explaining a Reinforcement Learning Agent via Prototyping
- Provable Benefit of Multitask Representation Learning in Reinforcement Learning
- Provable Defense against Backdoor Policies in Reinforcement Learning
- Provable General Function Class Representation Learning in Multitask Bandits and MDP
- Provable Generalization of Overparameterized Meta-learning Trained with SGD
- Provable Subspace Identification Under Post-Nonlinear Mixtures
- Provably Adversarially Robust Detection of Out-of-Distribution Data (Almost) for Free
- Provably Efficient Model-Free Constrained RL with Linear Function Approximation
- Provably Efficient Offline Multi-agent Reinforcement Learning via Strategy-wise Bonus
- Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems
- Provably expressive temporal graph networks
- Provably Feedback-Efficient Reinforcement Learning via Active Reward Learning
- Provably sample-efficient RL with side information about latent dynamics
- Provably tuning the ElasticNet across instances
- Proximal Learning With Opponent-Learning Awareness
- Proximal Point Imitation Learning
- Prune and distill: similar reformatting of image information along rat visual cortex and deep neural networks
- Pruning has a disparate impact on model accuracy
- Pruning Neural Networks via Coresets and Convex Geometry: Towards No Assumptions
- Pruning’s Effect on Generalization Through the Lens of Training and Regularization
- Pseudo-Riemannian Graph Convolutional Networks
- Public Wisdom Matters! Discourse-Aware Hyperbolic Fourier Co-Attention for Social Text Classification
- PulseImpute: A Novel Benchmark Task for Pulsative Physiological Signal Imputation
- Pure Transformers are Powerful Graph Learners
- Pushing the limits of fairness impossibility: Who's the fairest of them all?
- pyKT: A Python Library to Benchmark Deep Learning based Knowledge Tracing Models
- Pyramid Attention For Source Code Summarization
- PyramidCLIP: Hierarchical Feature Alignment for Vision-language Model Pretraining
- Pythae: Unifying Generative Autoencoders in Python - A Benchmarking Use Case
- QC-StyleGAN - Quality Controllable Image Generation and Manipulation
- Quality Not Quantity: On the Interaction between Dataset Design and Robustness of CLIP
- Quantifying Statistical Significance of Neural Network-based Image Segmentation by Selective Inference
- Quantile Constrained Reinforcement Learning: A Reinforcement Learning Framework Constraining Outage Probability
- Quantized Training of Gradient Boosting Decision Trees
- Quantum Algorithms for Sampling Log-Concave Distributions and Estimating Normalizing Constants
- Quantum Speedups of Optimizing Approximately Convex Functions with Applications to Logarithmic Regret Stochastic Convex Bandits
- QUARK: Controllable Text Generation with Reinforced Unlearning
- Quasi-Newton Methods for Saddle Point Problems
- QueryPose: Sparse Multi-Person Pose Regression via Spatial-Aware Part-Level Query
- Queue Up Your Regrets: Achieving the Dynamic Capacity Region of Multiplayer Bandits
- Quo Vadis: Is Trajectory Forecasting the Key Towards Long-Term Multi-Object Tracking?
- Q-ViT: Accurate and Fully Quantized Low-bit Vision Transformer
- RainNet: A Large-Scale Imagery Dataset and Benchmark for Spatial Precipitation Downscaling
- RAMBO-RL: Robust Adversarial Model-Based Offline Reinforcement Learning
- Randomized Channel Shuffling: Minimal-Overhead Backdoor Attack Detection without Clean Datasets
- Randomized Message-Interception Smoothing: Gray-box Certificates for Graph Neural Networks
- Randomized Sketches for Clustering: Fast and Optimal Kernel k-Means
- Random Normalization Aggregation for Adversarial Defense
- Random Rank: The One and Only Strategyproof and Proportionally Fair Randomized Facility Location Mechanism
- Random Sharpness-Aware Minimization
- Rank Diminishing in Deep Neural Networks
- RankFeat: Rank-1 Feature Removal for Out-of-distribution Detection
- Rapidly Mixing Multiple-try Metropolis Algorithms for Model Selection Problems
- Rapid Model Architecture Adaption for Meta-Learning
- Rare Gems: Finding Lottery Tickets at Initialization
- Rashomon Capacity: A Metric for Predictive Multiplicity in Classification
- Rate-Distortion Theoretic Bounds on Generalization Error for Distributed Learning
- Rate-Optimal Online Convex Optimization in Adaptive Linear Control
- [Re] A Cluster-based Approach for Improving Isotropy in Contextual Embedding Space
- [Re] AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradients
- Real-Valued Backpropagation is Unsuitable for Complex-Valued Neural Networks
- Re-Analyze Gauss: Bounds for Private Matrix Approximation via Dyson Brownian Motion
- [Re] An Implementation of Fair Robust Learning
- [Re] Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentation
- Recall Distortion in Neural Network Pruning and the Undecayed Pruning Algorithm
- Receding Horizon Inverse Reinforcement Learning
- Recipe for a General, Powerful, Scalable Graph Transformer
- Recommender Forest for Efficient Retrieval
- Reconstructing Training Data From Trained Neural Networks
- Reconstruction on Trees and Low-Degree Polynomials
- ReCo: Retrieve and Co-segment for Zero-shot Transfer
- Recovering Private Text in Federated Learning of Language Models
- Recovery and Generalization in Over-Realized Dictionary Learning
- Recruitment Strategies That Take a Chance
- Recurrent Convolutional Neural Networks Learn Succinct Learning Algorithms
- Recurrent Memory Transformer
- Recurrent Video Restoration Transformer with Guided Deformable Attention
- RecursiveMix: Mixed Learning with History
- Recursive Reasoning in Minimax Games: A Level k Gradient Play Method
- Recursive Reinforcement Learning
- Redeeming intrinsic rewards via constrained optimization
- [Re] Differentiable Spatial Planning using Transformers
- Redistribution of Weights and Activations for AdderNet Quantization
- [Re] Does Self-Supervision Always Improve Few-Shot Learning?
