Reproducibility Index

Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..

Conference on Neural Information Processing Systems (NeurIPS) - 2020

Documentation Rate of Empirical Papers by Reproducibility Variable

Distribution of Empirical Papers by Number of Documented Variables

Website:

Venue	Year	Papers	Reproducibility Score Reproducibility Score based on Gundersen et al. (2025). See Methods for details.	Documentation Score Documentation Score is the average score over the seven reproducibility variables for empirical research papers. See Methods for details.	% Empirical Percentage of papers that are empirical research vs theoretical research.	% Industry Percentage of empirical research papers with at least one author from Industry.	Website
NeurIPS	2020	1898	0.56	3.38	89.88%	43.26%

Search Papers

	Pseudocode	Open Source Code	Open Datasets	Dataset Splits	Hardware Specification	Software Dependencies	Experiment Setup
(De)Randomized Smoothing for Certifiable Defense against Patch Attacks	❌	❌	✅	✅	✅	❌	✅	4
3D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Data	❌	❌	✅	❌	❌	❌	✅	2
3D Self-Supervised Methods for Medical Imaging	❌	✅	✅	✅	❌	❌	❌	3
3D Shape Reconstruction from Vision and Touch	❌	✅	❌	❌	❌	❌	❌	1
A Bandit Learning Algorithm and Applications to Auction Design	✅	❌	❌	❌	❌	❌	❌	1
A Bayesian Nonparametrics View into Deep Representations	❌	❌	✅	❌	❌	❌	❌	1
A Bayesian Perspective on Training Speed and Model Selection	✅	❌	✅	❌	✅	❌	✅	4
A Benchmark for Systematic Generalization in Grounded Language Understanding	❌	✅	✅	✅	❌	❌	✅	4
A Biologically Plausible Neural Network for Slow Feature Analysis	✅	✅	✅	❌	❌	❌	❌	3
A Boolean Task Algebra for Reinforcement Learning	✅	❌	❌	❌	❌	❌	❌	1
A Catalyst Framework for Minimax Optimization	✅	❌	❌	❌	❌	❌	✅	2
A Causal View on Robustness of Neural Networks	❌	❌	✅	❌	❌	❌	❌	1
A Class of Algorithms for General Instrumental Variable Models	✅	✅	✅	❌	❌	❌	✅	4
A Closer Look at Accuracy vs. Robustness	❌	✅	✅	❌	❌	❌	✅	3
A Closer Look at the Training Strategy for Modern Meta-Learning	❌	✅	✅	✅	❌	❌	✅	4
A Combinatorial Perspective on Transfer Learning	❌	✅	✅	✅	❌	❌	✅	4
A Computational Separation between Private Learning and Online Learning	✅	❌	❌	❌	❌	❌	❌	1
A Continuous-Time Mirror Descent Approach to Sparse Phase Retrieval	❌	❌	❌	❌	❌	❌	✅	1
A Contour Stochastic Gradient Langevin Dynamics Algorithm for Simulations of Multi-modal Distributions	✅	❌	✅	❌	❌	❌	✅	3
A Convolutional Auto-Encoder for Haplotype Assembly and Viral Quasispecies Reconstruction	❌	✅	✅	✅	✅	❌	✅	5
A Decentralized Parallel Algorithm for Training Generative Adversarial Nets	✅	❌	✅	❌	❌	❌	✅	3
A Dictionary Approach to Domain-Invariant Learning in Deep Networks	❌	❌	✅	✅	❌	❌	❌	2
A Discrete Variational Recurrent Topic Model without the Reparametrization Trick	❌	✅	✅	✅	❌	❌	✅	4
A Dynamical Central Limit Theorem for Shallow Neural Networks	❌	❌	❌	❌	❌	❌	✅	1
A Fair Classifier Using Kernel Density Estimation	❌	❌	✅	❌	✅	❌	✅	3
A Feasible Level Proximal Point Method for Nonconvex Sparse Constrained Optimization	✅	❌	✅	✅	❌	❌	✅	4
A Finite-Time Analysis of Two Time-Scale Actor-Critic Methods	✅	❌	❌	❌	❌	❌	❌	1
A Flexible Framework for Designing Trainable Priors with Adaptive Smoothing and Game Encoding	✅	✅	✅	✅	❌	❌	✅	5
A Game Theoretic Analysis of Additive Adversarial Attacks and Defenses	❌	❌	✅	❌	❌	❌	❌	1
A Game-Theoretic Analysis of the Empirical Revenue Maximization Algorithm with Endogenous Sampling	❌	❌	❌	❌	❌	❌	❌	0
A General Large Neighborhood Search Framework for Solving Integer Linear Programs	✅	❌	✅	✅	❌	✅	✅	5
A General Method for Robust Learning from Batches	❌	❌	❌	❌	❌	❌	❌	0
A Generalized Neural Tangent Kernel Analysis for Two-layer Neural Networks	✅	❌	❌	❌	❌	❌	❌	1
A Group-Theoretic Framework for Data Augmentation	❌	❌	✅	❌	❌	❌	✅	2
A Limitation of the PAC-Bayes Framework	❌	❌	❌	❌	❌	❌	❌	0
A Local Temporal Difference Code for Distributional Reinforcement Learning	❌	❌	❌	❌	❌	❌	❌	0
A Loss Function for Generative Neural Networks Based on Watson’s Perceptual Model	❌	✅	✅	✅	✅	❌	✅	5
A Matrix Chernoff Bound for Markov Chains and Its Application to Co-occurrence Matrices	✅	❌	✅	❌	❌	❌	✅	3
A Maximum-Entropy Approach to Off-Policy Evaluation in Average-Reward MDPs	❌	❌	✅	❌	❌	❌	✅	2
A Measure-Theoretic Approach to Kernel Conditional Mean Embeddings	❌	❌	❌	❌	❌	❌	✅	1
A Non-Asymptotic Analysis for Stein Variational Gradient Descent	❌	❌	❌	❌	❌	❌	❌	0
A Novel Approach for Constrained Optimization in Graphical Models	✅	❌	✅	❌	❌	✅	✅	4
A Novel Automated Curriculum Strategy to Solve Hard Sokoban Planning Instances	✅	❌	✅	❌	❌	❌	✅	3
A Randomized Algorithm to Reduce the Support of Discrete Measures	✅	✅	✅	❌	✅	❌	❌	4
A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection	✅	✅	✅	✅	✅	❌	✅	6
A Robust Functional EM Algorithm for Incomplete Panel Count Data	✅	❌	✅	❌	❌	❌	✅	3
A Scalable Approach for Privacy-Preserving Collaborative Machine Learning	✅	❌	✅	❌	✅	❌	✅	4
A Scalable MIP-based Method for Learning Optimal Multivariate Decision Trees	✅	❌	✅	✅	❌	✅	✅	5
A Self-Tuning Actor-Critic Algorithm	✅	❌	✅	❌	❌	❌	✅	3
A Simple Language Model for Task-Oriented Dialogue	❌	✅	✅	✅	❌	❌	❌	3
A Simple and Efficient Smoothing Method for Faster Optimization and Local Exploration	✅	❌	❌	❌	❌	❌	✅	2
A Single Recipe for Online Submodular Maximization with Adversarial or Stochastic Constraints	✅	❌	✅	❌	❌	❌	✅	3
A Single-Loop Smoothed Gradient Descent-Ascent Algorithm for Nonconvex-Concave Min-Max Problems	✅	❌	✅	❌	❌	❌	❌	2
A Spectral Energy Distance for Parallel Speech Synthesis	❌	✅	❌	✅	✅	❌	✅	4
A Statistical Framework for Low-bitwidth Training of Deep Neural Networks	❌	✅	✅	✅	✅	❌	✅	5
A Statistical Mechanics Framework for Task-Agnostic Sample Design in Machine Learning	❌	❌	❌	❌	❌	❌	✅	1
A Stochastic Path Integral Differential EstimatoR Expectation Maximization Algorithm	✅	❌	✅	❌	❌	❌	✅	3
A Study on Encodings for Neural Architecture Search	❌	✅	✅	✅	✅	❌	✅	5
A Theoretical Framework for Target Propagation	❌	✅	✅	✅	❌	❌	✅	4
A Tight Lower Bound and Efficient Reduction for Swap Regret	✅	❌	❌	❌	❌	❌	❌	1
A Topological Filter for Learning with Label Noise	✅	✅	✅	✅	✅	❌	✅	6
A Unified Switching System Perspective and Convergence Analysis of Q-Learning Algorithms	❌	❌	❌	❌	❌	❌	✅	1
A Unified View of Label Shift Estimation	❌	❌	✅	✅	❌	❌	✅	3
A Unifying View of Optimism in Episodic Reinforcement Learning	❌	❌	❌	❌	❌	❌	❌	0
A Universal Approximation Theorem of Deep Neural Networks for Expressing Probability Distributions	❌	❌	❌	❌	❌	❌	❌	0
A Variational Approach for Learning from Positive and Unlabeled Data	✅	✅	✅	✅	❌	✅	✅	6
A causal view of compositional zero-shot recognition	❌	✅	✅	✅	✅	❌	✅	5
A convex optimization formulation for multivariate regression	❌	❌	❌	✅	❌	❌	✅	2
A game-theoretic analysis of networked system control for common-pool resource management using multi-agent reinforcement learning	❌	✅	❌	❌	❌	❌	✅	2
A graph similarity for deep learning	✅	✅	✅	✅	❌	❌	✅	5
A kernel test for quasi-independence	❌	❌	✅	❌	❌	❌	❌	1
A mathematical model for automatic differentiation in machine learning	✅	❌	❌	❌	❌	❌	❌	1
A mathematical theory of cooperative communication	❌	❌	✅	❌	❌	❌	✅	2
A mean-field analysis of two-player zero-sum games	✅	✅	✅	❌	❌	❌	✅	4
A meta-learning approach to (re)discover plasticity rules that carve a desired function into a neural network	❌	❌	❌	❌	❌	❌	✅	1
A new convergent variant of Q-learning with linear function approximation	❌	❌	✅	❌	❌	❌	✅	2
A new inference approach for training shallow and deep generalized linear models of noisy interacting neurons	❌	✅	❌	❌	❌	❌	✅	2
A novel variational form of the Schatten-$p$ quasi-norm	❌	❌	✅	❌	✅	✅	✅	4
A polynomial-time algorithm for learning nonparametric causal graphs	✅	✅	❌	❌	❌	❌	❌	2
A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent	❌	❌	✅	❌	❌	❌	✅	2
A shooting formulation of deep learning	❌	✅	✅	✅	❌	❌	✅	4
A simple normative network approximates local non-Hebbian learning in the cortex	✅	❌	✅	❌	❌	❌	❌	2
A/B Testing in Dense Large-Scale Networks: Design and Inference	✅	❌	❌	❌	❌	❌	❌	1
AI Feynman 2.0: Pareto-optimal symbolic regression exploiting graph modularity	❌	✅	✅	✅	❌	❌	✅	4
AOT: Appearance Optimal Transport Based Identity Swapping for Forgery Detection	❌	❌	✅	❌	❌	❌	❌	1
ARMA Nets: Expanding Receptive Field for Dense Prediction	❌	✅	✅	✅	❌	❌	✅	4
AViD Dataset: Anonymized Videos from Diverse Countries	❌	✅	✅	❌	✅	❌	✅	4
Accelerating Reinforcement Learning through GPU Atari Emulation	❌	✅	✅	❌	✅	❌	✅	4
Accelerating Training of Transformer-Based Language Models with Progressive Layer Dropping	✅	✅	✅	✅	✅	❌	✅	6
Acceleration with a Ball Optimization Oracle	✅	❌	❌	❌	❌	❌	❌	1
Achieving Equalized Odds by Resampling Sensitive Attributes	✅	✅	✅	✅	❌	❌	❌	4
Active Invariant Causal Prediction: Experiment Selection through Stability	✅	✅	❌	❌	❌	❌	✅	3
Active Structure Learning of Causal DAGs via Directed Clique Trees	✅	✅	❌	❌	❌	❌	✅	3
AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradients	✅	✅	✅	✅	❌	❌	✅	5
AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning	❌	❌	✅	❌	❌	❌	✅	2
AdaTune: Adaptive Tensor Program Compilation Made Efficient	✅	❌	✅	❌	✅	❌	✅	4
Adam with Bandit Sampling for Deep Learning	✅	❌	✅	❌	❌	❌	✅	3
Adaptation Properties Allow Identification of Optimized Neural Codes	❌	❌	❌	❌	❌	❌	❌	0
Adapting Neural Architectures Between Domains	❌	❌	✅	✅	❌	❌	✅	3
Adapting to Misspecification in Contextual Bandits	✅	❌	❌	❌	❌	❌	❌	1
Adaptive Discretization for Model-Based Reinforcement Learning	✅	✅	❌	❌	❌	❌	✅	3
Adaptive Experimental Design with Temporal Interference: A Maximum Likelihood Approach	❌	❌	❌	❌	❌	❌	❌	0
Adaptive Gradient Quantization for Data-Parallel SGD	✅	✅	✅	✅	❌	❌	✅	5
Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting	❌	✅	✅	✅	✅	✅	✅	6
Adaptive Importance Sampling for Finite-Sum Optimization and Sampling with Decreasing Step-Sizes	❌	❌	✅	❌	❌	❌	✅	2
Adaptive Learned Bloom Filter (Ada-BF): Efficient Utilization of the Classifier with Application to Real-Time Information Filtering on the Web	❌	✅	✅	❌	❌	❌	✅	3
Adaptive Learning of Rank-One Models for Efficient Pairwise Sequence Alignment	✅	✅	✅	❌	❌	❌	❌	3
Adaptive Online Estimation of Piecewise Polynomial Trends	✅	❌	❌	❌	❌	❌	✅	2
Adaptive Probing Policies for Shortest Path Routing	✅	❌	✅	❌	❌	❌	✅	3
Adaptive Reduced Rank Regression	✅	❌	❌	❌	❌	❌	❌	1
Adaptive Sampling for Stochastic Risk-Averse Learning	✅	✅	✅	❌	❌	❌	✅	4
Adaptive Shrinkage Estimation for Streaming Graphs	✅	❌	✅	❌	✅	❌	✅	4
AdvFlow: Inconspicuous Black-box Adversarial Attacks using Normalizing Flows	✅	✅	✅	❌	❌	❌	✅	4
Advances in Black-Box VI: Normalizing Flows, Importance Weighting, and Optimization	❌	❌	✅	❌	❌	❌	✅	2
Adversarial Attacks on Deep Graph Matching	✅	❌	✅	❌	❌	❌	✅	3
Adversarial Attacks on Linear Contextual Bandits	✅	❌	✅	❌	❌	❌	✅	3
Adversarial Bandits with Corruptions: Regret Lower Bound and No-regret Algorithm	✅	❌	❌	❌	❌	❌	❌	1
Adversarial Blocking Bandits	✅	❌	❌	❌	❌	❌	❌	1
Adversarial Counterfactual Learning and Evaluation for Recommender System	✅	❌	✅	✅	❌	❌	❌	3
Adversarial Crowdsourcing Through Robust Rank-One Matrix Completion	✅	✅	✅	❌	❌	❌	❌	3
Adversarial Distributional Training for Robust Deep Learning	✅	✅	✅	❌	❌	❌	✅	4
Adversarial Example Games	❌	✅	✅	❌	❌	❌	✅	3
Adversarial Learning for Robust Deep Clustering	✅	✅	✅	✅	❌	❌	✅	5
Adversarial Robustness of Supervised Sparse Coding	❌	✅	✅	✅	❌	❌	✅	4
Adversarial Self-Supervised Contrastive Learning	✅	✅	✅	❌	❌	❌	✅	4
Adversarial Soft Advantage Fitting: Imitation Learning without Policy Optimization	✅	❌	❌	❌	❌	❌	✅	2
Adversarial Sparse Transformer for Time Series Forecasting	✅	❌	✅	❌	❌	❌	✅	3
Adversarial Style Mining for One-Shot Unsupervised Domain Adaptation	✅	✅	✅	❌	❌	❌	❌	3
Adversarial Training is a Form of Data-dependent Operator Norm Regularization	❌	❌	✅	❌	✅	❌	❌	2
Adversarial Weight Perturbation Helps Robust Generalization	✅	✅	✅	❌	❌	❌	✅	4
Adversarial robustness via robust low rank representations	✅	❌	✅	❌	❌	❌	✅	3
Adversarially Robust Few-Shot Learning: A Meta-Learning Approach	✅	✅	✅	❌	❌	❌	✅	4
Adversarially Robust Streaming Algorithms via Differential Privacy	✅	❌	❌	❌	❌	❌	❌	1
Adversarially-learned Inference via an Ensemble of Discrete Undirected Graphical Models	❌	❌	✅	❌	❌	❌	✅	2
Agnostic $Q$-learning with Function Approximation in Deterministic Systems: Near-Optimal Bounds on Approximation Error and Sample Complexity	✅	❌	❌	❌	❌	❌	❌	1
Agnostic Learning of a Single Neuron with Gradient Descent	❌	❌	❌	❌	❌	❌	❌	0
Agnostic Learning with Multiple Objectives	✅	❌	✅	✅	❌	❌	✅	4
Agree to Disagree: Adaptive Ensemble Knowledge Distillation in Gradient Space	❌	✅	✅	✅	❌	❌	✅	4
Algorithmic recourse under imperfect causal knowledge: a probabilistic approach	❌	✅	✅	❌	❌	❌	✅	3
All Word Embeddings from One Embedding	❌	✅	✅	✅	❌	❌	✅	4
All your loss are belong to Bayes	❌	✅	✅	✅	❌	❌	✅	4
All-or-nothing statistical and computational phase transitions in sparse spiked matrix estimation	❌	❌	❌	❌	❌	❌	❌	0
Almost Optimal Model-Free Reinforcement Learningvia Reference-Advantage Decomposition	✅	❌	❌	❌	❌	❌	❌	1
Almost Surely Stable Deep Dynamics	❌	✅	❌	❌	❌	❌	✅	2
An Analysis of SVD for Deep Rotation Estimation	❌	❌	✅	❌	❌	❌	✅	2
An Asymptotically Optimal Primal-Dual Incremental Algorithm for Contextual Linear Bandits	✅	❌	❌	❌	❌	❌	✅	2
An Efficient Adversarial Attack for Tree Ensembles	✅	✅	✅	❌	❌	❌	✅	4
An Efficient Asynchronous Method for Integrating Evolutionary and Gradient-based Policy Search	✅	✅	✅	❌	✅	❌	✅	5
An Efficient Framework for Clustered Federated Learning	✅	✅	✅	❌	❌	❌	✅	4
An Empirical Process Approach to the Union Bound: Practical Algorithms for Combinatorial and Linear Bandits	✅	❌	❌	❌	❌	❌	✅	2
An Equivalence between Loss Functions and Non-Uniform Sampling in Experience Replay	❌	✅	✅	❌	❌	❌	❌	2
An Imitation from Observation Approach to Transfer Learning with Dynamics Mismatch	✅	❌	✅	❌	❌	❌	✅	3
An Improved Analysis of (Variance-Reduced) Policy Gradient and Natural Policy Gradient Methods	✅	✅	❌	❌	❌	❌	✅	3
An Improved Analysis of Stochastic Gradient Descent with Momentum	✅	✅	✅	❌	❌	❌	✅	4
An Optimal Elimination Algorithm for Learning a Best Arm	✅	❌	❌	❌	❌	❌	❌	1
An Unbiased Risk Estimator for Learning with Augmented Classes	❌	❌	✅	✅	❌	❌	❌	2
An Unsupervised Information-Theoretic Perceptual Quality Metric	❌	✅	✅	❌	❌	❌	❌	2
An analytic theory of shallow networks dynamics for hinge loss classification	❌	❌	✅	❌	❌	❌	✅	2
An efficient nonconvex reformulation of stagewise convex optimization problems	✅	❌	✅	❌	❌	❌	✅	3
An implicit function learning approach for parametric modal regression	❌	❌	✅	❌	❌	❌	✅	2
An operator view of policy gradient methods	❌	❌	❌	❌	❌	❌	✅	1
Analysis and Design of Thompson Sampling for Stochastic Partial Monitoring	✅	❌	❌	❌	❌	❌	✅	2
Analytic Characterization of the Hessian in Shallow ReLU Models: A Tale of Symmetry	❌	❌	❌	❌	❌	❌	✅	1
Analytical Probability Distributions and Exact Expectation-Maximization for Deep Generative Networks	✅	✅	✅	❌	❌	❌	✅	4
Applications of Common Entropy for Causal Inference	✅	❌	✅	❌	❌	❌	✅	3
Approximate Cross-Validation for Structured Models	✅	❌	✅	✅	✅	❌	❌	4
Approximate Cross-Validation with Low-Rank Data in High Dimensions	❌	❌	✅	✅	❌	❌	✅	3
Approximate Heavily-Constrained Learning with Lagrange Multiplier Models	❌	✅	✅	❌	❌	❌	✅	3
Approximation Based Variance Reduction for Reparameterization Gradients	✅	❌	✅	❌	✅	✅	✅	5
Assessing SATNet's Ability to Solve the Symbol Grounding Problem	❌	❌	✅	❌	❌	❌	✅	2
Assisted Learning: A Framework for Multi-Organization Learning	✅	❌	✅	✅	❌	❌	❌	3
Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability	❌	❌	✅	❌	❌	❌	❌	1
Asymptotic Guarantees for Generative Modeling Based on the Smooth Wasserstein Distance	❌	❌	❌	❌	❌	❌	✅	1
Asymptotic normality and confidence intervals for derivatives of 2-layers neural network in the random features model	❌	✅	❌	❌	❌	❌	✅	2
Asymptotically Optimal Exact Minibatch Metropolis-Hastings	✅	✅	✅	❌	❌	❌	✅	4
Attack of the Tails: Yes, You Really Can Backdoor Federated Learning	❌	✅	✅	❌	❌	❌	✅	3
AttendLight: Universal Attention-Based Reinforcement Learning Model for Traffic Signal Control	❌	❌	✅	✅	❌	❌	✅	3
Attention-Gated Brain Propagation: How the brain can implement reward-based error backpropagation	❌	✅	✅	❌	❌	❌	✅	3
Attribute Prototype Network for Zero-Shot Learning	❌	❌	✅	✅	❌	❌	✅	3
Attribution Preservation in Network Compression for Reliable Network Interpretation	❌	❌	✅	❌	❌	❌	✅	2
Audeo: Audio Generation for a Silent Performance Video	❌	✅	✅	❌	✅	❌	✅	4
Auditing Differentially Private Machine Learning: How Private is Private SGD?	✅	❌	✅	❌	❌	❌	✅	3
Auto Learning Attention	❌	✅	✅	✅	❌	❌	✅	4
Auto-Panoptic: Cooperative Multi-Component Architecture Search for Panoptic Segmentation	✅	✅	✅	✅	✅	❌	✅	6
AutoBSS: An Efficient Algorithm for Block Stacking Style Search	❌	❌	✅	✅	❌	❌	✅	3
AutoPrivacy: Automated Layer-wise Parameter Selection for Secure Neural Network Inference	❌	❌	✅	❌	✅	❌	✅	3
AutoSync: Learning to Synchronize for Data-Parallel Distributed Deep Learning	❌	✅	✅	❌	✅	❌	❌	3
Autoencoders that don't overfit towards the Identity	❌	✅	✅	❌	❌	❌	✅	3
Autofocused oracles for model-based design	✅	✅	✅	❌	❌	❌	✅	4
Automatic Curriculum Learning through Value Disagreement	✅	✅	✅	❌	✅	❌	✅	5
Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond	✅	✅	✅	❌	✅	❌	✅	5
Automatically Learning Compact Quality-aware Surrogates for Optimization Problems	❌	✅	✅	✅	❌	✅	✅	5
Autoregressive Score Matching	❌	❌	✅	❌	✅	❌	❌	2
Auxiliary Task Reweighting for Minimum-data Learning	✅	✅	✅	❌	❌	❌	❌	3
AvE: Assistance via Empowerment	✅	✅	✅	❌	❌	❌	✅	4
Avoiding Side Effects By Considering Future Tasks	✅	✅	❌	❌	❌	❌	✅	3
Avoiding Side Effects in Complex Environments	✅	✅	✅	✅	❌	❌	✅	5
Axioms for Learning from Pairwise Comparisons	❌	❌	❌	❌	❌	❌	❌	0
BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning	✅	✅	✅	✅	❌	❌	✅	5
BERT Loses Patience: Fast and Robust Inference with Early Exit	❌	✅	✅	✅	✅	❌	✅	5
BOSS: Bayesian Optimization over String Spaces	❌	✅	✅	❌	✅	❌	✅	4
BRP-NAS: Prediction-based NAS using GCNs	❌	✅	✅	✅	✅	❌	✅	5
Backpropagating Linearly Improves Transferability of Adversarial Examples	❌	✅	✅	❌	✅	❌	✅	4
Bad Global Minima Exist and SGD Can Reach Them	✅	✅	✅	❌	❌	✅	✅	5
Balanced Meta-Softmax for Long-Tailed Visual Recognition	❌	✅	✅	✅	❌	❌	❌	3
Bandit Linear Control	✅	❌	❌	❌	❌	❌	❌	1
Bandit Samplers for Training Graph Neural Networks	✅	✅	✅	✅	✅	❌	✅	6
BanditPAM: Almost Linear Time k-Medoids Clustering via Multi-Armed Bandits	✅	✅	✅	❌	❌	❌	✅	4
Barking up the right tree: an approach to search over molecule synthesis DAGs	✅	✅	✅	❌	❌	❌	❌	3
Batch Normalization Biases Residual Blocks Towards the Identity Function in Deep Networks	❌	✅	✅	✅	❌	❌	✅	4
Batch normalization provably avoids ranks collapse for randomly initialised deep networks	❌	❌	✅	❌	❌	❌	✅	2
Batched Coarse Ranking in Multi-Armed Bandits	✅	❌	✅	✅	❌	❌	✅	4
Baxter Permutation Process	✅	✅	✅	❌	❌	❌	❌	3
BayReL: Bayesian Relational Learning for Multi-omics Data Integration	❌	✅	✅	✅	❌	❌	✅	4
Bayes Consistency vs. H-Consistency: The Interplay between Surrogate Loss Functions and the Scoring Function Class	❌	❌	✅	✅	❌	❌	✅	3
Bayesian Attention Modules	✅	✅	✅	✅	✅	❌	✅	6
Bayesian Bits: Unifying Quantization and Pruning	❌	❌	✅	❌	✅	❌	✅	3
Bayesian Causal Structural Learning with Zero-Inflated Poisson Bayesian Networks	✅	❌	✅	❌	✅	❌	✅	4
Bayesian Deep Ensembles via the Neural Tangent Kernel	✅	✅	✅	❌	❌	❌	✅	4
Bayesian Deep Learning and a Probabilistic Perspective of Generalization	❌	✅	✅	✅	❌	❌	✅	4
Bayesian Meta-Learning for the Few-Shot Setting via Deep Kernels	✅	✅	✅	✅	❌	❌	✅	5
Bayesian Multi-type Mean Field Multi-agent Imitation Learning	✅	❌	❌	❌	❌	❌	❌	1
Bayesian Optimization for Iterative Learning	✅	✅	✅	❌	✅	❌	✅	5
Bayesian Optimization of Risk Measures	❌	✅	❌	❌	❌	❌	✅	2
Bayesian Probabilistic Numerical Integration with Tree-Based Models	✅	❌	✅	❌	❌	❌	✅	3
Bayesian Pseudocoresets	✅	✅	❌	❌	❌	❌	✅	3
Bayesian Robust Optimization for Imitation Learning	❌	✅	❌	❌	❌	❌	✅	2
Bayesian filtering unifies adaptive and non-adaptive neural network optimization methods	✅	❌	✅	❌	❌	❌	✅	3
Belief Propagation Neural Networks	❌	❌	✅	✅	❌	❌	✅	3
Belief-Dependent Macro-Action Discovery in POMDPs using the Value of Information	✅	❌	❌	❌	❌	❌	✅	2
Benchmarking Deep Inverse Models over time, and the Neural-Adjoint method	❌	✅	✅	✅	❌	❌	❌	3
Benchmarking Deep Learning Interpretability in Time Series Predictions	✅	✅	✅	❌	❌	❌	❌	3
Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphs	❌	✅	✅	✅	❌	❌	✅	4
Beta R-CNN: Looking into Pedestrian Detection from Another Perspective	❌	❌	✅	✅	✅	❌	✅	4
Better Full-Matrix Regret via Parameter-Free Online Learning	✅	❌	❌	❌	❌	❌	❌	1
Better Set Representations For Relational Reasoning	✅	✅	✅	✅	❌	❌	✅	5
Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs	✅	✅	✅	✅	✅	❌	✅	6
Beyond Individualized Recourse: Interpretable and Interactive Summaries of Actionable Recourses	✅	❌	✅	❌	❌	❌	✅	3
Beyond Lazy Training for Over-parameterized Tensor Decomposition	✅	❌	❌	❌	❌	❌	❌	1
Beyond Perturbations: Learning Guarantees with Arbitrary Adversarial Test Examples	✅	❌	✅	❌	❌	❌	❌	2
Beyond accuracy: quantifying trial-by-trial behaviour of CNNs and humans by measuring error consistency	❌	✅	✅	❌	❌	✅	✅	4
Beyond the Mean-Field: Structured Deep Gaussian Processes Improve the Predictive Uncertainties	✅	✅	✅	✅	❌	❌	✅	5
Bi-level Score Matching for Learning Energy-based Latent Variable Models	✅	✅	✅	✅	❌	❌	✅	5
Bias no more: high-probability data-dependent regret bounds for adversarial bandits and MDPs	✅	❌	❌	❌	❌	❌	❌	1
Biased Stochastic First-Order Methods for Conditional Stochastic Optimization and Applications in Meta Learning	✅	❌	❌	❌	❌	❌	✅	2
Bidirectional Convolutional Poisson Gamma Dynamical Systems	❌	✅	✅	✅	✅	❌	✅	5
Big Bird: Transformers for Longer Sequences	❌	✅	✅	❌	❌	❌	✅	3
Big Self-Supervised Models are Strong Semi-Supervised Learners	❌	✅	✅	✅	✅	❌	✅	5
Biological credit assignment through dynamic inversion of feedforward networks	❌	❌	✅	❌	❌	❌	✅	2
Biologically Inspired Mechanisms for Adversarial Robustness	❌	❌	✅	❌	❌	❌	✅	2
Black-Box Certification with Randomized Smoothing: A Functional Optimization Based Framework	❌	❌	✅	❌	❌	❌	❌	1
Black-Box Optimization with Local Generative Surrogates	✅	❌	✅	❌	❌	❌	✅	3
Black-Box Ripper: Copying black-box models using generative evolutionary algorithms	✅	✅	✅	❌	❌	❌	✅	4
Blind Video Temporal Consistency via Deep Video Prior	❌	✅	✅	✅	✅	❌	✅	5
BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Images	❌	✅	✅	❌	❌	❌	❌	2
BoTorch: A Framework for Efficient Monte-Carlo Bayesian Optimization	✅	✅	✅	❌	❌	❌	❌	3
Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning	❌	✅	✅	✅	❌	❌	❌	3
Boosting Adversarial Training with Hypersphere Embedding	❌	✅	✅	✅	❌	❌	✅	4
Boosting First-Order Methods by Shifting Objective: New Schemes with Faster Worst-Case Rates	✅	❌	✅	❌	❌	❌	✅	3
Bootstrap Your Own Latent - A New Approach to Self-Supervised Learning	✅	✅	✅	✅	✅	❌	✅	6
Bootstrapping neural processes	❌	❌	✅	✅	❌	❌	✅	3
Boundary thickness and robustness in learning models	❌	✅	✅	❌	❌	❌	✅	3
BoxE: A Box Embedding Model for Knowledge Base Completion	❌	❌	✅	✅	❌	❌	❌	2
Breaking Reversibility Accelerates Langevin Dynamics for Non-Convex Optimization	❌	❌	✅	❌	❌	❌	❌	1
Breaking the Communication-Privacy-Accuracy Trilemma	❌	❌	❌	❌	❌	❌	❌	0
Breaking the Sample Size Barrier in Model-Based Reinforcement Learning with a Generative Model	❌	❌	❌	❌	❌	❌	✅	1
Bridging Imagination and Reality for Model-Based Deep Reinforcement Learning	✅	❌	✅	❌	✅	❌	✅	4
Bridging the Gap between Sample-based and One-shot Neural Architecture Search with BONAS	✅	✅	✅	✅	✅	❌	✅	6
Building powerful and equivariant graph neural networks with structural message-passing	❌	✅	✅	✅	❌	❌	✅	4
Byzantine Resilient Distributed Multi-Task Learning	❌	✅	✅	❌	❌	❌	✅	3
CASTLE: Regularization via Auxiliary Causal Graph Discovery	✅	✅	✅	✅	❌	❌	✅	5
CHIP: A Hawkes Process Model for Continuous-time Networks with Scalable and Consistent Estimation	✅	✅	✅	❌	✅	❌	✅	5
CLEARER: Multi-Scale Neural Architecture Search for Image Restoration	❌	✅	✅	✅	✅	❌	✅	5
CO-Optimal Transport	✅	❌	✅	❌	✅	❌	✅	4
COBE: Contextualized Object Embeddings from Narrated Instructional Video	❌	❌	✅	❌	❌	❌	❌	1
COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning	❌	✅	✅	✅	✅	❌	✅	5
COPT: Coordinated Optimal Transport on Graphs	✅	❌	✅	✅	✅	❌	✅	5
COT-GAN: Generating Sequential Data via Causal Optimal Transport	✅	✅	✅	❌	❌	❌	✅	4
CSER: Communication-efficient SGD with Error Reset	✅	❌	✅	❌	✅	❌	✅	4
CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances	❌	✅	✅	❌	❌	❌	✅	3
CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations	❌	❌	✅	❌	❌	❌	❌	1
Calibrated Reliable Regression using Maximum Mean Discrepancy	✅	❌	✅	❌	✅	❌	✅	4
Calibrating CNNs for Lifelong Learning	❌	❌	✅	✅	❌	❌	✅	3
Calibrating Deep Neural Networks using Focal Loss	❌	✅	✅	✅	❌	❌	✅	4
Calibration of Shared Equilibria in General Sum Partially Observable Markov Games	✅	❌	❌	❌	❌	❌	✅	2
Can Graph Neural Networks Count Substructures?	❌	✅	✅	✅	✅	❌	✅	5
Can I Trust My Fairness Metric? Assessing Fairness with Unlabeled Data and Bayesian Inference	❌	❌	✅	❌	❌	❌	✅	2
Can Implicit Bias Explain Generalization? Stochastic Convex Optimization as a Case Study	❌	❌	❌	❌	❌	❌	✅	1
Can Q-Learning with Graph Networks Learn a Generalizable Branching Heuristic for a SAT Solver?	❌	✅	✅	❌	❌	❌	❌	2
Can Temporal-Diﬀerence and Q-Learning Learn Representation? A Mean-Field Theory	✅	❌	❌	❌	❌	❌	❌	1
Can the Brain Do Backpropagation? --- Exact Implementation of Backpropagation in Predictive Coding Networks	✅	❌	✅	❌	❌	❌	✅	3
Canonical 3D Deformer Maps: Unifying parametric and non-parametric methods for dense weakly-supervised category reconstruction	❌	❌	✅	❌	❌	❌	❌	1
Cascaded Text Generation with Markov Transformers	✅	✅	✅	✅	✅	❌	✅	6
Causal Discovery from Soft Interventions with Unknown Targets: Characterization and Learning	✅	❌	❌	❌	❌	❌	❌	1
Causal Discovery in Physical Systems from Videos	❌	❌	❌	❌	❌	❌	❌	0
Causal Estimation with Functional Confounders	✅	❌	✅	✅	❌	❌	✅	4
Causal Imitation Learning With Unobserved Confounders	✅	❌	✅	❌	❌	❌	❌	2
Causal Intervention for Weakly-Supervised Semantic Segmentation	❌	✅	✅	✅	❌	❌	❌	3
Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Models	❌	❌	✅	❌	❌	❌	✅	2
Causal analysis of Covid-19 Spread in Germany	❌	❌	✅	❌	❌	❌	✅	2
Certifiably Adversarially Robust Detection of Out-of-Distribution Data	❌	✅	✅	❌	❌	❌	✅	3
Certified Defense to Image Transformations via Randomized Smoothing	❌	✅	✅	❌	✅	❌	✅	4
Certified Monotonic Neural Networks	✅	✅	✅	✅	✅	✅	✅	7
Certified Robustness of Graph Convolution Networks for Graph Classification under Topological Attacks	✅	✅	✅	✅	❌	❌	✅	5
Certifying Confidence via Randomized Smoothing	❌	✅	✅	❌	❌	❌	✅	3
Certifying Strategyproof Auction Networks	❌	❌	❌	✅	❌	❌	✅	2
Chaos, Extremism and Optimism: Volume Analysis of Learning in Games	❌	❌	❌	❌	❌	❌	❌	0
Characterizing Optimal Mixed Policies: Where to Intervene and What to Observe	✅	❌	❌	❌	❌	❌	❌	1
Characterizing emergent representations in a space of candidate learning rules for deep networks	❌	❌	❌	❌	❌	❌	✅	1