- Reduced Representation of Deformation Fields for Effective Non-rigid Shape Matching
- Reduction Algorithms for Persistence Diagrams of Networks: CoralTDA and PrunIT
- Redundancy-Free Message Passing for Graph Neural Networks
- Redundant representations help generalization in wide neural networks
- [Re] Exacerbating Algorithmic Bias through Fairness Attacks
- [Re] Exacerbating Algorithmic Bias through Fairness Attacks
- [Re] Explaining in Style: Training a GAN to explain a classifier in StyleSpace
- [Re] Explaining in Style: Training a GAN to explain a classifier in StyleSpace
- ReFactor GNNs: Revisiting Factorisation-based Models from a Message-Passing Perspective
- Refining Low-Resource Unsupervised Translation by Language Disentanglement of Multilingual Translation Model
- [Re] GANSpace: Discovering Interpretable GAN Controls
- [Re] Graph Edit Networks
- Regret Bounds for Information-Directed Reinforcement Learning
- Regret Bounds for Multilabel Classification in Sparse Label Regimes
- Regret Bounds for Risk-Sensitive Reinforcement Learning
- Regularized Gradient Descent Ascent for Two-Player Zero-Sum Markov Games
- Regularized Molecular Conformation Fields
- Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress
- Reinforced Genetic Algorithm for Structure-based Drug Design
- Reinforcement Learning for Real Life (RL4RealLife) Workshop
- Reinforcement Learning in a Birth and Death Process: Breaking the Dependence on the State Space
- Reinforcement Learning with a Terminator
- Reinforcement Learning with Automated Auxiliary Loss Search
- Reinforcement Learning with Logarithmic Regret and Policy Switches
- Reinforcement Learning with Neural Radiance Fields
- Reinforcement Learning with Non-Exponential Discounting
- Relational Proxies: Emergent Relationships as Fine-Grained Discriminators
- Relational Reasoning via Set Transformers: Provable Efficiency and Applications to MARL
- Relation-Constrained Decoding for Text Generation
- Relaxing Equivariance Constraints with Non-stationary Continuous Filters
- [Re] Learning to count everything
- [Re] Learning Unknown from Correlations: Graph Neural Network for Inter-novel-protein Interaction Prediction
- [Re] Lifting 2D StyleGAN for 3D-Aware Face Generation
- Remember the Past: Distilling Datasets into Addressable Memories for Neural Networks
- [Re] Nondeterminism and Instability in Neural Network Optimization
- RényiCL: Contrastive Representation Learning with Skew Rényi Divergence
- Renyi Differential Privacy of Propose-Test-Release and Applications to Private and Robust Machine Learning
- Repairing Neural Networks by Leaving the Right Past Behind
- Representing Spatial Trajectories as Distributions
- [Re] Privacy-preserving collaborative learning with automatic transformation search
- Reproducibility in Optimization: Theoretical Framework and Limits
- [Re] Projection-based Algorithm for Updating the TruncatedSVD of Evolving Matrices
- [Re] Replication study of 'Data-Driven Methods for Balancing Fairness and Efficiency in Ride-Pooling'
- [Re] Replication Study of DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networks
- [Re] Replication Study of "Fairness and Bias in Online Selection"
- [Re] Replication Study of "Fairness and Bias in Online Selection"
- [Re] Reproducibility Report: Contrastive Learning of Socially-aware Motion Representations
- [Re] Reproducibility Study of “Counterfactual Generative Networks”
- [Re] Reproduction and Extension of "Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation"
- [Re] Reproduction Study of Variational Fair Clustering
- Residual Multiplicative Filter Networks for Multiscale Reconstruction
- [Re] Solving Phase Retrieval With a Learned Reference
- Resolving the data ambiguity for periodic crystals
- Resource-Adaptive Federated Learning with All-In-One Neural Composition
- Respecting Transfer Gap in Knowledge Distillation
- ResQ: A Residual Q Function-based Approach for Multi-Agent Reinforcement Learning Value Factorization
- [Re] Strategic classification made practical: reproduction
- ResT V2: Simpler, Faster and Stronger
- Retaining Knowledge for Learning with Dynamic Definition
- Rethinking Alignment in Video Super-Resolution Transformers
- Rethinking and Improving Robustness of Convolutional Neural Networks: a Shapley Value-based Approach in Frequency Domain
- Rethinking and Scaling Up Graph Contrastive Learning: An Extremely Efficient Approach with Group Discrimination
- Rethinking Generalization in Few-Shot Classification
- Rethinking Image Restoration for Object Detection
- Rethinking Individual Global Max in Cooperative Multi-Agent Reinforcement Learning
- Rethinking Knowledge Graph Evaluation Under the Open-World Assumption
- Rethinking Lipschitz Neural Networks and Certified Robustness: A Boolean Function Perspective
- Rethinking Nonlinear Instrumental Variable Models through Prediction Validity
- Rethinking Resolution in the Context of Efficient Video Recognition
- Rethinking the compositionality of point clouds through regularization in the hyperbolic space
- Rethinking the Reverse-engineering of Trojan Triggers
- Rethinking Value Function Learning for Generalization in Reinforcement Learning
- Rethinking Variational Inference for Probabilistic Programs with Stochastic Support
- [Re] Transparent Object Tracking Benchmark
- Retrieval-Augmented Diffusion Models
- Retrieve, Reason, and Refine: Generating Accurate and Faithful Patient Instructions
- Retrospective Adversarial Replay for Continual Learning
- [Re] Understanding Self-Supervised Learning Dynamics without Contrastive Pairs
- [Re] Value Alignment Verification
- Revisiting Active Sets for Gaussian Process Decoders
- Revisiting Graph Contrastive Learning from the Perspective of Graph Spectrum
- Revisiting Heterophily For Graph Neural Networks
- Revisiting Injective Attacks on Recommender Systems
- Revisiting Neural Scaling Laws in Language and Vision
- Revisiting Non-Parametric Matching Cost Volumes for Robust and Generalizable Stereo Matching
- Revisiting Optimal Convergence Rate for Smooth and Non-convex Stochastic Decentralized Optimization
- Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering
- Revisiting Sliced Wasserstein on Images: From Vectorization to Convolution
- Revisiting Sparse Convolutional Model for Visual Recognition
- Revisit last-iterate convergence of mSGD under milder requirement on step size
- REVIVE: Regional Visual Representation Matters in Knowledge-Based Visual Question Answering
- Riemannian Diffusion Models
- Riemannian Neural SDE: Learning Stochastic Representations on Manifolds
- Riemannian Score-Based Generative Modelling
- RISE: Robust Individualized Decision Learning with Sensitive Variables
- Risk Bounds of Multi-Pass SGD for Least Squares in the Interpolation Regime
- Risk-Driven Design of Perception Systems
- RKHS-SHAP: Shapley Values for Kernel Methods
- RLIP: Relational Language-Image Pre-training for Human-Object Interaction Detection
- RNNs of RNNs: Recursive Construction of Stable Assemblies of Recurrent Neural Networks
- Roadblocks for Temporarily Disabling Shortcuts and Learning New Knowledge
- Robust ϕ-Divergence MDPs
- Robust and scalable manifold learning via landmark diffusion for long-term medical signal processing
- Robust Anytime Learning of Markov Decision Processes
- Robust Bayesian Regression via Hard Thresholding
- Robust Binary Models by Pruning Randomly-initialized Networks
- Robust Calibration with Multi-domain Temperature Scaling
- Robust Feature-Level Adversaries are Interpretability Tools
- Robust Generalized Method of Moments: A Finite Sample Viewpoint
- Robust Graph Structure Learning via Multiple Statistical Tests
- Robust Imitation of a Few Demonstrations with a Backwards Model
- Robust Imitation via Mirror Descent Inverse Reinforcement Learning
- Robust Learning against Relational Adversaries
- Robust Models are less Over-Confident
- Robust Model Selection and Nearly-Proper Learning for GMMs
- Robustness Analysis of Video-Language Models Against Visual and Language Perturbations
- Robustness Disparities in Face Detection
- Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization)
- Robustness in Sequence Modeling
- Robustness to Label Noise Depends on the Shape of the Noise Distribution
- Robustness to Unbounded Smoothness of Generalized SignSGD
- Robust Neural Posterior Estimation and Statistical Model Criticism
- Robust On-Policy Sampling for Data-Efficient Policy Evaluation in Reinforcement Learning
- Robust Reinforcement Learning using Offline Data
- Robust Rent Division
- Robust Semi-Supervised Learning when Not All Classes have Labels
- Robust Streaming PCA
- Robust Testing in High-Dimensional Sparse Models
- Root Cause Analysis of Failures in Microservices through Causal Discovery
- RORL: Robust Offline Reinforcement Learning via Conservative Smoothing
- Rotation-Equivariant Conditional Spherical Neural Fields for Learning a Natural Illumination Prior
- RSA: Reducing Semantic Shift from Aggressive Augmentations for Self-supervised Learning
- RTFormer: Efficient Design for Real-Time Semantic Segmentation with Transformer
- S3-NeRF: Neural Reflectance Field from Shading and Shadow under a Single Viewpoint
- S2P: State-conditioned Image Synthesis for Data Augmentation in Offline Reinforcement Learning
- S3GC: Scalable Self-Supervised Graph Clustering
- S4ND: Modeling Images and Videos as Multidimensional Signals with State Spaces
- SafeBench: A Benchmarking Platform for Safety Evaluation of Autonomous Vehicles
- Safe Opponent-Exploitation Subgame Refinement
- Safety Guarantees for Neural Network Dynamic Systems via Stochastic Barrier Functions
- SAGDA: Achieving O(ϵ−2) Communication Complexity in Federated Min-Max Learning
- SageMix: Saliency-Guided Mixup for Point Clouds
- Saliency-Aware Neural Architecture Search
- SALSA: Attacking Lattice Cryptography with Transformers
- Sample Complexity of Learning Heuristic Functions for Greedy-Best-First and A* Search
- Sample Constrained Treatment Effect Estimation
- Sample Efficiency Matters: A Benchmark for Practical Molecular Optimization
- Sample-Efficient Learning of Correlated Equilibria in Extensive-Form Games
- Sample-Efficient Reinforcement Learning of Partially Observable Markov Games
- Sample-Then-Optimize Batch Neural Thompson Sampling
- Sampling from Log-Concave Distributions with Infinity-Distance Guarantees
- Sampling in Constrained Domains with Orthogonal-Space Variational Gradient Descent
- Sampling without Replacement Leads to Faster Rates in Finite-Sum Minimax Optimization
- Sampling with Riemannian Hamiltonian Monte Carlo in a Constrained Space
- SAMURAI: Shape And Material from Unconstrained Real-world Arbitrary Image collections
- SAPA: Similarity-Aware Point Affiliation for Feature Upsampling
- SAPD+: An Accelerated Stochastic Method for Nonconvex-Concave Minimax Problems
- SAPipe: Staleness-Aware Pipeline for Data Parallel DNN Training
- SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery
- SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos
- SAViT: Structure-Aware Vision Transformer Pruning via Collaborative Optimization
- Scalable and Efficient Non-adaptive Deterministic Group Testing
- Scalable and Efficient Training of Large Convolutional Neural Networks with Differential Privacy
- Scalable design of Error-Correcting Output Codes using Discrete Optimization with Graph Coloring
- Scalable Distributional Robustness in a Class of Non-Convex Optimization with Guarantees
- Scalable Infomin Learning
- Scalable Interpretability via Polynomials
- Scalable Multi-agent Covering Option Discovery based on Kronecker Graphs
- Scalable Neural Video Representations with Learnable Positional Features
- Scalable Representation Learning in Linear Contextual Bandits with Constant Regret Guarantees
- Scalable Sensitivity and Uncertainty Analyses for Causal-Effect Estimates of Continuous-Valued Interventions
- Scale-invariant Learning by Physics Inversion
- Scaling Multimodal Pre-Training via Cross-Modality Gradient Harmonization
- Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning
- SCAMPS: Synthetics for Camera Measurement of Physiological Signals
- SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction
- SCL-WC: Cross-Slide Contrastive Learning for Weakly-Supervised Whole-Slide Image Classification
- SCONE: Surface Coverage Optimization in Unknown Environments by Volumetric Integration
- Score-Based Diffusion meets Annealed Importance Sampling
- Score-based Generative Modeling Secretly Minimizes the Wasserstein Distance
- Score-Based Generative Models Detect Manifolds
- Searching for Better Spatio-temporal Alignment in Few-Shot Action Recognition
- Second Thoughts are Best: Learning to Re-Align With Human Values from Text Edits
- Second Workshop on Efficient Natural Language and Speech Processing (ENLSP-II)
- SecureFedYJ: a safe feature Gaussianization protocol for Federated Learning
- Seeing the forest and the tree: Building representations of both individual and collective dynamics with transformers
- Segmenting Moving Objects via an Object-Centric Layered Representation
- SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation
- SegViT: Semantic Segmentation with Plain Vision Transformers
- SelecMix: Debiased Learning by Contradicting-pair Sampling
- Selective compression learning of latent representations for variable-rate image compression
- Self-Aware Personalized Federated Learning
- Self-Consistent Dynamical Field Theory of Kernel Evolution in Wide Neural Networks
- Self-explaining deep models with logic rule reasoning
- Self-Explaining Deviations for Coordination
- Self-Organized Group for Cooperative Multi-agent Reinforcement Learning
- Self-Similarity Priors: Neural Collages as Differentiable Fractal Representations
- Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition
- Self-supervised Amodal Video Object Segmentation
- Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency
- Self-Supervised Fair Representation Learning without Demographics
- Self-supervised Heterogeneous Graph Pre-training Based on Structural Clustering
- Self-Supervised Image Restoration with Blurry and Noisy Pairs
- Self-Supervised Learning of Brain Dynamics from Broad Neuroimaging Data
- Self-Supervised Learning: Theory and Practice
- Self-Supervised Learning Through Efference Copies
- Self-Supervised Learning via Maximum Entropy Coding
- Self-Supervised Learning with an Information Maximization Criterion
- Self-Supervised Pretraining for Large-Scale Point Clouds
- Self-supervised surround-view depth estimation with volumetric feature fusion
- Self-Supervised Visual Representation Learning with Semantic Grouping
- Semantic Diffusion Network for Semantic Segmentation
- Semantic Exploration from Language Abstractions and Pretrained Representations
- Semantic Probabilistic Layers for Neuro-Symbolic Learning
- Semantic uncertainty intervals for disentangled latent spaces
- Semi-Discrete Normalizing Flows through Differentiable Tessellation
- SemiFL: Semi-Supervised Federated Learning for Unlabeled Clients with Alternate Training
- Semi-infinitely Constrained Markov Decision Processes
- Semi-supervised Active Linear Regression
- Semi-Supervised Generative Models for Multiagent Trajectories
- Semi-Supervised Learning with Decision Trees: Graph Laplacian Tree Alternating Optimization
- Semi-Supervised Semantic Segmentation via Gentle Teaching Assistant
- Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularization
- Semi-Supervised Video Salient Object Detection Based on Uncertainty-Guided Pseudo Labels
- Semi-supervised Vision Transformers at Scale
- SemMAE: Semantic-Guided Masking for Learning Masked Autoencoders
- SeqPATE: Differentially Private Text Generation via Knowledge Distillation
- Sequence Model Imitation Learning with Unobserved Contexts
- Sequencer: Deep LSTM for Image Classification
- Sequence-to-Set Generative Models
- Sequential Information Design: Learning to Persuade in the Dark
- Set-based Meta-Interpolation for Few-Task Meta-Learning