Choice Bandits	✅	❌	✅	❌	❌	❌	✅	3
CircleGAN: Generative Adversarial Learning across Spherical Circles	✅	❌	✅	❌	❌	❌	✅	3
Classification Under Misspecification: Halfspaces, Generalized Linear Models, and Evolvability	✅	✅	✅	✅	✅	❌	✅	6
Classification with Valid and Adaptive Coverage	✅	✅	✅	✅	❌	❌	✅	5
Closing the Dequantization Gap: PixelCNN as a Single-Layer Flow	❌	✅	✅	❌	❌	❌	❌	2
Co-Tuning for Transfer Learning	✅	✅	✅	✅	❌	❌	✅	5
Co-exposure Maximization in Online Social Networks	✅	✅	✅	❌	✅	❌	✅	5
CoADNet: Collaborative Aggregation-and-Distribution Networks for Co-Salient Object Detection	❌	✅	✅	❌	✅	❌	✅	4
CoMIR: Contrastive Multimodal Image Representation for Registration	❌	✅	✅	✅	❌	❌	✅	4
CoSE: Compositional Stroke Embeddings	❌	✅	✅	❌	❌	❌	❌	2
CodeCMR: Cross-Modal Retrieval For Function-Level Binary Source Code Matching	❌	❌	✅	✅	❌	❌	✅	3
Coded Sequential Matrix Multiplication For Straggler Mitigation	✅	❌	✅	❌	✅	❌	✅	4
CogLTX: Applying BERT to Long Texts	✅	✅	✅	✅	✅	❌	✅	6
CogMol: Target-Specific and Selective Drug Design for COVID-19 Using Deep Generative Models	❌	❌	✅	✅	❌	❌	✅	3
Coherent Hierarchical Multi-Label Classification Networks	❌	✅	✅	✅	❌	❌	✅	4
CoinDICE: Off-Policy Confidence Interval Estimation	❌	✅	✅	❌	❌	❌	✅	3
CoinPress: Practical Private Mean and Covariance Estimation	✅	✅	✅	❌	✅	❌	✅	5
ColdGANs: Taming Language GANs with Cautious Sampling Strategies	❌	❌	✅	✅	❌	❌	✅	3
Collapsing Bandits and Their Application to Public Health Intervention	✅	✅	✅	❌	❌	❌	✅	4
Collegial Ensembles	✅	❌	✅	❌	❌	❌	✅	3
Color Visual Illusions: A Statistics-based Computational Model	❌	✅	✅	❌	❌	❌	❌	2
Combining Deep Reinforcement Learning and Search for Imperfect-Information Games	✅	✅	✅	❌	❌	❌	✅	4
Community detection in sparse time-evolving graphs with a dynamical Bethe-Hessian	✅	✅	✅	❌	✅	❌	❌	4
Community detection using fast low-cardinality semidefinite programming	✅	✅	✅	❌	❌	❌	✅	4
CompRess: Self-Supervised Learning by Compressing Representations	❌	✅	✅	✅	✅	❌	✅	5
Compact task representations as a normative model for higher-order brain activity	❌	✅	✅	❌	❌	❌	❌	2
Comparator-Adaptive Convex Bandits	✅	❌	❌	❌	❌	❌	❌	1
Complex Dynamics in Simple Neural Networks: Understanding Gradient Flow in Phase Retrieval	❌	❌	❌	❌	❌	❌	✅	1
Compositional Explanations of Neurons	❌	✅	✅	✅	❌	❌	✅	4
Compositional Generalization by Learning Analytical Expressions	❌	✅	✅	❌	✅	❌	✅	4
Compositional Generalization via Neural-Symbolic Stack Machines	❌	❌	✅	✅	❌	❌	❌	2
Compositional Visual Generation with Energy Based Models	❌	✅	✅	❌	❌	❌	❌	2
Compositional Zero-Shot Learning via Fine-Grained Dense Feature Composition	✅	❌	✅	✅	✅	❌	✅	5
Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detection	❌	✅	✅	✅	❌	❌	✅	4
Compressing Images by Encoding Their Latent Representations with Relative Entropy Coding	✅	✅	✅	❌	❌	❌	✅	4
Computing Valid p-value for Optimal Changepoint by Selective Inference using Dynamic Programming	✅	✅	✅	❌	❌	❌	✅	4
Conditioning and Processing: Techniques to Improve Information-Theoretic Generalization Bounds	❌	❌	❌	❌	❌	❌	❌	0
Confidence sequences for sampling without replacement	❌	✅	❌	❌	❌	❌	❌	1
Conformal Symplectic and Relativistic Optimization	✅	✅	✅	❌	❌	❌	✅	4
Confounding-Robust Policy Evaluation in Infinite-Horizon Reinforcement Learning	✅	❌	❌	❌	❌	✅	✅	3
Conic Descent and its Application to Memory-efficient Optimization over Positive Semidefinite Matrices	✅	✅	✅	❌	❌	❌	✅	4
Consequences of Misaligned AI	❌	❌	❌	❌	❌	❌	❌	0
Conservative Q-Learning for Offline Reinforcement Learning	✅	❌	✅	❌	❌	❌	✅	3
Consistency Regularization for Certified Robustness of Smoothed Classifiers	❌	✅	✅	❌	✅	❌	✅	4
Consistent Estimation of Identifiable Nonparametric Mixture Models from Grouped Observations	✅	❌	✅	✅	❌	❌	✅	4
Consistent Plug-in Classifiers for Complex Objectives and Constraints	✅	✅	✅	❌	❌	❌	✅	4
Consistent Structural Relation Learning for Zero-Shot Segmentation	❌	❌	✅	✅	❌	❌	❌	2
Consistent feature selection for analytic deep neural networks	❌	✅	✅	❌	❌	❌	✅	3
Constant-Expansion Suffices for Compressed Sensing with Generative Priors	❌	❌	❌	❌	❌	❌	❌	0
Constrained episodic reinforcement learning in concave-convex and knapsack settings	❌	✅	✅	❌	❌	❌	✅	3
Constraining Variational Inference with Geometric Jensen-Shannon Divergence	❌	✅	✅	❌	❌	❌	✅	3
Content Provider Dynamics and Coordination in Recommendation Ecosystems	✅	❌	❌	❌	❌	❌	❌	1
Contextual Games: Multi-Agent Learning with Side Information	✅	❌	✅	❌	❌	❌	✅	3
Contextual Reserve Price Optimization in Auctions via Mixed Integer Programming	❌	✅	✅	✅	❌	✅	✅	5
Continual Deep Learning by Functional Regularisation of Memorable Past	✅	✅	✅	❌	❌	❌	✅	4
Continual Learning in Low-rank Orthogonal Subspaces	✅	✅	✅	❌	❌	❌	✅	4
Continual Learning of Control Primitives : Skill Discovery via Reset-Games	✅	✅	✅	❌	❌	❌	❌	3
Continual Learning of a Mixed Sequence of Similar and Dissimilar Tasks	❌	✅	✅	✅	❌	❌	✅	4
Continual Learning with Node-Importance based Adaptive Group Sparse Regularization	✅	❌	✅	❌	❌	❌	✅	3
Continuous Meta-Learning without Tasks	✅	✅	✅	❌	❌	❌	❌	3
Continuous Object Representation Networks: Novel View Synthesis without Target View Supervision	❌	✅	✅	❌	❌	❌	❌	2
Continuous Regularized Wasserstein Barycenters	✅	✅	✅	❌	✅	✅	✅	6
Continuous Submodular Maximization: Beyond DR-Submodularity	✅	❌	❌	❌	❌	❌	❌	1
Continuous Surface Embeddings	❌	❌	✅	✅	❌	❌	✅	3
ContraGAN: Contrastive Learning for Conditional Image Generation	✅	✅	✅	✅	❌	❌	✅	5
Contrastive Learning with Adversarial Examples	✅	❌	✅	❌	❌	❌	✅	3
Contrastive learning of global and local features for medical image segmentation with limited annotations	❌	✅	✅	✅	❌	❌	✅	4
ConvBERT: Improving BERT with Span-based Dynamic Convolution	❌	✅	✅	✅	❌	❌	✅	4
Convergence and Stability of Graph Convolutional Networks on Large Random Graphs	❌	✅	❌	❌	❌	❌	❌	1
Convergence of Meta-Learning with Task-Specific Adaptation over Partial Parameters	✅	❌	✅	❌	❌	❌	✅	3
Convex optimization based on global lower second-order models	✅	✅	✅	❌	✅	❌	❌	4
Convolutional Generation of Textured 3D Meshes	❌	✅	✅	❌	✅	❌	✅	4
Convolutional Tensor-Train LSTM for Spatio-Temporal Learning	✅	✅	✅	❌	❌	❌	✅	4
Cooperative Heterogeneous Deep Reinforcement Learning	✅	❌	✅	❌	❌	❌	✅	3
Cooperative Multi-player Bandit Optimization	✅	❌	❌	❌	❌	❌	✅	2
Coresets for Near-Convex Functions	✅	✅	✅	❌	✅	✅	✅	6
Coresets for Regressions with Panel Data	✅	✅	❌	❌	✅	❌	✅	4
Coresets for Robust Training of Deep Neural Networks against Noisy Labels	✅	✅	✅	❌	✅	❌	✅	5
Coresets via Bilevel Optimization for Continual Learning and Streaming	✅	✅	✅	❌	✅	❌	✅	5
Correlation Robust Influence Maximization	❌	✅	✅	❌	✅	❌	❌	3
Correspondence learning via linearly-invariant embedding	❌	✅	✅	❌	❌	❌	✅	3
Counterexample-Guided Learning of Monotonic Neural Networks	❌	✅	✅	❌	❌	❌	✅	3
Counterfactual Contrastive Learning for Weakly-Supervised Vision-Language Grounding	❌	❌	✅	❌	❌	❌	✅	2
Counterfactual Data Augmentation using Locally Factored Dynamics	✅	✅	✅	❌	❌	❌	✅	4
Counterfactual Prediction for Bundle Treatment	❌	❌	✅	❌	❌	❌	✅	2
Counterfactual Predictions under Runtime Confounding	✅	❌	❌	✅	❌	❌	✅	3
Counterfactual Vision-and-Language Navigation: Unravelling the Unseen	✅	❌	✅	✅	❌	❌	✅	4
Coupling-based Invertible Neural Networks Are Universal Diffeomorphism Approximators	❌	❌	❌	❌	❌	❌	❌	0
Cream of the Crop: Distilling Prioritized Paths For One-Shot Neural Architecture Search	✅	✅	✅	✅	✅	❌	✅	6
Critic Regularized Regression	✅	❌	✅	❌	❌	❌	✅	3
Cross-Scale Internal Graph Neural Network for Image Super-Resolution	❌	✅	✅	❌	✅	❌	✅	4
Cross-lingual Retrieval for Iterative Self-Supervised Training	✅	✅	✅	✅	❌	❌	✅	5
Cross-validation Confidence Intervals for Test Error	❌	✅	✅	✅	❌	❌	✅	4
CrossTransformers: spatially-aware few-shot transfer	❌	✅	✅	✅	❌	❌	✅	4
Crush Optimism with Pessimism: Structured Bandits Beyond Asymptotic Optimality	✅	❌	❌	❌	❌	❌	❌	1
CryptoNAS: Private Inference on a ReLU Budget	✅	❌	✅	❌	✅	❌	✅	4
Curriculum By Smoothing	✅	❌	✅	❌	✅	❌	✅	4
Curriculum Learning by Dynamic Instance Hardness	✅	✅	✅	❌	❌	❌	✅	4
Curriculum learning for multilevel budgeted combinatorial problems	✅	✅	✅	❌	✅	✅	❌	5
Curvature Regularization to Prevent Distortion in Graph Embedding	✅	❌	✅	✅	❌	❌	✅	4
Cycle-Contrast for Self-Supervised Video Representation Learning	❌	❌	✅	✅	❌	❌	✅	3
DAGs with No Fears: A Closer Look at Continuous Optimization for Learning Bayesian Networks	✅	❌	❌	❌	❌	❌	❌	1
DISK: Learning local features with policy gradient	❌	✅	✅	✅	❌	❌	✅	4
DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of Ensembles	✅	✅	✅	❌	❌	❌	✅	4
Dark Experience for General Continual Learning: a Strong, Simple Baseline	✅	✅	✅	✅	✅	❌	✅	6
Data Diversification: A Simple Strategy For Neural Machine Translation	✅	✅	✅	✅	❌	❌	✅	5
De-Anonymizing Text by Fingerprinting Language Generation	✅	❌	✅	❌	✅	✅	✅	5
Debiased Contrastive Learning	✅	✅	✅	✅	❌	❌	✅	5
Debiasing Averaged Stochastic Gradient Descent to handle missing values	✅	✅	❌	❌	❌	❌	✅	3
Debiasing Distributed Second Order Optimization with Surrogate Sketching and Scaled Regularization	❌	❌	✅	❌	❌	❌	✅	2
Debugging Tests for Model Explanations	❌	✅	✅	❌	❌	❌	✅	3
Decentralized Accelerated Proximal Gradient Descent	✅	❌	❌	❌	❌	❌	✅	2
Decentralized Langevin Dynamics for Bayesian Learning	✅	❌	✅	❌	❌	❌	❌	2
Decentralized TD Tracking with Linear Function Approximation and its Finite-Time Analysis	✅	❌	❌	❌	❌	❌	✅	2
Decision trees as partitioning machines to characterize their generalization properties	✅	✅	✅	✅	❌	❌	✅	5
Decision-Making with Auto-Encoding Variational Bayes	❌	✅	✅	❌	✅	❌	✅	4
Decisions, Counterfactual Explanations and Strategic Behavior	✅	✅	✅	❌	❌	❌	✅	4
Deep Archimedean Copulas	❌	✅	✅	✅	✅	✅	✅	6
Deep Automodulators	❌	✅	✅	❌	❌	❌	✅	3
Deep Diffusion-Invariant Wasserstein Distributional Classification	✅	❌	✅	❌	✅	✅	✅	5
Deep Direct Likelihood Knockoffs	✅	❌	✅	✅	✅	❌	✅	5
Deep Energy-based Modeling of Discrete-Time Physics	✅	✅	✅	❌	❌	❌	✅	4
Deep Evidential Regression	❌	❌	✅	❌	✅	❌	✅	3
Deep Graph Pose: a semi-supervised deep graphical model for improved animal pose tracking	❌	✅	✅	❌	❌	❌	✅	3
Deep Imitation Learning for Bimanual Robotic Manipulation	❌	✅	❌	❌	❌	❌	✅	2
Deep Inverse Q-learning with Constraints	✅	❌	✅	❌	✅	❌	✅	4
Deep Metric Learning with Spherical Embedding	❌	❌	✅	✅	❌	❌	✅	3
Deep Multimodal Fusion by Channel Exchanging	❌	✅	✅	✅	❌	❌	✅	4
Deep Rao-Blackwellised Particle Filters for Time Series Forecasting	✅	❌	✅	❌	❌	❌	✅	3
Deep Reinforcement Learning with Stacked Hierarchical Attention for Text-based Games	❌	✅	✅	❌	❌	❌	✅	3
Deep Reinforcement and InfoMax Learning	✅	✅	✅	❌	❌	❌	✅	4
Deep Relational Topic Modeling via Graph Poisson Gamma Belief Network	✅	✅	✅	✅	❌	❌	✅	5
Deep Shells: Unsupervised Shape Correspondence with Optimal Transport	❌	❌	✅	❌	❌	❌	✅	2
Deep Smoothing of the Implied Volatility Surface	❌	❌	❌	✅	❌	❌	✅	2
Deep Statistical Solvers	❌	✅	✅	✅	✅	✅	✅	6
Deep Structural Causal Models for Tractable Counterfactual Inference	❌	✅	✅	✅	✅	✅	✅	6
Deep Subspace Clustering with Data Augmentation	❌	✅	✅	❌	❌	❌	✅	3
Deep Transformation-Invariant Clustering	✅	✅	✅	❌	✅	❌	✅	5
Deep Transformers with Latent Depth	✅	❌	✅	✅	❌	❌	✅	4
Deep Variational Instance Segmentation	❌	✅	✅	✅	✅	❌	✅	5
Deep Wiener Deconvolution: Wiener Meets Deep Learning for Image Deblurring	❌	✅	✅	❌	❌	❌	✅	3
Deep active inference agents using Monte-Carlo methods	❌	✅	✅	❌	❌	❌	❌	2
Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel	❌	❌	✅	❌	❌	✅	✅	3
Deep reconstruction of strange attractors from time series	❌	✅	✅	✅	❌	❌	✅	4
DeepI2I: Enabling Deep Hierarchical Image-to-Image Translation by Transferring from GANs	❌	✅	✅	❌	❌	❌	✅	3
DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation	❌	✅	✅	❌	✅	❌	✅	4
Deeply Learned Spectral Total Variation Decomposition	❌	✅	✅	❌	✅	❌	✅	4
Delay and Cooperation in Nonstochastic Linear Bandits	✅	❌	❌	❌	❌	❌	❌	1
Delta-STN: Efficient Bilevel Optimization for Neural Networks using Structured Response Jacobians	✅	❌	✅	❌	❌	❌	✅	3
Delving into the Cyclic Mechanism in Semi-supervised Video Object Segmentation	❌	❌	✅	✅	✅	❌	✅	4
Demixed shared component analysis of neural population data from multiple brain areas	❌	✅	✅	❌	❌	❌	❌	2
Demystifying Contrastive Self-Supervised Learning: Invariances, Augmentations and Dataset Biases	❌	❌	✅	❌	❌	❌	❌	1
Demystifying Orthogonal Monte Carlo and Beyond	✅	✅	❌	❌	❌	❌	❌	2
Denoised Smoothing: A Provable Defense for Pretrained Classifiers	❌	✅	✅	✅	❌	❌	✅	4
Denoising Diffusion Probabilistic Models	✅	✅	✅	❌	❌	❌	✅	4
Dense Correspondences between Human Bodies via Learning Transformation Synchronization on Graphs	❌	✅	✅	✅	❌	❌	✅	4
Depth Uncertainty in Neural Networks	❌	✅	✅	✅	✅	❌	✅	5
Design Space for Graph Neural Networks	❌	✅	✅	✅	❌	❌	✅	4
Detecting Hands and Recognizing Physical Contact in the Wild	❌	✅	✅	✅	❌	❌	✅	4
Detecting Interactions from Neural Networks via Topological Analysis	✅	❌	✅	✅	❌	❌	✅	4
Detection as Regression: Certified Object Detection with Median Smoothing	✅	❌	✅	❌	❌	❌	✅	3
Deterministic Approximation for Submodular Maximization over a Matroid in Nearly Linear Time	✅	❌	✅	❌	❌	❌	✅	3
Dialog without Dialog Data: Learning Visual Dialog Agents from VQA Data	✅	✅	✅	✅	❌	❌	✅	5
DiffGCN: Graph Convolutional Networks via Differential Operators and Algebraic Multigrid Pooling	❌	❌	✅	✅	✅	❌	✅	4
Differentiable Augmentation for Data-Efficient GAN Training	❌	✅	✅	✅	✅	❌	✅	5
Differentiable Causal Discovery from Interventional Data	❌	✅	✅	❌	❌	❌	✅	3
Differentiable Expected Hypervolume Improvement for Parallel Multi-Objective Bayesian Optimization	❌	✅	✅	❌	✅	❌	✅	4
Differentiable Meta-Learning of Bandit Policies	✅	❌	❌	❌	✅	❌	✅	3