- SGAM: Building a Virtual 3D World through Simultaneous Generation and Mapping
- Shadow Knowledge Distillation: Bridging Offline and Online Knowledge Transfer
- Shape And Structure Preserving Differential Privacy
- ShapeCrafter: A Recursive Text-Conditioned 3D Shape Generation Model
- Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and Denoising
- SHAQ: Incorporating Shapley Value Theory into Multi-Agent Q-Learning
- Shared Visual Representations in Human and Machine Intelligence (SVRHM)
- Sharing Knowledge for Meta-learning with Feature Descriptions
- Sharp Analysis of Stochastic Optimization under Global Kurdyka-Lojasiewicz Inequality
- Sharper Convergence Guarantees for Asynchronous SGD for Distributed and Federated Learning
- Sharpness-Aware Training for Free
- Shield Decentralization for Safe Multi-Agent Reinforcement Learning
- SHINE: SubHypergraph Inductive Neural nEtwork
- ShuffleMixer: An Efficient ConvNet for Image Super-Resolution
- Signal Processing for Implicit Neural Representations
- Signal Propagation in Transformers: Theoretical Perspectives and the Role of Rank Collapse
- Signal Recovery with Non-Expansive Generative Network Priors
- SignRFF: Sign Random Fourier Features
- Simple and Optimal Greedy Online Contention Resolution Schemes
- Simple Mechanisms for Welfare Maximization in Rich Advertising Auctions
- Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videos
- Simplified Graph Convolution with Heterophily
- Simulation-guided Beam Search for Neural Combinatorial Optimization
- Simultaneous Missing Value Imputation and Structure Learning with Groups
- SInGE: Sparsity via Integrated Gradients Estimation of Neuron Relevance
- Single Loop Gaussian Homotopy Method for Non-convex Optimization
- Single Model Uncertainty Estimation via Stochastic Data Centering
- Single-pass Streaming Lower Bounds for Multi-armed Bandits Exploration with Instance-sensitive Sample Complexity
- Single-phase deep learning in cortico-cortical networks
- Single-Stage Visual Relationship Learning using Conditional Queries
- Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning
- SIREN: Shaping Representations for Detecting Out-of-Distribution Objects
- SIXO: Smoothing Inference with Twisted Objectives
- Size and depth of monotone neural networks: interpolation and approximation
- SizeShiftReg: a Regularization Method for Improving Size-Generalization in Graph Neural Networks
- SketchBoost: Fast Gradient Boosted Decision Tree for Multioutput Problems
- Sketch-GNN: Scalable Graph Neural Networks with Sublinear Training Complexity
- Sketching based Representations for Robust Image Classification with Provable Guarantees
- SKFlow: Learning Optical Flow with Super Kernels
- Skills Regularized Task Decomposition for Multi-task Offline Reinforcement Learning
- SkinCon: A skin disease dataset densely annotated by domain experts for fine-grained debugging and analysis
- Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch
- Smoothed Embeddings for Certified Few-Shot Learning
- Smoothed Online Convex Optimization Based on Discounted-Normal-Predictor
- Smooth Fictitious Play in Stochastic Games with Perturbed Payoffs and Unknown Transitions
- SMPL: Simulated Industrial Manufacturing and Process Control Learning Environments
- SnAKe: Bayesian Optimization with Pathwise Exploration
- SNAKE: Shape-aware Neural 3D Keypoint Field
- SNN-RAT: Robustness-enhanced Spiking Neural Network through Regularized Adversarial Training
- So3krates: Equivariant attention for interactions on arbitrary length-scales in molecular systems
- Sobolev Acceleration and Statistical Optimality for Learning Elliptic Equations via Gradient Descent
- Social-Inverse: Inverse Decision-making of Social Contagion Management with Task Migrations
- Society of Agents: Regret Bounds of Concurrent Thompson Sampling
- SoftPatch: Unsupervised Anomaly Detection with Noisy Data
- SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learning
- Solving Quantitative Reasoning Problems with Language Models
- SoteriaFL: A Unified Framework for Private Federated Learning with Communication Compression
- Sound and Complete Causal Identification with Latent Variables Given Local Background Knowledge
- Sound and Complete Verification of Polynomial Networks
- SoundSpaces 2.0: A Simulation Platform for Visual-Acoustic Learning
- SparCL: Sparse Continual Learning on the Edge
- Sparse2Dense: Learning to Densify 3D Features for 3D Object Detection
- Sparse Additive Gaussian Process Regression
- Sparse Fourier Backpropagation in Cryo-EM Reconstruction
- Sparse Gaussian Process Hyperparameters: Optimize or Integrate?
- Sparse Hypergraph Community Detection Thresholds in Stochastic Block Model
- Sparse Interaction Additive Networks via Feature Interaction Detection and Sparse Selection
- Sparse Probabilistic Circuits via Pruning and Growing
- Sparse Structure Search for Delta Tuning
- Sparse Winning Tickets are Data-Efficient Image Recognizers
- Sparsity in Continuous-Depth Neural Networks
- Spartan: Differentiable Sparsity via Regularized Transportation
- Spatial Mixture-of-Experts
- Spatial Pruned Sparse Convolution for Efficient 3D Object Detection
- SPD domain-specific batch normalization to crack interpretable unsupervised domain adaptation in EEG
- SPD: Synergy Pattern Diversifying Oriented Unsupervised Multi-agent Reinforcement Learning
- Spectral Bias in Practice: The Role of Function Frequency in Generalization
- Spectral Bias Outside the Training Set for Deep Networks in the Kernel Regime
- Spectrum Random Masking for Generalization in Image-based Reinforcement Learning
- Spending Thinking Time Wisely: Accelerating MCTS with Virtual Expansions
- Spherical Channels for Modeling Atomic Interactions
- Spherization Layer: Representation Using Only Angles
- S-PIFu: Integrating Parametric Human Models with PIFu for Single-view Clothed Human Reconstruction
- Split-kl and PAC-Bayes-split-kl Inequalities for Ternary Random Variables
- SPoVT: Semantic-Prototype Variational Transformer for Dense Point Cloud Semantic Completion
- S-Prompts Learning with Pre-trained Transformers: An Occam’s Razor for Domain Incremental Learning
- SQ Lower Bounds for Learning Single Neurons with Massart Noise
- Squeezeformer: An Efficient Transformer for Automatic Speech Recognition
- Stability Analysis and Generalization Bounds of Adversarial Training
- Stability and Generalization Analysis of Gradient Methods for Shallow Neural Networks
- Stability and Generalization for Markov Chain Stochastic Gradient Methods
- Stability and Generalization of Kernel Clustering: from Single Kernel to Multiple Kernel
- ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning
- Staggered Rollout Designs Enable Causal Inference Under Interference Without Network Knowledge
- Staircase Attention for Recurrent Processing of Sequences
- STaR: Bootstrapping Reasoning With Reasoning
- Stars: Tera-Scale Graph Building for Clustering and Learning
- Star Temporal Classification: Sequence Modeling with Partially Labeled Data
- Statistical Learning and Inverse Problems: A Stochastic Gradient Approach
- Statistically Meaningful Approximation: a Case Study on Approximating Turing Machines with Transformers
- Statistical, Robustness, and Computational Guarantees for Sliced Wasserstein Distances
- Stimulative Training of Residual Networks: A Social Psychology Perspective of Loafing
- STNDT: Modeling Neural Population Activity with Spatiotemporal Transformers
- Stochastic Adaptive Activation Function
- Stochastic Halpern Iteration with Variance Reduction for Stochastic Monotone Inclusions
- Stochastic Multiple Target Sampling Gradient Descent
- Stochastic Online Learning with Feedback Graphs: Finite-Time and Asymptotic Optimality
- Stochastic Second-Order Methods Improve Best-Known Sample Complexity of SGD for Gradient-Dominated Functions
- Stochastic Window Transformer for Image Restoration
- Streaming Radiance Fields for 3D Video Synthesis
- StrokeRehab: A Benchmark Dataset for Sub-second Action Identification
- Structural Analysis of Branch-and-Cut and the Learnability of Gomory Mixed Integer Cuts
- Structural Kernel Search via Bayesian Optimization and Symbolical Optimal Transport
- Structural Knowledge Distillation for Object Detection
- Structural Pruning via Latency-Saliency Knapsack
- Structure-Aware Image Segmentation with Homotopy Warping
- Structured Energy Network As a Loss
- Structured Recognition for Generative Models with Explaining Away
- Structure-Preserving 3D Garment Modeling with Neural Sewing Machines
- Structuring Representations Using Group Invariants
- Structuring Uncertainty for Fine-Grained Sampling in Stochastic Segmentation Networks
- Sub-exponential time Sum-of-Squares lower bounds for Principal Components Analysis
- Subgame Solving in Adversarial Team Games
- Subgroup Robustness Grows On Trees: An Empirical Baseline Investigation
- Sublinear Algorithms for Hierarchical Clustering
- Submodular Maximization in Clean Linear Time
- Subquadratic Kronecker Regression with Applications to Tensor Decomposition
- Subsidiary Prototype Alignment for Universal Domain Adaptation
- Subspace clustering in high-dimensions: Phase transitions & Statistical-to-Computational gap
- Subspace Recovery from Heterogeneous Data with Non-isotropic Noise
- Sufficient reductions in regression with mixed predictors
- Supervised Dimensionality Reduction and Visualization using Centroid-Encoder
- Supervised Training of Conditional Monge Maps
- Supervising the Multi-Fidelity Race of Hyperparameter Configurations
- Supported Policy Optimization for Offline Reinforcement Learning
- Support Recovery in Sparse PCA with Incomplete Data
- SurDis: A Surface Discontinuity Dataset for Wearable Technology to Assist Blind Navigation in Urban Environments
- Surprise Minimizing Multi-Agent Learning with Energy-based Models
- Surprising Instabilities in Training Deep Networks and a Theoretical Analysis
- Sustainable Online Reinforcement Learning for Auto-bidding
- SwinTrack: A Simple and Strong Baseline for Transformer Tracking
- Symbolic Distillation for Learned TCP Congestion Control
- Symmetry and Geometry in Neural Representations (NeurReps)
- Symmetry-induced Disentanglement on Graphs
- Symmetry Teleportation for Accelerated Optimization
- Sym-NCO: Leveraging Symmetricity for Neural Combinatorial Optimization
- Symplectic Spectrum Gaussian Processes: Learning Hamiltonians from Noisy and Sparse Data
- Syndicated Bandits: A Framework for Auto Tuning Hyper-parameters in Contextual Bandit Algorithms
- Synergy-of-Experts: Collaborate to Improve Adversarial Robustness
- Synthetic Data for Empowering ML Research
- Synthetic Model Combination: An Instance-wise Approach to Unsupervised Ensemble Learning
- Systematic improvement of neural network quantum states using Lanczos
- Table Representation Learning
- TabNAS: Rejection Sampling for Neural Architecture Search on Tabular Datasets
- Tackling Climate Change with Machine Learning
- TA-GATES: An Encoding Scheme for Neural Network Architectures
- TaiSu: A 166M Large-scale High-Quality Dataset for Chinese Vision-Language Pre-training
- Taming Fat-Tailed (“Heavier-Tailed” with Potentially Infinite Variance) Noise in Federated Learning
- TA-MoE: Topology-Aware Large Scale Mixture-of-Expert Training
- TANGO: Text-driven Photorealistic and Robust 3D Stylization via Lighting Decomposition
- TANKBind: Trigonometry-Aware Neural NetworKs for Drug-Protein Binding Structure Prediction
- TAP-Vid: A Benchmark for Tracking Any Point in a Video
- Target alignment in truncated kernel ridge regression
- TarGF: Learning Target Gradient Field to Rearrange Objects without Explicit Goal Specification
- TaSIL: Taylor Series Imitation Learning
- Task-Agnostic Graph Explanations
- Task Discovery: Finding the Tasks that Neural Networks Generalize on
- Task-Free Continual Learning via Online Discrepancy Distance Learning
- Task-level Differentially Private Meta Learning
- TCT: Convexifying Federated Learning using Bootstrapped Neural Tangent Kernels
- Teacher Forcing Recovers Reward Functions for Text Generation
- Teach Less, Learn More: On the Undistillable Classes in Knowledge Distillation
- TempEL: Linking Dynamically Evolving and Newly Emerging Entities
- Template based Graph Neural Network with Optimal Transport Distances
- Tempo: Accelerating Transformer-Based Model Training through Memory Footprint Reduction
- Temporal Effective Batch Normalization in Spiking Neural Networks
- Temporal Graph Learning Workshop
- Temporal Latent Bottleneck: Synthesis of Fast and Slow Processing Mechanisms in Sequence Learning
- Temporally-Consistent Survival Analysis
- Temporally Disentangled Representation Learning
- Tenrec: A Large-scale Multipurpose Benchmark Dataset for Recommender Systems
- Tensor Program Optimization with Probabilistic Programs
- Tensor Wheel Decomposition and Its Tensor Completion Application
- Test Time Adaptation via Conjugate Pseudo-labels
- Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models
- Test-Time Training with Masked Autoencoders
- Text-Adaptive Multiple Visual Prototype Matching for Video-Text Retrieval
- Text Classification with Born's Rule
- TGEA 2.0: A Large-Scale Diagnostically Annotated Dataset with Benchmark Tasks for Text Generation of Pretrained Language Models
- The alignment property of SGD noise and how it helps select flat minima: A stability analysis
- The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset
- The Burer-Monteiro SDP method can fail even above the Barvinok-Pataki bound
- The computational and learning benefits of Daleian neural networks
- The Curse of Unrolling: Rate of Differentiating Through Optimization
- The Data-Centric Era: How ML is Becoming an Experimental Science
- The Dollar Street Dataset: Images Representing the Geographic and Socioeconomic Diversity of the World
- The Effects of Regularization and Data Augmentation are Class Dependent
- The First Optimal Acceleration of High-Order Methods in Smooth Convex Optimization
- The First Optimal Algorithm for Smooth and Strongly-Convex-Strongly-Concave Minimax Optimization
- The Forward-Forward Algorithm for Training Deep Neural Networks
- The Fourth Workshop on AI for Humanitarian Assistance and Disaster Response
- The Franz-Parisi Criterion and Computational Trade-offs in High Dimensional Statistics
- The Gyro-Structure of Some Matrix Manifolds
- The Hessian Screening Rule
- The Impact of Task Underspecification in Evaluating Deep Reinforcement Learning
- The Implicit Delta Method
- The Importance of Being Correlated: Implications of Dependence in Joint Spectral Inference across Multiple Networks
- The least-control principle for local learning at equilibrium
- The Mechanism of Prediction Head in Non-contrastive Self-supervised Learning
- The Minority Matters: A Diversity-Promoting Collaborative Metric Learning Algorithm
- The Missing Invariance Principle found -- the Reciprocal Twin of Invariant Risk Minimization
- The Nature of Temporal Difference Errors in Multi-step Distributional Reinforcement Learning
- The Neural Covariance SDE: Shaped Infinite Depth-and-Width Networks at Initialization
- The Neural Testbed: Evaluating Joint Predictions
- Theoretical analysis of deep neural networks for temporally dependent observations
- Theoretically Better and Numerically Faster Distributed Optimization with Smoothness-Aware Quantization Techniques
- Theoretically Provable Spiking Neural Networks
- Theory and Approximate Solvers for Branched Optimal Transport with Multiple Sources
- Theory and Practice of Efficient and Accurate Dataset Construction
- The Phenomenon of Policy Churn
- The Pitfalls of Regularization in Off-Policy TD Learning
- The Policy-gradient Placement and Generative Routing Neural Networks for Chip Design
- The Power and Limitation of Pretraining-Finetuning for Linear Regression under Covariate Shift
- The price of ignorance: how much does it cost to forget noise structure in low-rank matrix estimation?