Differentiable Neural Architecture Search in Equivalent Space with Exploration Enhancement	✅	❌	✅	✅	❌	❌	✅	4
Differentiable Top-k with Optimal Transport	✅	✅	✅	❌	❌	❌	✅	4
Differentially Private Clustering: Tight Approximation Ratios	✅	❌	❌	❌	❌	❌	❌	1
Differentially-Private Federated Linear Bandits	✅	❌	❌	❌	❌	❌	✅	2
Digraph Inception Convolutional Networks	❌	✅	✅	✅	✅	❌	✅	5
Direct Feedback Alignment Scales to Modern Deep Learning Tasks and Architectures	❌	✅	✅	❌	❌	❌	✅	3
Direct Policy Gradients: Direct Optimization of Policies in Discrete Action Spaces	✅	❌	✅	❌	❌	❌	✅	3
Directional Pruning of Deep Neural Networks	✅	✅	✅	❌	❌	❌	✅	4
Directional convergence and alignment in deep learning	❌	❌	✅	❌	❌	❌	✅	2
Dirichlet Graph Variational Autoencoder	❌	❌	✅	❌	❌	❌	✅	2
DisARM: An Antithetic Gradient Estimator for Binary Latent Variables	✅	✅	✅	✅	✅	❌	✅	6
DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction	✅	❌	✅	✅	❌	❌	✅	4
Discover, Hallucinate, and Adapt: Open Compound Domain Adaptation for Semantic Segmentation	❌	❌	✅	❌	❌	❌	✅	2
Discovering Reinforcement Learning Algorithms	✅	❌	❌	❌	❌	❌	✅	2
Discovering Symbolic Models from Deep Learning with Inductive Biases	❌	✅	✅	❌	❌	❌	✅	3
Discovering conflicting groups in signed networks	✅	✅	✅	❌	✅	❌	❌	4
Discriminative Sounding Objects Localization via Self-supervised Audiovisual Matching	❌	✅	✅	❌	❌	❌	✅	3
Disentangling Human Error from Ground Truth in Segmentation of Medical Images	❌	✅	✅	✅	❌	❌	❌	3
Disentangling by Subspace Diffusion	✅	❌	✅	❌	❌	❌	✅	3
Displacement-Invariant Matching Cost Learning for Accurate Optical Flow Estimation	❌	✅	✅	✅	✅	❌	✅	5
Dissecting Neural ODEs	❌	✅	✅	❌	❌	✅	❌	3
Distance Encoding: Design Provably More Powerful Neural Networks for Graph Representation Learning	✅	✅	✅	✅	❌	❌	❌	4
Distributed Distillation for On-Device Learning	✅	❌	✅	❌	❌	❌	✅	3
Distributed Newton Can Communicate Less and Resist Byzantine Workers	✅	❌	✅	❌	❌	❌	✅	3
Distributed Training with Heterogeneous Data: Bridging Median- and Mean-Based Algorithms	✅	❌	✅	❌	❌	❌	✅	3
Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning	✅	❌	✅	❌	❌	❌	✅	3
Distribution Matching for Crowd Counting	❌	✅	✅	❌	❌	❌	✅	3
Distribution-free binary classification: prediction sets, confidence intervals and calibration	❌	❌	❌	❌	❌	❌	❌	0
Distributional Robustness with IPMs and links to Regularization and GANs	❌	❌	❌	❌	❌	❌	❌	0
Distributionally Robust Federated Averaging	✅	✅	✅	❌	✅	❌	✅	5
Distributionally Robust Local Non-parametric Conditional Estimation	❌	✅	✅	✅	❌	❌	✅	4
Distributionally Robust Parametric Maximum Likelihood Estimation	❌	✅	✅	✅	✅	✅	✅	6
Diverse Image Captioning with Context-Object Split Latent Spaces	❌	✅	✅	✅	❌	❌	❌	3
Diversity can be Transferred: Output Diversification for White- and Black-box Attacks	✅	❌	✅	❌	❌	❌	✅	3
Diversity-Guided Multi-Objective Bayesian Optimization With Batch Evaluations	✅	✅	✅	❌	❌	❌	✅	4
Do Adversarially Robust ImageNet Models Transfer Better?	❌	✅	✅	❌	❌	❌	✅	3
Does Unsupervised Architecture Representation Learning Help Neural Architecture Search?	❌	✅	✅	✅	❌	❌	✅	4
Domain Adaptation as a Problem of Inference on Graphical Models	❌	✅	✅	❌	❌	❌	✅	3
Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift	✅	✅	✅	❌	❌	❌	✅	4
Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization	❌	✅	✅	✅	❌	❌	❌	3
Domain Generalization via Entropy Regularization	✅	✅	✅	✅	❌	❌	✅	5
Doubly Robust Off-Policy Value and Gradient Estimation for Deterministic Policies	✅	❌	❌	❌	❌	❌	✅	2
Dual Instrumental Variable Regression	✅	✅	✅	✅	❌	❌	✅	5
Dual Manifold Adversarial Robustness: Defense against Lp and non-Lp Adversarial Attacks	❌	❌	✅	❌	❌	❌	✅	2
Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learning	✅	❌	✅	✅	❌	❌	✅	4
Dual-Free Stochastic Decentralized Optimization with Variance Reduction	✅	✅	✅	❌	❌	❌	✅	4
Dual-Resolution Correspondence Networks	❌	✅	✅	✅	❌	❌	✅	4
Duality-Induced Regularizer for Tensor Factorization Based Knowledge Graph Completion	❌	✅	✅	✅	❌	❌	✅	4
DynaBERT: Dynamic BERT with Adaptive Width and Depth	✅	✅	✅	✅	✅	❌	✅	6
Dynamic Fusion of Eye Movement Data and Verbal Narrations in Knowledge-rich Domains	✅	❌	✅	❌	❌	✅	❌	3
Dynamic Regret of Convex and Smooth Functions	✅	❌	❌	❌	❌	❌	❌	1
Dynamic Regret of Policy Optimization in Non-Stationary Environments	✅	❌	❌	❌	❌	❌	❌	1
Dynamic Submodular Maximization	✅	❌	❌	❌	❌	❌	❌	1
Dynamic allocation of limited memory resources in reinforcement learning	✅	✅	✅	❌	❌	❌	✅	4
Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification	❌	❌	❌	❌	❌	❌	✅	1
Early-Learning Regularization Prevents Memorization of Noisy Labels	❌	✅	✅	✅	❌	❌	✅	4
EcoLight: Intersection Control in Developing Regions Under Extreme Budget and Network Constraints	✅	❌	✅	❌	✅	❌	✅	4
Effective Dimension Adaptive Sketching Methods for Faster Regularized Least-Squares Optimization	✅	✅	✅	❌	❌	❌	✅	4
Effective Diversity in Population Based Reinforcement Learning	❌	✅	✅	❌	✅	❌	✅	4
Efficient Algorithms for Device Placement of DNN Graph Operators	❌	✅	❌	❌	✅	❌	✅	3
Efficient Clustering Based On A Unified View Of $K$-means And Ratio-cut	✅	✅	✅	❌	✅	❌	✅	5
Efficient Clustering for Stretched Mixtures: Landscape and Optimality	✅	❌	✅	❌	❌	❌	✅	3
Efficient Contextual Bandits with Continuous Actions	✅	❌	✅	❌	❌	❌	✅	3
Efficient Distance Approximation for Structured High-Dimensional Distributions via Learning	✅	❌	❌	❌	❌	❌	❌	1
Efficient Exact Verification of Binarized Neural Networks	❌	✅	✅	✅	❌	❌	✅	4
Efficient Exploration of Reward Functions in Inverse Reinforcement Learning via Bayesian Optimization	✅	❌	✅	❌	❌	❌	❌	2
Efficient Generation of Structured Objects with Constrained Adversarial Networks	❌	✅	✅	❌	✅	❌	✅	4
Efficient Learning of Discrete Graphical Models	✅	❌	❌	❌	❌	❌	✅	2
Efficient Learning of Generative Models via Finite-Difference Score Matching	✅	✅	✅	❌	❌	❌	✅	4
Efficient Low Rank Gaussian Variational Inference for Neural Networks	❌	✅	✅	❌	❌	❌	✅	3
Efficient Marginalization of Discrete and Structured Latent Variables via Sparsity	❌	✅	✅	❌	❌	❌	✅	3
Efficient Model-Based Reinforcement Learning through Optimistic Policy Search and Planning	✅	✅	❌	❌	❌	❌	✅	3
Efficient Nonmyopic Bayesian Optimization via One-Shot Multi-Step Trees	✅	✅	❌	❌	❌	❌	✅	3
Efficient Online Learning of Optimal Rankings: Dimensionality Reduction via Gradient Descent	✅	✅	❌	❌	❌	❌	✅	3
Efficient Planning in Large MDPs with Weak Linear Function Approximation	✅	❌	❌	❌	❌	❌	❌	1
Efficient Projection-free Algorithms for Saddle Point Problems	✅	❌	✅	❌	❌	❌	✅	3
Efficient Variational Inference for Sparse Deep Learning with Theoretical Guarantee	✅	❌	✅	❌	❌	❌	✅	3
Efficient active learning of sparse halfspaces with arbitrary bounded noise	✅	❌	❌	❌	❌	❌	❌	1
Efficient estimation of neural tuning during naturalistic behavior	❌	✅	✅	❌	❌	❌	✅	3
Efficient semidefinite-programming-based inference for binary and multi-class MRFs	✅	✅	❌	❌	❌	❌	✅	3
Elastic-InfoGAN: Unsupervised Disentangled Representation Learning in Class-Imbalanced Data	❌	✅	✅	✅	❌	❌	❌	3
Election Coding for Distributed Learning: Protecting SignSGD against Byzantine Attacks	✅	❌	✅	❌	✅	❌	✅	4
Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design	✅	✅	✅	❌	❌	❌	✅	4
Emergent Reciprocity and Team Formation from Randomized Uncertain Social Preferences	❌	✅	❌	❌	❌	❌	✅	2
Empirical Likelihood for Contextual Bandits	❌	✅	✅	✅	❌	❌	✅	4
Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming	✅	✅	✅	❌	✅	❌	✅	5
End-to-End Learning and Intervention in Games	❌	❌	❌	❌	❌	❌	✅	1
Energy-based Out-of-distribution Detection	❌	✅	✅	✅	✅	❌	✅	5
Ensemble Distillation for Robust Model Fusion in Federated Learning	✅	❌	✅	✅	❌	❌	✅	4
Ensembling geophysical models with Bayesian Neural Networks	✅	✅	✅	✅	❌	❌	❌	4
Ensuring Fairness Beyond the Training Data	✅	✅	✅	✅	❌	❌	✅	5
Entropic Causal Inference: Identifiability and Finite Sample Results	❌	❌	✅	❌	❌	❌	❌	1
Entropic Optimal Transport between Unbalanced Gaussian Measures has a Closed Form	❌	❌	❌	❌	❌	❌	✅	1
Entrywise convergence of iterative methods for eigenproblems	✅	❌	✅	❌	❌	❌	❌	2
Equivariant Networks for Hierarchical Structures	❌	✅	✅	❌	❌	❌	✅	3
Erdos Goes Neural: an Unsupervised Learning Framework for Combinatorial Optimization on Graphs	❌	✅	✅	✅	❌	✅	❌	4
Error Bounds of Imitating Policies and Environments	✅	❌	✅	❌	❌	❌	✅	3
Escaping Saddle-Point Faster under Interpolation-like Conditions	✅	❌	❌	❌	❌	❌	❌	1
Escaping the Gravitational Pull of Softmax	❌	❌	✅	✅	❌	❌	✅	3
Estimating Fluctuations in Neural Representations of Uncertain Environments	❌	❌	❌	❌	❌	❌	❌	0
Estimating Rank-One Spikes from Heavy-Tailed Noise via Self-Avoiding Walks	✅	❌	❌	❌	❌	❌	❌	1
Estimating Training Data Influence by Tracing Gradient Descent	❌	✅	✅	❌	❌	❌	✅	3
Estimating decision tree learnability with polylogarithmic sample complexity	✅	❌	❌	❌	❌	❌	❌	1
Estimating the Effects of Continuous-valued Interventions using Generative Adversarial Networks	✅	✅	✅	❌	❌	❌	❌	3
Estimating weighted areas under the ROC curve	❌	❌	❌	❌	❌	❌	❌	0
Estimation and Imputation in Probabilistic Principal Component Analysis with Missing Not At Random Data	✅	✅	✅	❌	❌	❌	❌	3
Estimation of Skill Distribution from a Tournament	✅	❌	✅	❌	❌	❌	✅	3
Evaluating Attribution for Graph Neural Networks	❌	✅	✅	❌	❌	❌	✅	3
Evaluating and Rewarding Teamwork Using Cooperative Game Abstractions	❌	❌	✅	✅	❌	❌	✅	3
Every View Counts: Cross-View Consistency in 3D Object Detection with Hybrid-Cylindrical-Spherical Voxelization	❌	❌	✅	✅	✅	❌	✅	4
Evidential Sparsification of Multimodal Latent Spaces in Conditional Variational Autoencoders	❌	✅	✅	❌	✅	❌	✅	4
EvolveGraph: Multi-Agent Trajectory Prediction with Dynamic Relational Reasoning	❌	❌	✅	❌	❌	❌	❌	1
Evolving Graphical Planner: Contextual Global Planning for Vision-and-Language Navigation	❌	✅	✅	✅	❌	❌	✅	4
Evolving Normalization-Activation Layers	✅	✅	✅	✅	❌	❌	✅	5
Exact Recovery of Mangled Clusters with Same-Cluster Queries	✅	❌	❌	❌	❌	❌	✅	2
Exact expressions for double descent and implicit regularization via surrogate random design	❌	❌	❌	❌	❌	❌	✅	1
Exactly Computing the Local Lipschitz Constant of ReLU Networks	❌	❌	✅	❌	❌	❌	❌	1
Exchangeable Neural ODE for Set Modeling	❌	✅	✅	❌	✅	❌	❌	3
Exemplar Guided Active Learning	✅	❌	❌	❌	❌	❌	❌	1
Exemplar VAE: Linking Generative Models, Nearest Neighbor Retrieval, and Data Augmentation	❌	✅	✅	✅	❌	❌	✅	4
ExpandNets: Linear Over-parameterization to Train Compact Convolutional Networks	❌	✅	✅	✅	✅	❌	✅	5
Experimental design for MRI by greedy policy search	❌	✅	✅	✅	❌	❌	✅	4
Expert-Supervised Reinforcement Learning for Offline Policy Learning and Evaluation	✅	✅	✅	✅	❌	❌	✅	5
Explainable Voting	❌	❌	❌	❌	❌	❌	❌	0
Explaining Naive Bayes and Other Linear Classifiers with Polynomial Time and Delay	✅	✅	✅	❌	✅	❌	❌	4
Explicit Regularisation in Gaussian Noise Injections	❌	❌	✅	❌	❌	❌	✅	2
Exploiting Higher Order Smoothness in Derivative-free Optimization and Continuous Bandits	✅	❌	❌	❌	❌	❌	❌	1
Exploiting MMD and Sinkhorn Divergences for Fair and Transferable Representation Learning	❌	❌	✅	✅	❌	❌	✅	3
Exploiting the Surrogate Gap in Online Multiclass Classification	✅	❌	❌	❌	❌	❌	❌	1
Exploiting weakly supervised visual patterns to learn from partial annotations	❌	❌	✅	✅	✅	❌	✅	4
Explore Aggressively, Update Conservatively: Stochastic Extragradient Methods with Variable Stepsize Scaling	❌	❌	❌	❌	❌	❌	❌	0
Exponential ergodicity of mirror-Langevin diffusions	✅	❌	❌	❌	❌	❌	✅	2
Extrapolation Towards Imaginary 0-Nearest Neighbour and Its Improved Convergence Rate	❌	❌	✅	✅	❌	❌	✅	3
FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs	✅	❌	❌	❌	❌	❌	❌	1
Factor Graph Grammars	❌	❌	❌	❌	❌	❌	❌	0
Factor Graph Neural Networks	✅	❌	✅	✅	❌	❌	✅	4
Factorizable Graph Convolutional Networks	❌	✅	✅	✅	❌	❌	✅	4
Factorized Neural Processes for Neural Processes: K-Shot Prediction of Neural Responses	❌	✅	✅	✅	✅	❌	❌	4
Fair Hierarchical Clustering	✅	✅	✅	❌	❌	❌	✅	4
Fair Multiple Decision Making Through Soft Interventions	❌	✅	✅	✅	✅	❌	✅	5
Fair Performance Metric Elicitation	✅	❌	❌	❌	❌	❌	✅	2
Fair regression via plug-in estimator and recalibration with statistical guarantees	✅	✅	✅	✅	❌	❌	✅	5
Fair regression with Wasserstein barycenters	✅	✅	✅	✅	❌	❌	✅	5
Fairness constraints can help exact inference in structured prediction	❌	❌	❌	❌	❌	❌	❌	0
Fairness in Streaming Submodular Maximization: Algorithms and Hardness	✅	✅	✅	❌	❌	❌	❌	3
Fairness with Overlapping Groups; a Probabilistic Perspective	✅	✅	✅	❌	❌	❌	❌	3
Fairness without Demographics through Adversarially Reweighted Learning	❌	❌	✅	✅	❌	❌	✅	3
Faithful Embeddings for Knowledge Base Queries	❌	✅	✅	✅	❌	❌	✅	4
Falcon: Fast Spectral Inference on Encrypted Data	✅	❌	✅	❌	✅	✅	✅	5
Fast Adaptive Non-Monotone Submodular Maximization Subject to a Knapsack Constraint	✅	❌	✅	❌	❌	❌	✅	3
Fast Adversarial Robustness Certification of Nearest Prototype Classifiers for Arbitrary Seminorms	❌	✅	✅	❌	❌	❌	✅	3
Fast Convergence of Langevin Dynamics on Manifold: Geodesics meet Log-Sobolev	❌	❌	❌	❌	❌	❌	❌	0
Fast Epigraphical Projection-based Incremental Algorithms for Wasserstein Distributionally Robust Support Vector Machine	❌	✅	✅	❌	✅	✅	❌	4
Fast Fourier Convolution	✅	❌	✅	✅	❌	❌	✅	4
Fast Matrix Square Roots with Applications to Gaussian Processes and Bayesian Optimization	✅	✅	✅	❌	✅	❌	✅	5
Fast Transformers with Clustered Attention	❌	✅	✅	❌	✅	❌	✅	4
Fast Unbalanced Optimal Transport on a Tree	✅	✅	✅	✅	✅	❌	✅	6
Fast and Accurate $k$-means++ via Rejection Sampling	✅	❌	✅	❌	❌	❌	❌	2
Fast and Flexible Temporal Point Processes with Triangular Maps	❌	✅	✅	✅	✅	❌	✅	5
Fast geometric learning with symbolic matrices	✅	✅	✅	❌	✅	❌	✅	5
Fast, Accurate, and Simple Models for Tabular Data via Augmented Distillation	❌	❌	✅	✅	❌	❌	❌	2
Faster DBSCAN via subsampled similarity queries	✅	❌	✅	❌	❌	❌	✅	3
Faster Differentially Private Samplers via Rényi Divergence Analysis of Discretized Langevin MCMC	❌	❌	❌	❌	❌	❌	❌	0
Faster Randomized Infeasible Interior Point Methods for Tall/Wide Linear Programs	✅	❌	✅	❌	✅	❌	✅	4
Faster Wasserstein Distance Estimation with the Sinkhorn Divergence	❌	✅	❌	❌	❌	❌	✅	2
Feature Importance Ranking for Deep Learning	✅	✅	✅	✅	❌	❌	❌	4
Feature Shift Detection: Localizing Which Features Have Shifted via Conditional Distribution Tests	❌	✅	✅	❌	❌	❌	✅	3
FedSplit: an algorithmic framework for fast federated optimization	✅	❌	✅	❌	❌	❌	✅	3
Federated Accelerated Stochastic Gradient Descent	✅	✅	✅	❌	❌	❌	✅	4
Federated Bayesian Optimization via Thompson Sampling	✅	❌	✅	❌	❌	❌	✅	3
Federated Principal Component Analysis	✅	✅	✅	❌	✅	✅	✅	6
Few-Cost Salient Object Detection with Adversarial-Paced Learning	❌	✅	✅	❌	✅	❌	✅	4
Few-shot Image Generation with Elastic Weight Consolidation	❌	❌	✅	❌	❌	❌	❌	1
Few-shot Visual Reasoning with Meta-Analogical Contrastive Learning	❌	❌	✅	✅	✅	❌	✅	4
Fewer is More: A Deep Graph Metric Learning Perspective Using Fewer Proxies	❌	✅	✅	❌	✅	❌	✅	4
Fictitious Play for Mean Field Games: Continuous Time Analysis and Applications	✅	❌	❌	❌	❌	❌	✅	2
Field-wise Learning for Multi-field Categorical Data	❌	✅	✅	✅	✅	❌	✅	5
Fighting Copycat Agents in Behavioral Cloning from Observation Histories	✅	❌	✅	❌	❌	❌	✅	3
Finding All $\epsilon$-Good Arms in Stochastic Bandits	✅	✅	❌	❌	❌	❌	✅	3
Finding Second-Order Stationary Points Efficiently in Smooth Nonconvex Linearly Constrained Optimization Problems	✅	❌	❌	❌	❌	❌	✅	2
Finding the Homology of Decision Boundaries with Active Learning	❌	✅	✅	❌	❌	❌	❌	2
Fine-Grained Dynamic Head for Object Detection	❌	✅	✅	✅	❌	❌	✅	4
Finer Metagenomic Reconstruction via Biodiversity Optimization	❌	✅	✅	❌	❌	✅	✅	4
Finite Continuum-Armed Bandits	✅	❌	❌	❌	❌	❌	❌	1
Finite Versus Infinite Neural Networks: an Empirical Study	❌	❌	✅	❌	❌	❌	✅	2
Finite-Sample Analysis of Contractive Stochastic Approximation Using Smooth Convex Envelopes	❌	❌	❌	❌	❌	❌	❌	0
Finite-Time Analysis for Double Q-learning	✅	❌	❌	❌	❌	❌	❌	1
Finite-Time Analysis of Round-Robin Kullback-Leibler Upper Confidence Bounds for Optimal Adaptive Allocation with Multiple Plays and Markovian Rewards	✅	❌	❌	❌	✅	❌	✅	3
Firefly Neural Architecture Descent: a General Approach for Growing Neural Networks	✅	❌	✅	✅	❌	❌	✅	4
First Order Constrained Optimization in Policy Space	✅	❌	✅	❌	❌	❌	✅	3
First-Order Methods for Large-Scale Market Equilibrium Computation	✅	✅	❌	❌	❌	❌	✅	3
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence	✅	✅	✅	✅	❌	❌	✅	5
Fixed-Support Wasserstein Barycenters: Computational Hardness and Fast Algorithm	✅	❌	✅	❌	❌	❌	✅	3
FleXOR: Trainable Fractional Quantization	✅	❌	✅	❌	❌	❌	✅	3
Flexible mean field variational inference using mixtures of non-overlapping exponential families	❌	✅	❌	❌	✅	❌	✅	3
Flows for simultaneous manifold learning and density estimation	❌	✅	✅	❌	❌	✅	✅	4
Focus of Attention Improves Information Transfer in Visual Features	❌	✅	❌	❌	❌	❌	✅	2
Follow the Perturbed Leader: Optimism and Fast Parallel Algorithms for Smooth Minimax Games	✅	❌	❌	❌	❌	❌	❌	1
Forethought and Hindsight in Credit Assignment	✅	❌	❌	❌	❌	❌	❌	1
Forget About the LiDAR: Self-Supervised Depth Estimators with MED Probability Volumes	❌	❌	✅	❌	✅	❌	✅	3
Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains	❌	❌	✅	❌	❌	❌	✅	2
Fourier Sparse Leverage Scores and Approximate Kernel Learning	❌	❌	✅	✅	❌	❌	❌	2
Fourier Spectrum Discrepancies in Deep Network Generated Images	❌	❌	✅	✅	❌	❌	✅	3
Fourier-transform-based attribution priors improve the interpretability and stability of deep learning models for genomics	❌	❌	✅	✅	❌	❌	✅	3
FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training	✅	✅	✅	✅	✅	❌	✅	6
From Boltzmann Machines to Neural Networks and Back Again	✅	❌	✅	❌	✅	❌	✅	4
From Finite to Countable-Armed Bandits	✅	❌	❌	❌	❌	❌	✅	2
From Predictions to Decisions: Using Lookahead Regularization	❌	✅	✅	❌	❌	❌	✅	3
From Trees to Continuous Embeddings and Back: Hyperbolic Hierarchical Clustering	✅	✅	✅	✅	✅	❌	✅	6
FrugalML: How to use ML Prediction APIs more accurately and cheaply	✅	✅	✅	❌	❌	❌	❌	3
Fully Convolutional Mesh Autoencoder using Efficient Spatially Varying Kernels	❌	❌	✅	✅	❌	❌	✅	3
Fully Dynamic Algorithm for Constrained Submodular Optimization	✅	✅	✅	❌	❌	❌	❌	3
Functional Regularization for Representation Learning: A Unified Theoretical Perspective	❌	❌	❌	❌	❌	❌	✅	1
Funnel-Transformer: Filtering out Sequential Redundancy for Efficient Language Processing	❌	✅	✅	✅	❌	❌	✅	4
Further Analysis of Outlier Detection with Deep Generative Models	❌	✅	✅	❌	❌	❌	❌	2
GAIT-prop: A biologically plausible learning rule derived from backpropagation of error	✅	✅	✅	❌	❌	❌	❌	3
GAN Memory with No Forgetting	❌	✅	✅	❌	✅	❌	❌	3
GANSpace: Discovering Interpretable GAN Controls	❌	✅	✅	❌	❌	❌	❌	2
GCN meets GPU: Decoupling “When to Sample” from “How to Sample”	✅	❌	✅	✅	✅	❌	✅	5
GCOMB: Learning Budget-constrained Combinatorial Algorithms over Billion-sized Graphs	✅	✅	✅	✅	✅	✅	✅	7
GNNGuard: Defending Graph Neural Networks against Adversarial Attacks	✅	✅	✅	❌	❌	❌	✅	4
GOCor: Bringing Globally Optimized Correspondence Volumes into Your Neural Network	❌	✅	✅	❌	✅	❌	✅	4
GPS-Net: Graph-based Photometric Stereo Network	❌	❌	✅	✅	✅	❌	✅	4
GPU-Accelerated Primal Learning for Extremely Fast Large-Scale Classification	✅	❌	✅	✅	✅	✅	✅	6
GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis	❌	✅	✅	❌	❌	❌	✅	3
GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators	❌	❌	✅	❌	❌	❌	✅	2
Gamma-Models: Generative Temporal Difference Learning for Infinite-Horizon Prediction	✅	❌	✅	❌	❌	✅	✅	4
Gaussian Gated Linear Networks	✅	✅	✅	✅	❌	❌	✅	5
Gaussian Process Bandit Optimization of the Thermodynamic Variational Objective	✅	✅	✅	❌	❌	❌	✅	4
General Control Functions for Causal Effect Estimation from IVs	❌	❌	✅	✅	❌	❌	✅	3
General Transportability of Soft Interventions: Completeness Results	✅	❌	❌	❌	❌	❌	❌	1
Generalised Bayesian Filtering via Sequential Monte Carlo	✅	✅	❌	❌	❌	❌	❌	2
Generalization Bound of Gradient Descent for Non-Convex Metric Learning	❌	✅	✅	✅	❌	❌	✅	4
Generalization bound of globally optimal non-convex neural network training: Transportation map estimation by infinite dimensional Langevin dynamics	❌	❌	❌	❌	❌	❌	❌	0
Generalization error in high-dimensional perceptrons: Approaching Bayes error with convex optimization	❌	❌	❌	❌	❌	❌	❌	0
Generalized Boosting	✅	❌	✅	✅	❌	❌	✅	4
Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection	❌	❌	✅	✅	✅	✅	✅	5
Generalized Hindsight for Reinforcement Learning	✅	❌	✅	❌	❌	❌	✅	3
Generalized Independent Noise Condition for Estimating Latent Variable Causal Graphs	✅	✅	✅	❌	❌	❌	✅	4
Generalized Leverage Score Sampling for Neural Networks	❌	❌	❌	❌	❌	❌	❌	0
Generating Adjacency-Constrained Subgoals in Hierarchical Reinforcement Learning	❌	✅	✅	❌	❌	❌	✅	3
Generating Correct Answers for Progressive Matrices Intelligence Tests	❌	❌	✅	❌	❌	❌	✅	2
Generative 3D Part Assembly via Dynamic Graph Learning	❌	❌	✅	✅	❌	❌	✅	3
Generative Neurosymbolic Machines	❌	❌	✅	❌	❌	❌	✅	2
Generative View Synthesis: From Single-view Semantics to Novel-view Images	❌	✅	✅	❌	✅	❌	✅	4
Generative causal explanations of black-box classifiers	✅	✅	✅	✅	❌	❌	✅	5
Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstruction	❌	❌	✅	❌	✅	❌	✅	3
Geometric All-way Boolean Tensor Decomposition	✅	✅	✅	❌	❌	❌	✅	4
Geometric Dataset Distances via Optimal Transport	❌	❌	✅	❌	❌	❌	✅	2
Geometric Exploration for Online Control	✅	❌	❌	❌	❌	❌	❌	1
Gibbs Sampling with People	❌	✅	✅	❌	❌	❌	✅	3
Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification	❌	✅	✅	✅	✅	❌	❌	4
Global Convergence and Variance Reduction for a Class of Nonconvex-Nonconcave Minimax Problems	✅	❌	✅	❌	❌	❌	✅	3
Global Convergence of Deep Networks with One Wide Layer Followed by Pyramidal Topology	❌	❌	❌	❌	❌	❌	❌	0
Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search	✅	✅	✅	✅	✅	❌	✅	6
Glyph: Fast and Accurately Training Deep Neural Networks on Encrypted Data	❌	❌	✅	❌	✅	❌	✅	3
Goal-directed Generation of Discrete Structures with Conditional Generative Models	✅	❌	✅	✅	❌	❌	✅	4
GradAug: A New Regularization Method for Deep Neural Networks	✅	✅	✅	✅	✅	❌	✅	6
Gradient Boosted Normalizing Flows	❌	❌	✅	❌	❌	❌	✅	2
Gradient Estimation with Stochastic Softmax Tricks	❌	✅	✅	❌	❌	❌	✅	3
Gradient Regularized V-Learning for Dynamic Treatment Regimes	❌	✅	✅	❌	❌	❌	❌	2
Gradient Surgery for Multi-Task Learning	✅	✅	✅	❌	❌	❌	✅	4
Gradient-EM Bayesian Meta-Learning	✅	❌	✅	✅	❌	❌	✅	4
Graduated Assignment for Joint Multi-Graph Matching and Clustering with Application to Unsupervised Graph Matching Network Learning	✅	✅	✅	✅	✅	❌	✅	6
GramGAN: Deep 3D Texture Synthesis From 2D Exemplars	❌	❌	❌	❌	✅	❌	✅	2
Graph Contrastive Learning with Augmentations	✅	✅	✅	❌	❌	❌	✅	4
Graph Cross Networks with Vertex Infomax Pooling	❌	✅	✅	✅	✅	✅	✅	6
Graph Geometry Interaction Learning	❌	✅	✅	✅	❌	❌	✅	4
Graph Information Bottleneck	✅	✅	✅	✅	❌	❌	✅	5
Graph Meta Learning via Local Subgraphs	✅	✅	✅	✅	❌	❌	✅	5
Graph Policy Network for Transferable Active Learning on Graphs	✅	✅	✅	✅	❌	❌	✅	5
Graph Random Neural Networks for Semi-Supervised Learning on Graphs	✅	✅	✅	✅	❌	✅	✅	6
Graph Stochastic Neural Networks for Semi-supervised Learning	✅	✅	✅	✅	❌	❌	✅	5
Graphon Neural Networks and the Transferability of Graph Neural Networks	❌	✅	✅	✅	❌	✅	✅	5
Grasp Proposal Networks: An End-to-End Solution for Visual Learning of Robotic Grasps	❌	✅	✅	❌	❌	❌	✅	3
Greedy Optimization Provably Wins the Lottery: Logarithmic Number of Winning Tickets is Enough	✅	❌	✅	✅	❌	❌	✅	4
Greedy inference with structure-exploiting lazy maps	✅	✅	✅	❌	❌	❌	✅	4
GreedyFool: Distortion-Aware Sparse Adversarial Attack	✅	✅	✅	✅	❌	❌	✅	5
Group Contextual Encoding for 3D Point Clouds	❌	✅	✅	❌	❌	❌	✅	3
Group Knowledge Transfer: Federated Learning of Large CNNs at the Edge	✅	✅	✅	✅	✅	❌	✅	6
Group-Fair Online Allocation in Continuous Time	✅	❌	❌	❌	❌	❌	✅	2
Guided Adversarial Attack for Evaluating and Enhancing Adversarial Defenses	✅	✅	✅	❌	❌	❌	✅	4
Guiding Deep Molecular Optimization with Genetic Exploration	✅	✅	✅	❌	✅	❌	✅	5
H-Mem: Harnessing synaptic plasticity with Hebbian Memory Networks	❌	✅	✅	✅	❌	❌	✅	4
HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks	❌	❌	✅	❌	✅	❌	✅	3
HM-ANN: Efficient Billion-Point Nearest Neighbor Search on Heterogeneous Memory	✅	❌	✅	❌	✅	❌	✅	4
HOI Analysis: Integrating and Decomposing Human-Object Interaction	❌	✅	✅	✅	✅	❌	✅	5
HRN: A Holistic Approach to One Class Learning	❌	✅	✅	✅	❌	❌	✅	4
HYDRA: Pruning Adversarially Robust Neural Networks	✅	✅	✅	❌	❌	❌	✅	4
Hamiltonian Monte Carlo using an adjoint-differentiated Laplace approximation: Bayesian inference for latent Gaussian models and beyond	✅	✅	✅	❌	❌	❌	✅	4
Handling Missing Data with Graph Representation Learning	✅	✅	✅	✅	❌	❌	✅	5
Hard Example Generation by Texture Synthesis for Cross-domain Shape Similarity Learning	❌	✅	✅	✅	❌	❌	✅	4
Hard Negative Mixing for Contrastive Learning	❌	✅	✅	✅	❌	❌	✅	4
Hard Shape-Constrained Kernel Machines	❌	✅	✅	✅	✅	❌	✅	5
Hardness of Learning Neural Networks with Natural Weights	❌	❌	❌	❌	❌	❌	❌	0
Hausdorff Dimension, Heavy Tails, and Generalization in Neural Networks	❌	✅	✅	❌	❌	❌	✅	3
Heavy-tailed Representations, Text Polarity Classification & Data Augmentation	✅	❌	✅	❌	❌	❌	✅	3
Hedging in games: Faster convergence of external and swap regrets	❌	❌	❌	❌	❌	❌	❌	0
Heuristic Domain Adaptation	❌	✅	✅	✅	❌	❌	✅	4
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis	❌	✅	✅	❌	✅	❌	✅	4
HiPPO: Recurrent Memory with Optimal Polynomial Projections	❌	✅	✅	❌	❌	❌	❌	2
Hierarchical Gaussian Process Priors for Bayesian Neural Network Weights	❌	❌	✅	❌	❌	❌	✅	2
Hierarchical Granularity Transfer Learning	❌	❌	✅	✅	❌	❌	✅	3
Hierarchical Neural Architecture Search for Deep Stereo Matching	❌	✅	✅	✅	✅	❌	✅	5
Hierarchical Patch VAE-GAN: Generating Diverse Videos from a Single Sample	❌	✅	✅	✅	❌	❌	✅	4
Hierarchical Poset Decoding for Compositional Generalization in Language	✅	❌	✅	✅	❌	❌	✅	4
Hierarchical Quantized Autoencoders	✅	✅	✅	❌	❌	❌	✅	4
Hierarchical nucleation in deep neural networks	❌	✅	✅	❌	❌	❌	✅	3
Hierarchically Organized Latent Modules for Exploratory Search in Morphogenetic Systems	✅	✅	❌	❌	❌	❌	✅	3
High-Dimensional Bayesian Optimization via Nested Riemannian Manifolds	✅	✅	✅	❌	❌	❌	✅	4
High-Dimensional Contextual Policy Search with Unknown Context Rewards using Bayesian Optimization	❌	✅	❌	❌	❌	❌	❌	1
High-Dimensional Sparse Linear Bandits	✅	❌	❌	❌	❌	❌	✅	2
High-Fidelity Generative Image Compression	❌	❌	✅	✅	❌	❌	✅	3
High-Throughput Synchronous Deep RL	❌	✅	✅	❌	❌	❌	✅	3
High-contrast “gaudy” images improve the training of deep neural network models of visual cortex	❌	✅	✅	❌	✅	❌	✅	4
High-recall causal discovery for autocorrelated time series with latent confounders	✅	✅	✅	❌	✅	❌	✅	5
Higher-Order Certification For Randomized Smoothing	❌	❌	✅	❌	❌	❌	✅	2
Higher-Order Spectral Clustering of Directed Graphs	❌	❌	✅	❌	✅	❌	✅	3
Hitting the High Notes: Subset Selection for Maximizing Expected Order Statistics	✅	❌	✅	❌	❌	❌	✅	3
Hold me tight! Influence of discriminative features on deep network boundaries	❌	✅	✅	❌	❌	❌	❌	2
How Can I Explain This to You? An Empirical Study of Deep Neural Network Explanation Methods	❌	✅	✅	❌	❌	❌	✅	3
How Robust are the Estimated Effects of Nonpharmaceutical Interventions against COVID-19?	❌	✅	✅	❌	❌	❌	✅	3