- The price of unfairness in linear bandits with biased feedback
- The Privacy Onion Effect: Memorization is Relative
- The Query Complexity of Cake Cutting
- The Role of Baselines in Policy Gradient Optimization
- The Role of Meta-learning for Few-shot Learning
- The Sample Complexity of One-Hidden-Layer Neural Networks
- Theseus: A Library for Differentiable Nonlinear Optimization
- The Stability-Efficiency Dilemma: Investigating Sequence Length Warmup for Training GPT Models
- The Surprising Effectiveness of PPO in Cooperative Multi-Agent Games
- The Symbiosis of Deep Learning and Differential Equations II
- The trade-offs of model size in large recommendation models : 100GB to 10MB Criteo-tb DLRM model
- The Unreasonable Effectiveness of Fully-Connected Layers for Low-Data Regimes
- The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning
- Thinking Outside the Ball: Optimal Learning with Gradient Descent for Generalized Linear Stochastic Convex Optimization
- Thinned random measures for sparse graphs with overlapping communities
- This is the way: designing and compiling LEPISZCZE, a comprehensive NLP benchmark for Polish
- Thompson Sampling Efficiently Learns to Control Diffusion Processes
- Thor: Wielding Hammers to Integrate Language Models and Automated Theorem Provers
- Tiered Reinforcement Learning: Pessimism in the Face of Uncertainty and Constant Regret
- Tight Analysis of Extra-gradient and Optimistic Gradient Methods For Nonconvex Minimax Problems
- Tight Lower Bounds on Worst-Case Guarantees for Zero-Shot Learning with Attributes
- Tight Mutual Information Estimation With Contrastive Fenchel-Legendre Optimization
- Tikhonov Regularization is Optimal Transport Robust under Martingale Constraints
- Time-Conditioned Dances with Simplicial Complexes: Zigzag Filtration Curve based Supra-Hodge Convolution Networks for Time-series Forecasting
- tntorch: Tensor Network Learning with PyTorch
- ToDD: Topological Compound Fingerprinting in Computer-Aided Drug Discovery
- TOIST: Task Oriented Instance Segmentation Transformer with Noun-Pronoun Distillation
- TokenMixup: Efficient Attention-guided Token-level Data Augmentation for Transformers
- Top Two Algorithms Revisited
- Torsional Diffusion for Molecular Conformer Generation
- TotalSelfScan: Learning Full-body Avatars from Self-Portrait Videos of Faces, Hands, and Bodies
- Touch and Go: Learning from Human-Collected Vision and Touch
- To update or not to update? Neurons at equilibrium in deep models
- Toward a realistic model of speech processing in the brain with self-supervised learning
- Toward Efficient Robust Training against Union of ℓp Threat Models
- Toward Equation of Motion for Deep Neural Networks: Continuous-time Gradient Descent and Discretization Error Analysis
- Toward Robust Spiking Neural Network Against Adversarial Perturbation
- Towards a Standardised Performance Evaluation Protocol for Cooperative MARL
- Towards a Unified Framework for Uncertainty-aware Nonlinear Variable Selection with Theoretical Guarantees
- Towards Better Evaluation for Dynamic Link Prediction
- Towards Consistency in Adversarial Classification
- Towards Disentangling Information Paths with Coded ResNeXt
- Towards Diverse and Faithful One-shot Adaption of Generative Adversarial Networks
- Towards Effective Multi-Modal Interchanges in Zero-Resource Sounding Object Localization
- Towards Efficient 3D Object Detection with Knowledge Distillation
- Towards Efficient Post-training Quantization of Pre-trained Language Models
- Towards Hard-pose Virtual Try-on via 3D-aware Global Correspondence Learning
- Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learning
- Towards Improving Calibration in Object Detection Under Domain Shift
- Towards Improving Faithfulness in Abstractive Summarization
- Towards Learning Universal Hyperparameter Optimizers with Transformers
- Towards Lightweight Black-Box Attack Against Deep Neural Networks
- Towards Optimal Communication Complexity in Distributed Non-Convex Optimization
- Towards Out-of-Distribution Sequential Event Prediction: A Causal Treatment
- Towards Practical Control of Singular Values of Convolutional Layers
- Towards Practical Few-shot Query Sets: Transductive Minimum Description Length Inference
- Towards Reasonable Budget Allocation in Untargeted Graph Structure Attacks via Gradient Debias
- Towards Reliable Simulation-Based Inference with Balanced Neural Ratio Estimation
- Towards Robust Blind Face Restoration with Codebook Lookup Transformer
- Towards Safe Reinforcement Learning with a Safety Editor Policy
- Towards Theoretically Inspired Neural Initialization Optimization
- Towards Trustworthy Automatic Diagnosis Systems by Emulating Doctors' Reasoning with Deep Reinforcement Learning
- Towards Understanding Grokking: An Effective Theory of Representation Learning
- Towards Understanding the Condensation of Neural Networks at Initial Training
- Towards Understanding the Mixture-of-Experts Layer in Deep Learning
- Towards Versatile Embodied Navigation
- Towards Video Text Visual Question Answering: Benchmark and Baseline
- Toward Understanding Privileged Features Distillation in Learning-to-Rank
- TPU-KNN: K Nearest Neighbor Search at Peak FLOP/s
- Tracking Functional Changes in Nonstationary Signals with Evolutionary Ensemble Bayesian Model for Robust Neural Decoding
- Tractable Function-Space Variational Inference in Bayesian Neural Networks
- Tractable Optimality in Episodic Latent MABs
- Trade-off between Payoff and Model Rewards in Shapley-Fair Collaborative Machine Learning
- Trading off Image Quality for Robustness is not Necessary with Regularized Deterministic Autoencoders
- Trading Off Resource Budgets For Improved Regret Bounds
- Trading off Utility, Informativeness, and Complexity in Emergent Communication
- Training and Inference on Any-Order Autoregressive Models the Right Way
- Training language models to follow instructions with human feedback
- Training Scale-Invariant Neural Networks on the Sphere Can Happen in Three Regimes
- Training Spiking Neural Networks with Event-driven Backpropagation
- Training Spiking Neural Networks with Local Tandem Learning
- Training stochastic stabilized supralinear networks by dynamics-neutral growth
- Training Subset Selection for Weak Supervision
- Training Uncertainty-Aware Classifiers with Conformalized Deep Learning
- Training with More Confidence: Mitigating Injected and Natural Backdoors During Training
- Trajectory balance: Improved credit assignment in GFlowNets
- Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline
- Trajectory Inference via Mean-field Langevin in Path Space
- Trajectory of Mini-Batch Momentum: Batch Size Saturation and Convergence in High Dimensions
- TransBoost: Improving the Best ImageNet Performance using Deep Transduction
- Transcormer: Transformer for Sentence Scoring with Sliding Language Modeling
- Transfer Learning for Natural Language Processing
- Transfer Learning in Information Criteria-based Feature Selection
- Transfer Learning on Heterogeneous Feature Spaces for Treatment Effects Estimation
- Transferring Fairness under Distribution Shifts via Fair Consistency Regularization
- Transferring Pre-trained Multimodal Representations with Cross-modal Similarity Matching
- Transformer-based Working Memory for Multiagent Reinforcement Learning with Action Parsing
- Transformer Memory as a Differentiable Search Index
- Transformers from an Optimization Perspective
- Transformers meet Stochastic Block Models: Attention with Data-Adaptive Sparsity and Cost
- Transform Once: Efficient Operator Learning in Frequency Domain
- Transition to Linearity of General Neural Networks with Directed Acyclic Graph Architecture
- Translation-equivariant Representation in Recurrent Networks with a Continuous Manifold of Attractors
- TransTab: Learning Transferable Tabular Transformers Across Tables
- Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork
- TREC: Transient Redundancy Elimination-based Convolution
- Tree ensemble kernels for Bayesian optimization with known constraints over mixed-feature spaces
- TreeMoCo: Contrastive Neuron Morphology Representation Learning
- Tree Mover's Distance: Bridging Graph Metrics and Stability of Graph Neural Networks
- Triangulation candidates for Bayesian optimization
- Trimmed Maximum Likelihood Estimation for Robust Generalized Linear Model
- Truly Deterministic Policy Optimization
- Truncated Emphatic Temporal Difference Methods for Prediction and Control
- Truncated Matrix Power Iteration for Differentiable DAG Learning
- Truncated proposals for scalable and hassle-free simulation-based inference
- Trust Region Policy Optimization with Optimal Transport Discrepancies: Duality and Algorithm for Continuous Actions
- Trustworthy and Socially Responsible Machine Learning
- Trustworthy Monte Carlo
- Tsetlin Machine for Solving Contextual Bandit Problems
- TTOpt: A Maximum Volume Quantized Tensor Train-based Optimization and its Application to Reinforcement Learning
- Turbocharging Solution Concepts: Solving NEs, CEs and CCEs with Neural Equilibrium Solvers
- Turning the Tables: Biased, Imbalanced, Dynamic Tabular Datasets for ML Evaluation
- TUSK: Task-Agnostic Unsupervised Keypoints
- TVLT: Textless Vision-Language Transformer
- TweetNERD - End to End Entity Linking Benchmark for Tweets
- TwiBot-22: Towards Graph-Based Twitter Bot Detection
- Two-layer neural network on infinite dimensional data: global optimization guarantee in the mean-field regime
- Two-Stream Network for Sign Language Recognition and Translation
- UDC: Unified DNAS for Compressible TinyML Models for Neural Processing Units
- u-HuBERT: Unified Mixed-Modal Speech Pretraining And Zero-Shot Transfer to Unlabeled Modality
- ULNeF: Untangled Layered Neural Fields for Mix-and-Match Virtual Try-On
- UMIX: Improving Importance Weighting for Subpopulation Shift via Uncertainty-Aware Mixup
- Uncalibrated Models Can Improve Human-AI Collaboration
- Uncertainty-Aware Hierarchical Refinement for Incremental Implicitly-Refined Classification
- Uncertainty-Aware Reinforcement Learning for Risk-Sensitive Player Evaluation in Sports Game
- Uncertainty Estimation for Multi-view Data: The Power of Seeing the Whole Picture
- Uncertainty Estimation Using Riemannian Model Dynamics for Offline Reinforcement Learning
- Uncoupled Learning Dynamics with O(logT) Swap Regret in Multiplayer Games
- Uncovering the Structural Fairness in Graph Contrastive Learning
- Understanding Aesthetics with Language: A Photo Critique Dataset for Aesthetic Assessment
- Understanding and Extending Subgraph GNNs by Rethinking Their Symmetries
- Understanding and Improving Robustness of Vision Transformers through Patch-based Negative Augmentation
- Understanding Benign Overfitting in Gradient-Based Meta Learning
- Understanding Cross-Domain Few-Shot Learning Based on Domain Similarity and Few-Shot Difficulty
- Understanding Deep Contrastive Learning via Coordinate-wise Optimization
- Understanding Deep Neural Function Approximation in Reinforcement Learning via ϵ-Greedy Exploration
- Understanding Hyperdimensional Computing for Parallel Single-Pass Learning
- Understanding Non-linearity in Graph Neural Networks from the Bayesian-Inference Perspective
- Understanding Programmatic Weak Supervision via Source-aware Influence Function
- Understanding Robust Learning through the Lens of Representation Similarities
- Understanding Square Loss in Training Overparametrized Neural Network Classifiers
- Understanding the Eluder Dimension
- Understanding the Evolution of Linear Regions in Deep Reinforcement Learning
- Understanding the Failure of Batch Normalization for Transformers in NLP
- Understanding the Generalization Benefit of Normalization Layers: Sharpness Reduction
- UnfoldML: Cost-Aware and Uncertainty-Based Dynamic 2D Prediction for Multi-Stage Classification
- UniCLIP: Unified Framework for Contrastive Language-Image Pre-training
- Unified Optimal Transport Framework for Universal Domain Adaptation
- Unifying and Boosting Gradient-Based Training-Free Neural Architecture Search
- Unifying Voxel-based Representation with Transformer for 3D Object Detection
- UniGAN: Reducing Mode Collapse in GANs using a Uniform Generator
- Uni[MASK]: Unified Inference in Sequential Decision Problems
- Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional MoEs
- Universality of Group Convolutional Neural Networks Based on Ridgelet Analysis on Groups
- Universally Expressive Communication in Multi-Agent Reinforcement Learning
- Universal Rates for Interactive Learning
- Unknown-Aware Domain Adversarial Learning for Open-Set Domain Adaptation
- Unlabelled Sample Compression Schemes for Intersection-Closed Classes and Extremal Classes
- Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity
- Unravelling the Performance of Physics-informed Graph Neural Networks for Dynamical Systems
- Unsupervised Adaptation from Repeated Traversals for Autonomous Driving
- Unsupervised Causal Generative Understanding of Images
- Unsupervised Cross-Task Generalization via Retrieval Augmentation
- Unsupervised Domain Adaptation for Semantic Segmentation using Depth Distribution
- Unsupervised Image-to-Image Translation with Density Changing Regularization
- Unsupervised Learning for Combinatorial Optimization with Principled Objective Relaxation
- Unsupervised Learning From Incomplete Measurements for Inverse Problems
- Unsupervised Learning of Equivariant Structure from Sequences
- Unsupervised Learning of Group Invariant and Equivariant Representations
- Unsupervised Learning of Shape Programs with Repeatable Implicit Parts
- Unsupervised Learning under Latent Label Shift
- Unsupervised Multi-Object Segmentation by Predicting Probable Motion Patterns
- Unsupervised Multi-View Object Segmentation Using Radiance Field Propagation
- Unsupervised Object Detection Pretraining with Joint Object Priors Generation and Detector Learning
- Unsupervised Object Representation Learning using Translation and Rotation Group Equivariant VAE
- Unsupervised Point Cloud Completion and Segmentation by Generative Adversarial Autoencoding Network
- Unsupervised Reinforcement Learning with Contrastive Intrinsic Control
- Unsupervised Representation Learning from Pre-trained Diffusion Probabilistic Models
- Unsupervised Skill Discovery via Recurrent Skill Training
- Unsupervised Visual Representation Learning via Mutual Information Regularized Assignment
- Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protection
- Uplifting Bandits
- UQGAN: A Unified Model for Uncertainty Quantification of Deep Classifiers trained via Conditional GANs
- USB: A Unified Semi-supervised Learning Benchmark for Classification
- Use-Case-Grounded Simulations for Explanation Evaluation
- Using Embeddings for Causal Estimation of Peer Influence in Social Networks
- Using Mixup as a Regularizer Can Surprisingly Improve Accuracy & Out-of-Distribution Robustness
- Using natural language and program abstractions to instill human inductive biases in machines
- Using Partial Monotonicity in Submodular Maximization
- UViM: A Unified Modeling Approach for Vision with Learned Guiding Codes
- VAEL: Bridging Variational Autoencoders and Probabilistic Logic Programming
- VaiPhy: a Variational Inference Based Algorithm for Phylogeny
- Value Function Decomposition for Iterative Design of Reinforcement Learning Agents
- Variable-rate hierarchical CPC leads to acoustic unit discovery in speech
- Variance Reduced ProxSkip: Algorithm, Theory and Application to Federated Learning
- Variational inference via Wasserstein gradient flows
- Variational Model Perturbation for Source-Free Domain Adaptation
- VCT: A Video Compression Transformer
- VectorAdam for Rotation Equivariant Geometry Optimization
- VeriDark: A Large-Scale Benchmark for Authorship Verification on the Dark Web
- Verification and search algorithms for causal DAGs
- Versatile Multi-stage Graph Neural Network for Circuit Representation
- VER: Scaling On-Policy RL Leads to the Emergence of Navigation in Embodied Rearrangement
- VF-PS: How to Select Important Participants in Vertical Federated Learning, Efficiently and Securely?