How do fair decisions fare in long-term qualification?	❌	❌	✅	❌	❌	❌	❌	1
How does This Interaction Affect Me? Interpretable Attribution for Feature Interactions	❌	✅	✅	❌	✅	❌	❌	3
How does Weight Correlation Affect Generalisation Ability of Deep Neural Networks?	❌	❌	✅	❌	❌	❌	✅	2
How hard is to distinguish graphs with graph neural networks?	❌	❌	❌	✅	❌	❌	✅	2
How many samples is a good initial point worth in Low-rank Matrix Recovery?	❌	❌	❌	❌	❌	❌	❌	0
How to Characterize The Landscape of Overparameterized Convolutional Neural Networks	✅	❌	✅	❌	❌	❌	✅	3
How to Learn a Useful Critic? Model-based Action-Gradient-Estimator Policy Optimization	✅	✅	✅	❌	❌	❌	✅	4
Human Parsing Based Texture Transfer from Single Image to 3D Human via Cross-View Consistency	❌	✅	✅	❌	❌	❌	✅	3
HyNet: Learning Local Descriptor with Hybrid Similarity Measure and Triplet Loss	❌	✅	✅	✅	❌	❌	✅	4
Hybrid Models for Learning to Branch	❌	✅	❌	✅	❌	❌	✅	3
Hybrid Variance-Reduced SGD Algorithms For Minimax Problems with Nonconvex-Linear Function	✅	❌	✅	❌	✅	✅	✅	5
Hyperparameter Ensembles for Robustness and Uncertainty Quantification	✅	✅	✅	✅	❌	❌	✅	5
Hypersolvers: Toward Fast Continuous-Depth Models	❌	✅	✅	❌	✅	❌	✅	4
ICAM: Interpretable Classification via Disentangled Representations and Feature Attribution Mapping	❌	✅	✅	❌	❌	❌	❌	2
ICE-BeeM: Identifiable Conditional Energy-Based Deep Models Based on Nonlinear ICA	❌	✅	✅	❌	❌	❌	❌	2
ICNet: Intra-saliency Correlation Network for Co-Saliency Detection	❌	✅	✅	❌	✅	❌	✅	4
IDEAL: Inexact DEcentralized Accelerated Augmented Lagrangian Method	✅	❌	✅	❌	❌	❌	✅	3
ISTA-NAS: Efficient and Consistent Neural Architecture Search by Sparse Coding	✅	✅	✅	❌	✅	❌	✅	5
Identifying Causal-Effect Inference Failure with Uncertainty-Aware Models	❌	✅	✅	✅	❌	❌	✅	4
Identifying Learning Rules From Neural Network Observables	❌	✅	✅	✅	✅	❌	✅	5
Identifying Mislabeled Data using the Area Under the Margin Ranking	✅	✅	✅	❌	❌	❌	✅	4
Identifying signal and noise structure in neural population activity with Gaussian process factor models	❌	✅	✅	✅	❌	❌	✅	4
ImpatientCapsAndRuns: Approximately Optimal Algorithm Configuration from an Infinite Pool	✅	❌	✅	❌	❌	❌	❌	2
Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy	❌	❌	❌	❌	❌	❌	✅	1
Implicit Distributional Reinforcement Learning	✅	✅	✅	❌	✅	❌	✅	5
Implicit Graph Neural Networks	❌	✅	✅	✅	❌	❌	✅	4
Implicit Neural Representations with Periodic Activation Functions	❌	✅	✅	❌	❌	❌	❌	2
Implicit Rank-Minimizing Autoencoder	❌	❌	✅	❌	❌	❌	✅	2
Implicit Regularization and Convergence for Weight Normalization	✅	❌	❌	❌	❌	❌	❌	1
Implicit Regularization in Deep Learning May Not Be Explainable by Norms	❌	❌	❌	❌	❌	❌	✅	1
Impossibility Results for Grammar-Compressed Linear Algebra	❌	❌	✅	❌	❌	❌	❌	1
Improved Algorithms for Convex-Concave Minimax Optimization	✅	❌	❌	❌	❌	❌	❌	1
Improved Algorithms for Online Submodular Maximization via First-order Regret Bounds	✅	❌	❌	❌	❌	❌	❌	1
Improved Analysis of Clipping Algorithms for Non-convex Optimization	✅	✅	✅	✅	❌	❌	✅	5
Improved Guarantees for k-means++ and k-means++ Parallel	✅	❌	✅	❌	❌	❌	❌	2
Improved Sample Complexity for Incremental Autonomous Exploration in MDPs	✅	❌	❌	❌	❌	❌	❌	1
Improved Schemes for Episodic Memory-based Lifelong Learning	✅	✅	✅	✅	✅	❌	✅	6
Improved Techniques for Training Score-Based Generative Models	✅	❌	✅	❌	❌	❌	✅	3
Improved Variational Bayesian Phylogenetic Inference with Normalizing Flows	✅	✅	✅	❌	❌	❌	✅	4
Improved guarantees and a multiple-descent curve for Column Subset Selection and the Nystrom method	❌	❌	✅	❌	❌	❌	✅	2
Improving Auto-Augment via Augmentation-Wise Weight Sharing	✅	❌	✅	✅	✅	❌	✅	5
Improving GAN Training with Probability Ratio Clipping and Sample Reweighting	✅	✅	✅	❌	❌	❌	✅	4
Improving Generalization in Reinforcement Learning with Mixture Regularization	❌	✅	✅	❌	❌	❌	❌	2
Improving Inference for Neural Image Compression	✅	❌	✅	❌	❌	✅	✅	4
Improving Local Identifiability in Probabilistic Box Embeddings	✅	✅	✅	❌	❌	❌	❌	3
Improving Natural Language Processing Tasks with Human Gaze-Guided Neural Attention	❌	✅	✅	✅	❌	❌	✅	4
Improving Neural Network Training in Low Dimensional Random Bases	✅	✅	✅	❌	✅	❌	✅	5
Improving Online Rent-or-Buy Algorithms with Sequential Decision Making and ML Predictions	✅	❌	❌	❌	❌	❌	✅	2
Improving Policy-Constrained Kidney Exchange via Pre-Screening	✅	✅	❌	❌	❌	❌	✅	3
Improving Sample Complexity Bounds for (Natural) Actor-Critic Algorithms	✅	❌	❌	❌	❌	❌	❌	1
Improving Sparse Vector Technique with Renyi Differential Privacy	✅	❌	✅	❌	❌	❌	✅	3
Improving model calibration with accuracy versus uncertainty optimization	✅	✅	✅	❌	❌	❌	✅	4
Improving robustness against common corruptions by covariate shift adaptation	❌	✅	✅	✅	❌	❌	✅	4
In search of robust measures of generalization	❌	❌	✅	❌	❌	❌	✅	2
Incorporating BERT into Parallel Sequence Decoding with Adapters	❌	✅	✅	✅	✅	❌	✅	5
Incorporating Interpretable Output Constraints in Bayesian Neural Networks	❌	✅	✅	❌	❌	❌	✅	3
Incorporating Pragmatic Reasoning Communication into Emergent Language	❌	✅	❌	❌	✅	❌	✅	3
Independent Policy Gradient Methods for Competitive Reinforcement Learning	✅	❌	❌	❌	❌	❌	✅	2
Inductive Quantum Embedding	✅	✅	✅	✅	❌	❌	✅	5
Inference Stage Optimization for Cross-scenario 3D Human Pose Estimation	✅	❌	✅	❌	✅	❌	✅	4
Inference for Batched Bandits	❌	❌	❌	❌	❌	❌	✅	1
Inferring learning rules from animal decision-making	❌	✅	✅	❌	❌	❌	✅	3
Influence-Augmented Online Planning for Complex Environments	✅	✅	❌	❌	❌	❌	✅	3
Information Maximization for Few-Shot Learning	❌	✅	✅	✅	✅	❌	✅	5
Information Theoretic Counterfactual Learning from Missing-Not-At-Random Feedback	✅	✅	✅	✅	❌	❌	✅	5
Information Theoretic Regret Bounds for Online Nonlinear Control	✅	✅	✅	❌	❌	❌	❌	3
Information theoretic limits of learning a sparse rule	❌	❌	❌	❌	❌	❌	❌	0
Information-theoretic Task Selection for Meta-Reinforcement Learning	✅	✅	✅	✅	✅	❌	✅	6
Input-Aware Dynamic Backdoor Attack	✅	✅	✅	❌	❌	❌	✅	4
Instance Based Approximations to Profile Maximum Likelihood	✅	❌	❌	❌	❌	❌	❌	1
Instance Selection for GANs	❌	✅	✅	✅	✅	❌	✅	5
Instance-based Generalization in Reinforcement Learning	✅	✅	✅	❌	✅	✅	✅	6
Instance-optimality in differential privacy via approximate inverse sensitivity mechanisms	✅	❌	❌	❌	❌	❌	❌	1
Instance-wise Feature Grouping	❌	✅	✅	✅	✅	❌	✅	5
Instead of Rewriting Foreign Code for Machine Learning, Automatically Synthesize Fast Gradients	❌	✅	✅	❌	✅	❌	✅	4
Interferobot: aligning an optical interferometer by a reinforcement learning agent	❌	✅	❌	❌	✅	❌	✅	3
Interior Point Solving for LP-based prediction+optimisation	✅	✅	✅	✅	✅	✅	✅	7
Interpolation Technique to Speed Up Gradients Propagation in Neural ODEs	❌	✅	✅	❌	✅	❌	✅	4
Interpretable Sequence Learning for Covid-19 Forecasting	✅	❌	✅	✅	❌	❌	✅	4
Interpretable and Personalized Apprenticeship Scheduling: Learning Interpretable Scheduling Policies from Heterogeneous User Demonstrations	✅	✅	✅	❌	❌	❌	❌	3
Interpretable multi-timescale models for predicting fMRI responses to continuous natural speech	❌	❌	✅	✅	❌	❌	✅	3
Interstellar: Searching Recurrent Architecture for Knowledge Graph Embedding	✅	✅	✅	❌	✅	❌	❌	4
Interventional Few-Shot Learning	❌	✅	✅	✅	❌	❌	✅	4
Intra Order-preserving Functions for Calibration of Multi-Class Neural Networks	❌	❌	✅	✅	❌	❌	❌	2
Intra-Processing Methods for Debiasing Neural Networks	✅	✅	✅	✅	❌	❌	✅	5
Introducing Routing Uncertainty in Capsule Networks	✅	✅	✅	✅	❌	❌	✅	5
Inverse Learning of Symmetries	❌	✅	✅	❌	❌	❌	❌	2
Inverse Rational Control with Partially Observable Continuous Nonlinear Dynamics	✅	❌	❌	❌	❌	❌	✅	2
Inverse Reinforcement Learning from a Gradient-based Learner	✅	❌	❌	❌	❌	❌	✅	2
Invertible Gaussian Reparameterization: Revisiting the Gumbel-Softmax	❌	✅	✅	✅	❌	❌	✅	4
Inverting Gradients - How easy is it to break privacy in federated learning?	❌	✅	✅	✅	❌	❌	✅	4
Investigating Gender Bias in Language Models Using Causal Mediation Analysis	❌	✅	✅	❌	❌	❌	❌	2
Is Long Horizon RL More Difficult Than Short Horizon RL?	✅	❌	❌	❌	❌	❌	❌	1
Is Plug-in Solver Sample-Efficient for Feature-based Reinforcement Learning?	✅	❌	❌	❌	❌	❌	❌	1
Is normalization indispensable for training deep neural network?	❌	✅	✅	✅	❌	❌	✅	4
Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings	✅	✅	✅	✅	❌	❌	❌	4
JAX MD: A Framework for Differentiable Physics	❌	✅	✅	✅	✅	❌	✅	5
Joint Contrastive Learning with Infinite Possibilities	✅	✅	✅	✅	✅	❌	✅	6
Joint Policy Search for Multi-agent Collaboration with Imperfect Information	✅	✅	✅	❌	❌	❌	✅	4
Joints in Random Forests	✅	❌	✅	✅	❌	❌	✅	4
Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout	✅	❌	✅	❌	✅	❌	✅	4
KFC: A Scalable Approximation Algorithm for $k$−center Fair Clustering	✅	✅	✅	❌	✅	❌	✅	5
Kalman Filtering Attention for User Behavior Modeling in CTR Prediction	❌	❌	✅	❌	❌	❌	✅	2
Kernel Alignment Risk Estimator: Risk Prediction from Training Data	❌	❌	✅	❌	❌	❌	✅	2
Kernel Based Progressive Distillation for Adder Neural Networks	✅	❌	✅	❌	✅	❌	✅	4
Kernel Methods Through the Roof: Handling Billions of Points Efficiently	✅	✅	✅	✅	✅	❌	✅	6
Kernelized information bottleneck leads to biologically plausible 3-factor Hebbian learning in deep networks	❌	✅	✅	✅	❌	❌	✅	4
Knowledge Augmented Deep Neural Networks for Joint Facial Expression and Action Unit Recognition	✅	❌	✅	✅	❌	❌	✅	4
Knowledge Distillation in Wide Neural Networks: Risk Bound, Data Efficiency and Imperfect Teacher	❌	❌	❌	❌	❌	❌	✅	1
Knowledge Transfer in Multi-Task Deep Reinforcement Learning for Continuous Control	✅	❌	✅	❌	✅	❌	✅	4
LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-resolution and Beyond	❌	❌	✅	❌	✅	❌	✅	3
Label-Aware Neural Tangent Kernel: Toward Better Generalization and Local Elasticity	❌	✅	✅	❌	❌	❌	❌	2
Labelling unlabelled videos from scratch with multi-modal self-supervision	❌	❌	✅	❌	❌	❌	✅	2
Lamina-specific neuronal properties promote robust, stable signal propagation in feedforward networks	❌	❌	❌	❌	❌	❌	✅	1
Language Models are Few-Shot Learners	❌	❌	✅	✅	✅	❌	✅	4
Language Through a Prism: A Spectral Approach for Multiscale Language Representations	✅	❌	✅	❌	❌	❌	✅	3
Language and Visual Entity Relationship Graph for Agent Navigation	❌	✅	✅	✅	❌	❌	❌	3
Language as a Cognitive Tool to Imagine Goals in Curiosity Driven Exploration	❌	✅	✅	❌	❌	❌	❌	2
Language-Conditioned Imitation Learning for Robot Manipulation Tasks	❌	✅	✅	✅	❌	❌	✅	4
Large-Scale Adversarial Training for Vision-and-Language Representation Learning	✅	✅	✅	✅	❌	❌	✅	5
Large-Scale Methods for Distributionally Robust Optimization	❌	✅	✅	❌	❌	❌	✅	3
Latent Bandits Revisited	✅	❌	✅	❌	❌	❌	✅	3
Latent Dynamic Factor Analysis of High-Dimensional Neural Recordings	❌	✅	✅	✅	✅	❌	✅	5
Latent Template Induction with Gumbel-CRFs	✅	✅	✅	✅	✅	❌	✅	6
Latent World Models For Intrinsically Motivated Exploration	❌	✅	✅	❌	✅	❌	✅	4
Leap-Of-Thought: Teaching Pre-Trained Models to Systematically Reason Over Implicit Knowledge	❌	✅	✅	✅	❌	❌	❌	3
Learnability with Indirect Supervision Signals	❌	❌	❌	❌	❌	❌	❌	0
Learning About Objects by Learning to Interact with Them	❌	❌	✅	❌	❌	❌	✅	2
Learning Affordance Landscapes for Interaction Exploration in 3D Environments	❌	✅	✅	✅	❌	❌	✅	4
Learning Agent Representations for Ice Hockey	❌	✅	❌	✅	❌	❌	❌	2
Learning Augmented Energy Minimization via Speed Scaling	✅	✅	✅	❌	❌	❌	✅	4
Learning Black-Box Attackers with Transferable Priors and Query Feedback	✅	✅	✅	❌	❌	✅	✅	5
Learning Bounds for Risk-sensitive Learning	❌	✅	✅	❌	❌	❌	✅	3
Learning Causal Effects via Weighted Empirical Risk Minimization	✅	❌	❌	❌	❌	❌	❌	1
Learning Certified Individually Fair Representations	❌	✅	✅	❌	✅	❌	✅	4
Learning Composable Energy Surrogates for PDE Order Reduction	❌	❌	❌	✅	✅	❌	✅	3
Learning Compositional Rules via Neural Program Synthesis	❌	✅	✅	❌	❌	❌	✅	3
Learning Continuous System Dynamics from Irregularly-Sampled Partial Observations	❌	✅	✅	❌	❌	❌	❌	2
Learning Deep Attribution Priors Based On Prior Knowledge	❌	❌	✅	✅	❌	❌	✅	3
Learning Deformable Tetrahedral Meshes for 3D Reconstruction	❌	✅	✅	❌	✅	❌	❌	3
Learning Differentiable Programs with Admissible Neural Heuristics	✅	✅	✅	✅	❌	❌	✅	5
Learning Differential Equations that are Easy to Solve	❌	✅	✅	❌	❌	❌	✅	3
Learning Discrete Energy-based Models via Auxiliary-variable Local Exploration	✅	✅	✅	❌	❌	❌	✅	4
Learning Disentangled Representations and Group Structure of Dynamical Environments	✅	✅	❌	❌	❌	❌	❌	2
Learning Disentangled Representations of Videos with Missing Data	❌	✅	✅	❌	❌	❌	✅	3
Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction	❌	✅	✅	❌	❌	❌	✅	3
Learning Dynamic Belief Graphs to Generalize on Text-Based Games	❌	✅	✅	✅	❌	❌	❌	3
Learning Feature Sparse Principal Subspace	✅	❌	✅	❌	✅	✅	✅	5
Learning Global Transparent Models consistent with Local Contrastive Explanations	✅	❌	✅	✅	❌	❌	✅	4
Learning Graph Structure With A Finite-State Automaton Layer	❌	✅	✅	❌	❌	❌	✅	3
Learning Guidance Rewards with Trajectory-space Smoothing	✅	✅	✅	❌	❌	❌	✅	4
Learning Implicit Credit Assignment for Cooperative Multi-Agent Reinforcement Learning	❌	✅	✅	❌	❌	✅	✅	4
Learning Implicit Functions for Topology-Varying Dense 3D Shape Correspondence	❌	✅	✅	❌	✅	❌	✅	4
Learning Individually Inferred Communication for Multi-Agent Cooperation	❌	❌	❌	❌	❌	❌	❌	0
Learning Invariances in Neural Networks from Training Data	✅	✅	✅	❌	❌	❌	✅	4
Learning Invariants through Soft Unification	✅	✅	✅	✅	✅	❌	✅	6
Learning Kernel Tests Without Data Splitting	✅	✅	✅	❌	❌	❌	✅	4
Learning Latent Space Energy-Based Prior Model	✅	✅	✅	❌	✅	❌	✅	5
Learning Linear Programs from Optimal Decisions	❌	✅	✅	✅	✅	✅	✅	6