- VICE: Variational Interpretable Concept Embeddings
- VICRegL: Self-Supervised Learning of Local Visual Features
- Video-based Human-Object Interaction Detection from Tubelet Tokens
- Video compression dataset and benchmark of learning-based video-quality metrics
- Video Diffusion Models
- VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
- Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos
- ViewFool: Evaluating the Robustness of Visual Recognition to Adversarial Viewpoints
- VisCo Grids: Surface Reconstruction with Viscosity and Coarea Grids
- VisFIS: Visual Feature Importance Supervision with Right-for-the-Right-Reason Objectives
- Vision GNN: An Image is Worth Graph of Nodes
- ViSioNS: Visual Search in Natural Scenes Benchmark
- Vision Transformers provably learn spatial structure
- Vision Transformers: Theory and applications
- Visual Clues: Bridging Vision and Language Foundations for Image Paragraph Captioning
- Visual Concepts Tokenization
- Visual correspondence-based explanations improve AI robustness and human-AI team accuracy
- Visual Prompting via Image Inpainting
- VITA: Video Instance Segmentation via Object Token Association
- ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation
- VLMbench: A Compositional Benchmark for Vision-and-Language Manipulation
- VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts
- VoiceBlock: Privacy through Real-Time Adversarial Attacks with Audio-to-Audio Models
- VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Grids
- VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning
- VTC-LFC: Vision Transformer Compression with Low-Frequency Components
- Washing The Unwashable : On The (Im)possibility of Fairwashing Detection
- Wasserstein K-means for clustering probability distributions
- Wasserstein Iterative Networks for Barycenter Estimation
- Wasserstein Logistic Regression with Mixed Features
- Watermarking for Out-of-distribution Detection
- WaveBound: Dynamic Error Bounds for Stable Time Series Forecasting
- Wavelet Feature Maps Compression for Image-to-Image CNNs
- Wavelet Score-Based Generative Modeling
- Weakly supervised causal representation learning
- Weakly-Supervised Multi-Granularity Map Learning for Vision-and-Language Navigation
- Weakly Supervised Representation Learning with Sparse Perturbations
- Weak-shot Semantic Segmentation via Dual Similarity Transfer
- WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents
- Weighted Distillation with Unlabeled Examples
- Weighted Mutual Learning with Diversity-Driven Model Compression
- WeightedSHAP: analyzing and improving Shapley based feature attributions
- Weisfeiler and Leman Go Walking: Random Walk Kernels Revisited
- What are the best Systems? New Perspectives on NLP Benchmarking
- What Can the Neural Tangent Kernel Tell Us About Adversarial Robustness?
- What Can Transformers Learn In-Context? A Case Study of Simple Function Classes
- What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methods
- What is a Good Metric to Study Generalization of Minimax Learners?
- What is Where by Looking: Weakly-Supervised Open-World Phrase-Grounding without Text Inputs
- What Makes a "Good" Data Augmentation in Knowledge Distillation - A Statistical Perspective
- What Makes Graph Neural Networks Miscalibrated?
- What's the Harm? Sharp Bounds on the Fraction Negatively Affected by Treatment
- What You See is What You Classify: Black Box Attributions
- What You See is What You Get: Principled Deep Learning via Distributional Generalization
- When Adversarial Training Meets Vision Transformers: Recipes from Training to Architecture
- When are Local Queries Useful for Robust Learning?
- When are Offline Two-Player Zero-Sum Markov Games Solvable?
- When Combinatorial Thompson Sampling meets Approximation Regret
- When Does Differentially Private Learning Not Suffer in High Dimensions?
- When does dough become a bagel? Analyzing the remaining mistakes on ImageNet
- When Does Group Invariant Learning Survive Spurious Correlations?
- When does return-conditioned supervised learning work for offline reinforcement learning?
- When Do Flat Minima Optimizers Work?
- When is the Convergence Time of Langevin Algorithms Dimension Independent? A Composite Optimization Viewpoint
- When Privacy Meets Partial Information: A Refined Analysis of Differentially Private Bandits
- When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learning
- When to Intervene: Learning Optimal Intervention Policies for Critical Events
- When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment
- When to Trust Your Simulator: Dynamics-Aware Hybrid Offline-and-Online Reinforcement Learning
- When to Update Your Model: Constrained Model-based Reinforcement Learning
- Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Maps
- Where do Models go Wrong? Parameter-Space Saliency Maps for Explainability
- Where to Pay Attention in Sparse Training for Feature Selection?
- Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanations
- Whitening Convergence Rate of Coupling-based Normalizing Flows
- Why Do Artificially Generated Data Help Adversarial Robustness
- Why do tree-based models still outperform deep learning on typical tabular data?
- Why do We Need Large Batchsizes in Contrastive Learning? A Gradient-Bias Perspective
- Why neural networks find simple solutions: The many regularizers of geometric complexity
- “Why Not Other Classes?”: Towards Class-Contrastive Back-Propagation Explanations
- Why Robust Generalization in Deep Learning is Difficult: Perspective of Expressive Power
- Why So Pessimistic? Estimating Uncertainties for Offline RL through Ensembles, and Why Their Independence Matters
- Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Time
- Will Bilevel Optimizers Benefit from Loops
- WinoGAViL: Gamified Association Benchmark to Challenge Vision-and-Language Models
- Workshop on Distribution Shifts: Connecting Methods and Applications
- Workshop on Machine Learning for Creativity and Design
- Workshop on Machine Learning Safety
- Workshop on neuro Causal and Symbolic AI (nCSI)
- WT-MVSNet: Window-based Transformers for Multi-view Stereo
- Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark
- XTC: Extreme Compression for Pre-trained Transformers Made Simple and Efficient
- xView3-SAR: Detecting Dark Fishing Activity Using Synthetic Aperture Radar Imagery
- You Can’t Count on Luck: Why Decision Transformers and RvS Fail in Stochastic Environments
- You Never Stop Dancing: Non-freezing Dance Generation via Bank-constrained Manifold Projection
- You Only Live Once: Single-Life Reinforcement Learning
- Your Out-of-Distribution Detection Method is Not Robust!
- Your Transformer May Not be as Powerful as You Expect
- ZARTS: On Zero-order Optimization for Neural Architecture Search
- ZeroC: A Neuro-Symbolic Model for Zero-shot Concept Recognition and Acquisition at Inference Time
- ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers
- Zero-Shot 3D Drug Design by Sketching and Generating
- Zero-shot Transfer Learning within a Heterogeneous Graph via Knowledge Transfer Networks
- Zero-Shot Video Question Answering via Frozen Bidirectional Language Models
- Zero-Sum Stochastic Stackelberg Games
- Zeroth-Order Hard-Thresholding: Gradient Error vs. Expansivity
- Zeroth-Order Negative Curvature Finding: Escaping Saddle Points without Gradients
- ZIN: When and How to Learn Invariance Without Environment Partition?
- Zonotope Domains for Lagrangian Neural Network Verification
- ZooD: Exploiting Model Zoo for Out-of-Distribution Generalization
- ZSON: Zero-Shot Object-Goal Navigation using Multimodal Goal Embeddings