Learning Loss for Test-Time Augmentation	❌	❌	✅	✅	❌	❌	❌	2
Learning Manifold Implicitly via Explicit Heat-Kernel Learning	✅	❌	✅	❌	❌	❌	✅	3
Learning Multi-Agent Communication through Structured Attentive Reasoning	❌	✅	✅	❌	❌	❌	✅	3
Learning Multi-Agent Coordination for Enhancing Target Coverage in Directional Sensor Networks	✅	✅	❌	❌	❌	❌	✅	3
Learning Mutational Semantics	❌	✅	✅	✅	❌	❌	✅	4
Learning Object-Centric Representations of Multi-Object Scenes from Multiple Views	✅	✅	✅	❌	❌	❌	✅	4
Learning Optimal Representations with the Decodable Information Bottleneck	✅	❌	✅	❌	❌	❌	✅	3
Learning Parities with Neural Networks	❌	❌	✅	❌	❌	❌	✅	2
Learning Physical Constraints with Neural Projections	✅	❌	❌	❌	✅	❌	❌	2
Learning Physical Graph Representations from Visual Scenes	❌	❌	✅	❌	✅	✅	✅	4
Learning Representations from Audio-Visual Spatial Alignment	❌	✅	✅	❌	❌	❌	✅	3
Learning Restricted Boltzmann Machines with Sparse Latent Variables	✅	❌	❌	❌	❌	❌	❌	1
Learning Retrospective Knowledge with Reverse Reinforcement Learning	❌	✅	✅	❌	❌	❌	✅	3
Learning Rich Rankings	❌	✅	✅	✅	❌	❌	✅	4
Learning Robust Decision Policies from Observational Data	✅	✅	✅	❌	❌	❌	✅	4
Learning Search Space Partition for Black-box Optimization using Monte Carlo Tree Search	❌	✅	✅	❌	❌	❌	✅	3
Learning Semantic-aware Normalization for Generative Adversarial Networks	❌	✅	✅	❌	✅	❌	✅	4
Learning Some Popular Gaussian Graphical Models without Condition Number Bounds	❌	❌	✅	❌	❌	❌	✅	2
Learning Sparse Prototypes for Text Generation	❌	✅	✅	✅	✅	❌	✅	5
Learning Strategic Network Emergence Games	✅	❌	✅	❌	❌	❌	❌	2
Learning Strategy-Aware Linear Classifiers	✅	✅	❌	❌	❌	❌	✅	3
Learning Structured Distributions From Untrusted Batches: Faster and Simpler	✅	✅	❌	❌	✅	❌	✅	4
Learning Utilities and Equilibria in Non-Truthful Auctions	❌	❌	❌	❌	❌	❌	❌	0
Learning abstract structure for drawing by efficient motor program induction	❌	❌	❌	❌	❌	❌	❌	0
Learning by Minimizing the Sum of Ranked Range	✅	✅	✅	✅	❌	❌	✅	5
Learning compositional functions via multiplicative weight updates	✅	✅	✅	❌	❌	❌	✅	4
Learning discrete distributions with infinite support	❌	❌	❌	❌	❌	❌	❌	0
Learning discrete distributions: user vs item-level privacy	✅	❌	❌	❌	❌	❌	❌	1
Learning efficient task-dependent representations with synaptic plasticity	❌	✅	❌	❌	❌	❌	✅	2
Learning from Aggregate Observations	❌	❌	✅	✅	❌	❌	✅	3
Learning from Failure: De-biasing Classifier from Biased Classifier	✅	❌	✅	❌	❌	❌	❌	2
Learning from Label Proportions: A Mutual Contamination Framework	✅	✅	✅	✅	❌	❌	✅	5
Learning from Mixtures of Private and Public Populations	✅	❌	❌	❌	❌	❌	❌	1
Learning from Positive and Unlabeled Data with Arbitrary Positive Shift	✅	✅	✅	✅	❌	❌	✅	5
Learning identifiable and interpretable latent models of high-dimensional neural activity using pi-VAE	❌	❌	✅	✅	❌	❌	✅	3
Learning of Discrete Graphical Models with Neural Networks	❌	✅	❌	❌	❌	❌	✅	2
Learning outside the Black-Box: The pursuit of interpretable models	✅	✅	✅	❌	❌	❌	❌	3
Learning sparse codes from compressed representations with biologically plausible local wiring constraints	❌	✅	✅	✅	❌	❌	✅	4
Learning the Geometry of Wave-Based Imaging	❌	✅	✅	❌	❌	❌	✅	3
Learning the Linear Quadratic Regulator from Nonlinear Observations	✅	❌	❌	❌	❌	❌	❌	1
Learning to Adapt to Evolving Domains	✅	✅	✅	✅	❌	❌	✅	5
Learning to Approximate a Bregman Divergence	❌	✅	✅	✅	❌	❌	✅	4
Learning to Decode: Reinforcement Learning for Decoding of Sparse Graph-Based Channel Codes	✅	❌	❌	❌	❌	❌	✅	2
Learning to Detect Objects with a 1 Megapixel Event Camera	❌	✅	✅	✅	✅	❌	✅	5
Learning to Dispatch for Job Shop Scheduling via Deep Reinforcement Learning	❌	✅	✅	✅	✅	❌	✅	5
Learning to Execute Programs with Instruction Pointer Attention Graph Neural Networks	❌	❌	❌	✅	❌	❌	✅	2
Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction	✅	✅	✅	✅	❌	❌	✅	5
Learning to Incentivize Other Learning Agents	✅	✅	✅	❌	❌	❌	✅	4
Learning to Learn Variational Semantic Memory	❌	❌	✅	❌	❌	❌	❌	1
Learning to Learn with Feedback and Local Plasticity	❌	✅	✅	✅	❌	❌	✅	4
Learning to Mutate with Hypergradient Guided Population	✅	❌	✅	✅	❌	❌	✅	4
Learning to Orient Surfaces by Self-supervised Spherical CNNs	❌	✅	✅	✅	❌	❌	✅	4
Learning to Play No-Press Diplomacy with Best Response Policy Iteration	✅	✅	✅	✅	❌	❌	✅	5
Learning to Play Sequential Games versus Unknown Opponents	✅	❌	✅	❌	❌	❌	✅	3
Learning to Prove Theorems by Learning to Generate Theorems	✅	✅	✅	✅	❌	❌	✅	5
Learning to Select Best Forecast Tasks for Clinical Outcome Prediction	✅	✅	✅	✅	❌	❌	✅	5
Learning to Utilize Shaping Rewards: A New Approach of Reward Shaping	❌	❌	✅	❌	❌	❌	✅	2
Learning to search efficiently for causally near-optimal treatments	❌	✅	✅	✅	❌	❌	✅	4
Learning to solve TV regularised problems with unrolled algorithms	❌	❌	✅	❌	❌	❌	✅	2
Learning to summarize with human feedback	❌	✅	✅	✅	❌	❌	✅	4
Learning under Model Misspecification: Applications to Variational and Ensemble methods	❌	✅	✅	❌	❌	❌	❌	2
Learning with Differentiable Pertubed Optimizers	❌	✅	✅	✅	❌	❌	✅	4
Learning with Operator-valued Kernels in Reproducing Kernel Krein Spaces	✅	✅	✅	✅	❌	✅	✅	6
Learning with Optimized Random Features: Exponential Speedup by Quantum Machine Learning without Sparsity and Low-Rank Assumptions	✅	❌	❌	❌	❌	❌	❌	1
Least Squares Regression with Markovian Data: Fundamental Limits and Algorithms	✅	❌	❌	❌	❌	❌	✅	2
Leverage the Average: an Analysis of KL Regularization in Reinforcement Learning	❌	❌	✅	❌	❌	❌	❌	1
Leveraging Predictions in Smoothed Online Convex Optimization via Gradient-based Algorithms	✅	❌	❌	❌	❌	❌	❌	1
Liberty or Depth: Deep Bayesian Neural Nets Do Not Need Complex Weight Posterior Approximations	❌	❌	✅	❌	❌	❌	✅	2
Lifelong Policy Gradient Learning of Factored Policies for Faster Training Without Forgetting	✅	✅	✅	❌	❌	❌	✅	4
Lightweight Generative Adversarial Networks for Text-Guided Image Manipulation	❌	✅	✅	✅	✅	❌	✅	5
Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder	✅	❌	✅	❌	❌	❌	✅	3
Limits on Testing Structural Changes in Ising Models	❌	❌	❌	❌	❌	✅	✅	2
Limits to Depth Efficiencies of Self-Attention	❌	❌	✅	❌	✅	❌	❌	2
Linear Disentangled Representations and Unsupervised Action Estimation	❌	✅	✅	✅	❌	❌	✅	4
Linear Dynamical Systems as a Core Computational Primitive	✅	❌	✅	❌	❌	❌	✅	3
Linear Time Sinkhorn Divergences using Positive Features	✅	✅	✅	❌	✅	❌	✅	5
Linear-Sample Learning of Low-Rank Distributions	✅	❌	❌	❌	❌	❌	❌	1
Linearly Converging Error Compensated SGD	✅	✅	✅	❌	✅	❌	✅	5
Lipschitz Bounds and Provably Robust Training by Laplacian Smoothing	❌	✅	✅	❌	❌	❌	❌	2
Lipschitz-Certifiable Training with a Tight Outer Bound	✅	✅	✅	❌	✅	❌	✅	5
List-Decodable Mean Estimation via Iterative Multi-Filtering	✅	❌	❌	❌	❌	❌	❌	1
Listening to Sounds of Silence for Speech Denoising	❌	❌	✅	❌	❌	❌	✅	2
LoCo: Local Contrastive Representation Learning	❌	❌	✅	✅	❌	❌	✅	3
Locally Differentially Private (Contextual) Bandits Learning	✅	❌	❌	❌	❌	❌	❌	1
Locally private non-asymptotic testing of discrete distributions is faster using interactive mechanisms	❌	❌	❌	❌	❌	❌	❌	0
Locally-Adaptive Nonparametric Online Learning	✅	❌	❌	❌	❌	❌	❌	1
Log-Likelihood Ratio Minimizing Flows: Towards Robust and Quantifiable Neural Distribution Alignment	❌	✅	✅	❌	❌	❌	❌	2
Logarithmic Pruning is All You Need	❌	❌	❌	❌	❌	❌	❌	0
Logarithmic Regret Bound in Partially Observable Linear Dynamical Systems	✅	❌	❌	❌	❌	❌	❌	1
Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors	✅	✅	✅	❌	✅	❌	❌	4
Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect	❌	✅	✅	✅	❌	❌	✅	4
Look-ahead Meta Learning for Continual Learning	✅	✅	✅	✅	❌	❌	✅	5
LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registration	❌	✅	✅	❌	❌	❌	❌	2
Low Distortion Block-Resampling with Spatially Stochastic Networks	❌	❌	✅	❌	✅	❌	✅	3
Lower Bounds and Optimal Algorithms for Personalized Federated Learning	✅	❌	✅	❌	❌	❌	❌	2
MATE: Plugging in Model Awareness to Task Embedding for Meta Learning	❌	✅	✅	✅	❌	❌	✅	4
MCUNet: Tiny Deep Learning on IoT Devices	❌	❌	✅	✅	❌	❌	❌	2
MDP Homomorphic Networks: Group Symmetries in Reinforcement Learning	✅	✅	✅	❌	❌	❌	❌	3
MESA: Boost Ensemble Imbalanced Learning with MEta-SAmpler	✅	✅	✅	✅	❌	❌	✅	5
MMA Regularization: Decorrelating Weights of Neural Networks by Maximizing the Minimal Angles	❌	✅	✅	✅	✅	❌	✅	5
MOPO: Model-based Offline Policy Optimization	✅	✅	✅	❌	❌	❌	✅	4
MOReL: Model-Based Offline Reinforcement Learning	✅	❌	✅	❌	❌	❌	❌	2
MPNet: Masked and Permuted Pre-training for Language Understanding	❌	✅	✅	✅	✅	❌	✅	5
MRI Banding Removal via Adversarial Training	❌	✅	✅	✅	❌	❌	✅	4
Make One-Shot Video Object Segmentation Efficient Again	✅	✅	✅	✅	✅	❌	✅	6
Making Non-Stochastic Control (Almost) as Easy as Stochastic	✅	❌	❌	❌	❌	❌	❌	1
Manifold GPLVMs for discovering non-Euclidean latent structure in neural data	❌	❌	✅	✅	❌	❌	✅	3
Manifold structure in graph embeddings	❌	❌	✅	❌	❌	❌	✅	2
Marginal Utility for Planning in Continuous or Large Discrete Action Spaces	❌	❌	❌	❌	✅	❌	✅	2
Margins are Insufficient for Explaining Gradient Boosting	❌	❌	✅	✅	❌	❌	✅	3
Markovian Score Climbing: Variational Inference with KL(p\|\|q)	✅	✅	✅	✅	❌	❌	✅	5
Matrix Completion with Hierarchical Graph Side Information	✅	❌	✅	❌	❌	❌	✅	3
Matrix Completion with Quantified Uncertainty through Low Rank Gaussian Copula	✅	❌	✅	✅	✅	❌	✅	5
Matrix Inference and Estimation in Multi-Layer Models	✅	✅	❌	❌	❌	❌	✅	3
Matérn Gaussian Processes on Riemannian Manifolds	❌	✅	✅	❌	❌	❌	✅	3
Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustness	✅	✅	✅	✅	❌	❌	✅	5
Measuring Robustness to Natural Distribution Shifts in Image Classification	❌	✅	✅	❌	❌	❌	❌	2
Measuring Systematic Generalization in Neural Proof Generation with Transformers	✅	✅	✅	❌	❌	❌	✅	4
Memory Based Trajectory-conditioned Policies for Learning from Sparse Rewards	✅	❌	✅	❌	❌	❌	✅	3
Memory-Efficient Learning of Stable Linear Dynamical Systems for Prediction and Control	✅	✅	✅	❌	✅	✅	✅	6
MeshSDF: Differentiable Iso-Surface Extraction	✅	❌	✅	✅	❌	❌	✅	4
Meta-Consolidation for Continual Learning	✅	✅	✅	❌	✅	❌	✅	5
Meta-Gradient Reinforcement Learning with an Objective Discovered Online	✅	❌	✅	❌	❌	❌	✅	3
Meta-Learning Requires Meta-Augmentation	❌	✅	✅	❌	❌	❌	❌	2
Meta-Learning Stationary Stochastic Process Prediction with Convolutional Neural Processes	✅	✅	✅	❌	❌	❌	❌	3
Meta-Learning through Hebbian Plasticity in Random Networks	❌	✅	✅	❌	❌	✅	✅	4
Meta-Learning with Adaptive Hyperparameters	✅	✅	✅	✅	❌	❌	✅	5
Meta-Neighborhoods	✅	✅	✅	✅	❌	❌	✅	5
Meta-learning from Tasks with Heterogeneous Attribute Spaces	✅	❌	✅	✅	❌	❌	✅	4
Meta-trained agents implement Bayes-optimal agents	❌	❌	❌	❌	❌	❌	✅	1
MetaPerturb: Transferable Regularizer for Heterogeneous Tasks and Architectures	✅	❌	✅	✅	❌	❌	✅	4
MetaPoison: Practical General-purpose Clean-label Data Poisoning	✅	✅	✅	❌	❌	❌	✅	4
MetaSDF: Meta-Learning Signed Distance Functions	✅	✅	✅	✅	❌	❌	✅	5
Metric-Free Individual Fairness in Online Learning	✅	❌	❌	❌	❌	❌	❌	1
MinMax Methods for Optimal Transport and Beyond: Regularization, Approximation and Numerics	❌	✅	❌	❌	❌	❌	✅	2
MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers	❌	✅	✅	❌	❌	❌	❌	2
Minibatch Stochastic Approximate Proximal Point Methods	❌	✅	❌	❌	❌	❌	✅	2
Minibatch vs Local SGD for Heterogeneous Distributed Learning	✅	❌	✅	❌	❌	❌	✅	3
Minimax Bounds for Generalized Linear Models	❌	❌	❌	❌	❌	❌	❌	0
Minimax Classification with 0-1 Loss and Performance Guarantees	✅	✅	✅	✅	❌	❌	✅	5
Minimax Dynamics of Optimally Balanced Spiking Networks of Excitatory and Inhibitory Neurons	❌	❌	✅	❌	❌	✅	✅	3
Minimax Estimation of Conditional Moment Models	✅	✅	✅	❌	❌	❌	✅	4
Minimax Lower Bounds for Transfer Learning with Linear and One-hidden Layer Neural Networks	❌	✅	✅	✅	❌	❌	✅	4
Minimax Optimal Nonparametric Estimation of Heterogeneous Treatment Effects	✅	✅	❌	❌	❌	❌	❌	2
Minimax Regret of Switching-Constrained Online Convex Optimization: No Phase Transition	❌	❌	❌	❌	❌	❌	❌	0
Minimax Value Interval for Off-Policy Evaluation and Policy Optimization	❌	❌	✅	❌	❌	❌	✅	2
Mitigating Forgetting in Online Continual Learning via Instance-Aware Parameterization	❌	❌	✅	❌	❌	❌	✅	2
Mitigating Manipulation in Peer Review via Randomized Reviewer Assignments	❌	✅	✅	❌	✅	✅	✅	5
Mix and Match: An Optimistic Tree-Search Approach for Learning Models from Mixture Distributions	✅	✅	✅	✅	❌	❌	✅	5
Mixed Hamiltonian Monte Carlo for Mixed Discrete and Continuous Variables	✅	✅	✅	❌	❌	❌	✅	4
Model Agnostic Multilevel Explanations	✅	❌	✅	✅	❌	❌	✅	4
Model Class Reliance for Random Forests	❌	✅	✅	❌	❌	❌	❌	2
Model Fusion via Optimal Transport	✅	✅	✅	❌	✅	❌	✅	5
Model Interpretability through the lens of Computational Complexity	❌	❌	❌	❌	❌	❌	❌	0
Model Inversion Networks for Model-Based Optimization	✅	❌	✅	❌	❌	❌	✅	3
Model Rubik’s Cube: Twisting Resolution, Depth and Width for TinyNets	❌	✅	✅	✅	✅	❌	✅	5
Model Selection for Production System via Automated Online Experiments	✅	❌	✅	❌	❌	❌	✅	3
Model Selection in Contextual Stochastic Bandit Problems	✅	❌	❌	❌	❌	❌	✅	2
Model-Based Multi-Agent RL in Zero-Sum Markov Games with Near-Optimal Sample Complexity	❌	❌	❌	❌	❌	❌	❌	0
Model-based Adversarial Meta-Reinforcement Learning	✅	✅	✅	❌	❌	❌	✅	4
Model-based Policy Optimization with Unsupervised Model Adaptation	✅	✅	✅	❌	❌	❌	✅	4
Model-based Reinforcement Learning for Semi-Markov Decision Processes with Neural ODEs	✅	❌	✅	❌	❌	❌	❌	2
Modeling Continuous Stochastic Processes with Dynamic Normalizing Flows	❌	✅	✅	❌	❌	❌	✅	3
Modeling Noisy Annotations for Crowd Counting	❌	❌	✅	✅	❌	❌	✅	3
Modeling Shared responses in Neuroimaging Studies through MultiView ICA	✅	✅	✅	✅	❌	❌	✅	5
Modeling Task Effects on Meaning Representation in the Brain via Zero-Shot MEG Prediction	❌	✅	✅	✅	❌	❌	❌	3
Modeling and Optimization Trade-off in Meta-learning	❌	❌	✅	✅	❌	❌	✅	3
Modern Hopfield Networks and Attention for Immune Repertoire Classification	❌	✅	✅	✅	❌	❌	✅	4
Modular Meta-Learning with Shrinkage	✅	❌	✅	✅	❌	❌	✅	4
MomentumRNN: Integrating Momentum into Recurrent Neural Networks	❌	❌	✅	✅	❌	❌	✅	3
Monotone operator equilibrium networks	✅	✅	✅	❌	✅	❌	✅	5
Most ReLU Networks Suffer from $\ell^2$ Adversarial Perturbations	❌	✅	✅	❌	❌	❌	✅	3
Movement Pruning: Adaptive Sparsity by Fine-Tuning	❌	❌	✅	❌	❌	❌	✅	2
MuSCLE: Multi Sweep Compression of LiDAR using Deep Entropy Models	❌	❌	✅	✅	❌	❌	✅	3
Multi-Fidelity Bayesian Optimization via Deep Neural Networks	✅	❌	✅	✅	✅	❌	✅	5
Multi-Plane Program Induction with 3D Box Priors	❌	❌	❌	❌	❌	❌	✅	1
Multi-Robot Collision Avoidance under Uncertainty with Probabilistic Safety Barrier Certificates	❌	✅	❌	❌	✅	❌	✅	3
Multi-Stage Influence Function	✅	✅	✅	❌	✅	❌	✅	5
Multi-Task Reinforcement Learning with Soft Modularization	❌	✅	✅	❌	❌	❌	✅	3
Multi-Task Temporal Shift Attention Networks for On-Device Contactless Vitals Measurement	❌	✅	✅	✅	✅	✅	✅	6
Multi-agent Trajectory Prediction with Fuzzy Query Attention	❌	✅	✅	✅	❌	❌	✅	4
Multi-agent active perception with prediction rewards	✅	✅	❌	❌	❌	❌	✅	3
Multi-label Contrastive Predictive Coding	✅	✅	✅	❌	✅	❌	✅	5
Multi-label classification: do Hamming loss and subset accuracy really conflict with each other?	❌	❌	✅	✅	❌	❌	✅	3
Multi-task Additive Models for Robust Estimation and Automatic Structure Discovery	✅	❌	✅	✅	✅	✅	✅	6
Multi-task Batch Reinforcement Learning with Metric Learning	✅	✅	✅	❌	❌	❌	✅	4
Multi-task Causal Learning with Gaussian Processes	❌	✅	✅	❌	❌	❌	❌	2
MultiON: Benchmarking Semantic Map Memory using Multi-Object Navigation	❌	✅	✅	✅	❌	❌	✅	4
Multifaceted Uncertainty Estimation for Label-Efficient Deep Learning	❌	❌	✅	❌	❌	❌	✅	2
Multilabel Classification by Hierarchical Partitioning and Data-dependent Grouping	✅	✅	✅	❌	❌	❌	✅	4
Multimodal Generative Learning Utilizing Jensen-Shannon-Divergence	❌	❌	✅	❌	❌	❌	❌	1
Multimodal Graph Networks for Compositional Generalization in Visual Question Answering	❌	✅	✅	✅	❌	❌	✅	4
Multiparameter Persistence Image for Topological Machine Learning	❌	✅	✅	✅	✅	❌	✅	5
Multipole Graph Neural Operator for Parametric Partial Differential Equations	❌	✅	❌	❌	❌	❌	✅	2
Multiscale Deep Equilibrium Models	❌	✅	✅	✅	✅	❌	✅	5
Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance	❌	✅	✅	❌	❌	❌	✅	3
Munchausen Reinforcement Learning	❌	❌	✅	❌	❌	❌	✅	2
Mutual exclusivity as a challenge for deep neural networks	❌	❌	✅	❌	❌	❌	✅	2
Myersonian Regression	❌	❌	❌	❌	❌	❌	❌	0
NVAE: A Deep Hierarchical Variational Autoencoder	❌	✅	✅	❌	✅	❌	✅	4
NanoFlow: Scalable Normalizing Flows with Sublinear Parameter Complexity	❌	❌	✅	❌	✅	❌	✅	3
Natural Graph Networks	❌	❌	✅	✅	❌	❌	✅	3
Natural Policy Gradient Primal-Dual Method for Constrained Markov Decision Processes	✅	❌	❌	❌	❌	❌	✅	2
Near-Optimal Comparison Based Clustering	✅	✅	✅	❌	❌	❌	✅	4
Near-Optimal Reinforcement Learning with Self-Play	✅	❌	❌	❌	❌	❌	❌	1
Near-Optimal SQ Lower Bounds for Agnostically Learning Halfspaces and ReLUs under Gaussian Marginals	❌	❌	❌	❌	❌	❌	❌	0
Network Diffusions via Neural Mean-Field Dynamics	✅	✅	✅	❌	❌	❌	✅	4
Network size and size of the weights in memorization with two-layers neural networks	❌	❌	❌	❌	❌	❌	❌	0
Network-to-Network Translation with Conditional Invertible Neural Networks	❌	✅	✅	❌	✅	❌	❌	3
NeuMiss networks: differentiable programming for supervised learning with missing values.	❌	✅	❌	❌	❌	❌	✅	2
Neural Anisotropy Directions	❌	✅	✅	❌	❌	❌	❌	2
Neural Architecture Generator Optimization	✅	✅	✅	❌	✅	❌	✅	5
Neural Bridge Sampling for Evaluating Safety-Critical Autonomous Systems	✅	❌	✅	❌	❌	❌	❌	2
Neural Complexity Measures	✅	❌	✅	✅	❌	❌	✅	4
Neural Controlled Differential Equations for Irregular Time Series	❌	✅	✅	✅	❌	❌	✅	4
Neural Dynamic Policies for End-to-End Sensorimotor Learning	✅	✅	✅	❌	❌	❌	✅	4
Neural Execution Engines: Learning to Execute Subroutines	✅	✅	✅	❌	❌	❌	❌	3
Neural FFTs for Universal Texture Image Synthesis	❌	❌	✅	✅	✅	❌	✅	4
Neural Manifold Ordinary Differential Equations	✅	❌	✅	❌	❌	❌	✅	3
Neural Mesh Flow: 3D Manifold Mesh Generation via Diffeomorphic Flows	❌	✅	✅	✅	✅	❌	✅	5
Neural Message Passing for Multi-Relational Ordered and Recursive Hypergraphs	❌	✅	✅	❌	❌	❌	✅	3
Neural Methods for Point-wise Dependency Estimation	❌	✅	✅	❌	❌	❌	❌	2
Neural Networks Fail to Learn Periodic Functions and How to Fix It	❌	✅	✅	✅	❌	❌	✅	4
Neural Networks Learning and Memorization with (almost) no Over-Parameterization	✅	❌	❌	❌	❌	❌	✅	2
Neural Networks with Recurrent Generative Feedback	✅	❌	✅	❌	❌	❌	✅	3
Neural Networks with Small Weights and Depth-Separation Barriers	❌	❌	❌	❌	❌	❌	❌	0
Neural Non-Rigid Tracking	✅	✅	✅	✅	✅	❌	✅	6
Neural Path Features and Neural Path Kernel : Understanding the role of gates in deep learning	❌	❌	✅	❌	❌	❌	✅	2
Neural Power Units	❌	✅	❌	❌	❌	❌	✅	2
Neural Sparse Representation for Image Restoration	❌	✅	✅	✅	✅	❌	✅	5
Neural Sparse Voxel Fields	✅	✅	✅	❌	✅	❌	✅	5
Neural Star Domain as Primitive Representation	❌	❌	✅	✅	✅	❌	✅	4
Neural Topographic Factor Analysis for fMRI Data	✅	❌	✅	❌	❌	❌	✅	3
Neural Unsigned Distance Fields for Implicit Function Learning	✅	✅	✅	✅	✅	❌	✅	6
Neural encoding with visual attention	❌	✅	✅	✅	❌	❌	✅	4
Neuron Merging: Compensating for Pruned Neurons	✅	✅	✅	✅	❌	❌	✅	5
Neuron Shapley: Discovering the Responsible Neurons	✅	✅	✅	✅	❌	❌	✅	5
Neuron-level Structured Pruning using Polarization Regularizer	✅	✅	✅	❌	❌	❌	✅	4
Neuronal Gaussian Process Regression	❌	✅	✅	✅	❌	❌	✅	4
Neurosymbolic Reinforcement Learning with Formally Verified Exploration	✅	✅	❌	❌	❌	❌	✅	3
Neurosymbolic Transformers for Multi-Agent Communication	❌	✅	❌	❌	❌	❌	✅	2
Neutralizing Self-Selection Bias in Sampling for Sortition	❌	✅	✅	❌	❌	❌	❌	2
Nimble: Lightweight and Parallel GPU Task Scheduling for Deep Learning	✅	✅	✅	❌	✅	✅	✅	6
No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems	✅	✅	✅	❌	❌	❌	❌	3
No-Regret Learning Dynamics for Extensive-Form Correlated Equilibrium	✅	❌	✅	❌	✅	❌	✅	4
No-Regret Learning and Mixed Nash Equilibria: They Do Not Mix	❌	❌	❌	❌	❌	❌	❌	0
No-regret Learning in Price Competitions under Consumer Reference Effects	✅	❌	❌	❌	❌	❌	✅	2
Node Classification on Graphs with Few-Shot Novel Labels via Meta Transformed Network Embedding	❌	❌	✅	✅	❌	❌	✅	3
Node Embeddings and Exact Low-Rank Representations of Complex Networks	❌	✅	✅	❌	❌	❌	✅	3
Noise-Contrastive Estimation for Multivariate Point Processes	✅	✅	✅	✅	✅	❌	✅	6
Noise2Same: Optimizing A Self-Supervised Bound for Image Denoising	❌	❌	✅	❌	❌	❌	✅	2
Non-Convex SGD Learns Halfspaces with Adversarial Label Noise	✅	❌	❌	❌	❌	❌	❌	1
Non-Crossing Quantile Regression for Distributional Reinforcement Learning	❌	❌	✅	❌	❌	❌	✅	2
Non-Euclidean Universal Approximation	❌	✅	✅	❌	❌	❌	❌	2
Non-Stochastic Control with Bandit Feedback	✅	✅	❌	❌	❌	❌	✅	3
Non-parametric Models for Non-negative Functions	❌	✅	❌	❌	❌	❌	✅	2
Non-reversible Gaussian processes for identifying latent dynamical structure in neural data	❌	❌	✅	❌	❌	❌	✅	2
Nonasymptotic Guarantees for Spiked Matrix Recovery with Generative Priors	✅	❌	❌	❌	❌	❌	✅	2
Nonconvex Sparse Graph Learning under Laplacian Constrained Graphical Model	✅	✅	✅	❌	✅	❌	✅	5
Normalizing Kalman Filters for Multivariate Time Series Analysis	❌	❌	✅	✅	❌	❌	✅	3
Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning	✅	❌	✅	✅	✅	❌	✅	5
Novelty Search in Representational Space for Sample Efficient Exploration	✅	✅	❌	❌	❌	❌	✅	3
Numerically Solving Parametric Families of High-Dimensional Kolmogorov Partial Differential Equations via Deep Learning	❌	✅	❌	❌	✅	❌	✅	3
O(n) Connections are Expressive Enough: Universal Approximability of Sparse Transformers	❌	❌	✅	✅	❌	❌	✅	3
OOD-MAML: Meta-Learning for Few-Shot Out-of-Distribution Detection and Classification	❌	✅	✅	❌	❌	❌	❌	2
OTLDA: A Geometry-aware Optimal Transport Approach for Topic Modeling	✅	❌	✅	✅	❌	❌	✅	4
Object Goal Navigation using Goal-Oriented Semantic Exploration	❌	✅	✅	✅	❌	❌	✅	4
Object-Centric Learning with Slot Attention	✅	✅	✅	✅	✅	❌	✅	6
Ode to an ODE	❌	❌	✅	❌	❌	❌	✅	2
Off-Policy Evaluation and Learning for External Validity under a Covariate Shift	✅	❌	✅	✅	❌	❌	❌	3
Off-Policy Evaluation via the Regularized Lagrangian	❌	❌	✅	❌	❌	❌	✅	2
Off-Policy Imitation Learning from Observations	✅	❌	✅	❌	❌	❌	❌	2
Off-Policy Interval Estimation with Lipschitz Value Iteration	✅	❌	❌	❌	❌	❌	✅	2
Off-policy Policy Evaluation For Sequential Decisions Under Unobserved Confounding	❌	✅	✅	❌	❌	❌	✅	3
Offline Imitation Learning with a Misspecified Simulator	✅	❌	✅	❌	❌	❌	✅	3
On 1/n neural representation and robustness	❌	✅	✅	❌	❌	❌	✅	3
On Adaptive Attacks to Adversarial Example Defenses	❌	✅	✅	❌	❌	❌	✅	3
On Adaptive Distance Estimation	✅	❌	❌	❌	❌	❌	✅	2
On Completeness-aware Concept-Based Explanations in Deep Neural Networks	❌	✅	✅	✅	✅	❌	✅	5
On Convergence and Generalization of Dropout Training	✅	❌	✅	❌	❌	❌	✅	3
On Convergence of Nearest Neighbor Classifiers over Feature Transformations	❌	✅	✅	✅	❌	❌	✅	4
On Correctness of Automatic Differentiation for Non-Differentiable Functions	❌	❌	❌	❌	❌	❌	❌	0
On Efficiency in Hierarchical Reinforcement Learning	✅	❌	❌	❌	❌	❌	❌	1
On Infinite-Width Hypernetworks	❌	❌	✅	❌	❌	❌	✅	2
On Learning Ising Models under Huber's Contamination Model	✅	❌	❌	❌	❌	❌	✅	2
On Numerosity of Deep Neural Networks	❌	❌	✅	❌	❌	❌	❌	1
On Power Laws in Deep Ensembles	❌	✅	✅	✅	❌	❌	✅	4
On Regret with Multiple Best Arms	✅	❌	✅	❌	❌	❌	✅	3
On Reward-Free Reinforcement Learning with Linear Function Approximation	✅	❌	❌	❌	❌	❌	❌	1
On Second Order Behaviour in Augmented Neural ODEs	❌	✅	✅	❌	❌	❌	✅	3
On Testing of Samplers	✅	✅	✅	❌	✅	❌	❌	4
On Uniform Convergence and Low-Norm Interpolation Learning	❌	❌	❌	❌	❌	❌	❌	0
On Warm-Starting Neural Network Training	❌	❌	✅	✅	✅	❌	✅	4
On ranking via sorting by estimated expected utility	❌	❌	❌	❌	❌	❌	✅	1
On the Almost Sure Convergence of Stochastic Gradient Descent in Non-Convex Problems	❌	❌	✅	❌	❌	❌	✅	2
On the Convergence of Smooth Regularized Approximate Value Iteration Schemes	❌	❌	❌	❌	❌	❌	❌	0
On the Equivalence between Online and Private Learnability beyond Binary Classification	✅	❌	❌	❌	❌	❌	❌	1
On the Ergodicity, Bias and Asymptotic Normality of Randomized Midpoint Sampling Method	❌	❌	❌	❌	❌	❌	❌	0
On the Error Resistance of Hinge-Loss Minimization	❌	❌	❌	❌	❌	❌	❌	0
On the Expressiveness of Approximate Inference in Bayesian Neural Networks	❌	✅	✅	❌	❌	❌	✅	3
On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them	❌	✅	✅	❌	❌	❌	✅	3
On the Modularity of Hypernetworks	❌	❌	✅	❌	❌	❌	✅	2
On the Optimal Weighted $\ell_2$ Regularization in Overparameterized Linear Regression	❌	❌	❌	❌	❌	❌	✅	1
On the Power of Louvain in the Stochastic Block Model	❌	❌	❌	❌	❌	❌	✅	1
On the Role of Sparsity and DAG Constraints for Learning Linear DAGs	❌	❌	✅	✅	✅	❌	✅	4
On the Similarity between the Laplace and Neural Tangent Kernels	❌	❌	✅	✅	❌	❌	❌	2
On the Stability and Convergence of Robust Adversarial Reinforcement Learning: A Case Study on Linear Quadratic Systems	✅	❌	❌	❌	❌	❌	✅	2
On the Theory of Transfer Learning: The Importance of Task Diversity	❌	❌	❌	❌	❌	❌	❌	0
On the Tightness of Semidefinite Relaxations for Certifying Robustness to Adversarial Examples	❌	❌	✅	✅	✅	❌	✅	4
On the Trade-off between Adversarial and Backdoor Robustness	❌	✅	✅	❌	✅	❌	✅	4
On the Value of Out-of-Distribution Testing: An Example of Goodhart's Law	❌	❌	✅	✅	❌	❌	✅	3
On the distance between two neural networks and the stability of learning	✅	✅	✅	❌	❌	❌	✅	4
On the equivalence of molecular graph convolution and molecular wave function with poor basis set	❌	✅	✅	✅	✅	❌	❌	4
On the linearity of large non-linear models: when and why the tangent kernel is constant	❌	❌	❌	❌	❌	❌	❌	0
On the training dynamics of deep networks with $L_2$ regularization	❌	❌	✅	❌	❌	❌	✅	2
On the universality of deep learning	❌	❌	❌	❌	❌	❌	❌	0
Once-for-All Adversarial Training: In-Situ Tradeoff between Robustness and Accuracy for Free	✅	✅	✅	❌	❌	❌	✅	4
One Ring to Rule Them All: Certifiably Robust Geometric Perception with Outliers	❌	✅	✅	❌	❌	❌	✅	3
One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL	✅	❌	✅	❌	❌	❌	✅	3
One-bit Supervision for Image Classification	❌	❌	✅	❌	✅	❌	✅	3
One-sample Guided Object Representation Disassembling	❌	❌	✅	❌	❌	❌	✅	2
Online Adaptation for Consistent Mesh Reconstruction in the Wild	❌	❌	✅	❌	❌	❌	✅	2
Online Agnostic Boosting via Regret Minimization	✅	❌	❌	❌	❌	❌	❌	1
Online Algorithm for Unsupervised Sequential Selection with Contextual Information	✅	❌	✅	❌	❌	❌	❌	2
Online Algorithms for Multi-shop Ski Rental with Machine Learned Advice	✅	✅	✅	❌	❌	❌	✅	4
Online Bayesian Goal Inference for Boundedly Rational Planning Agents	✅	✅	✅	❌	❌	❌	✅	4
Online Bayesian Persuasion	✅	❌	❌	❌	❌	❌	❌	1
Online Convex Optimization Over Erdos-Renyi Random Networks	✅	❌	✅	❌	❌	❌	✅	3
Online Decision Based Visual Tracking via Reinforcement Learning	✅	❌	✅	❌	✅	❌	✅	4
Online Fast Adaptation and Knowledge Accumulation (OSAKA): a New Approach to Continual Learning	✅	✅	✅	✅	❌	❌	✅	5
Online Influence Maximization under Linear Threshold Model	✅	❌	❌	❌	❌	❌	❌	1
Online Learning in Contextual Bandits using Gated Linear Networks	✅	✅	✅	❌	❌	❌	✅	4
Online Learning with Primary and Secondary Losses	✅	❌	❌	❌	❌	❌	❌	1
Online Linear Optimization with Many Hints	✅	❌	❌	❌	❌	❌	❌	1
Online MAP Inference of Determinantal Point Processes	✅	❌	✅	❌	❌	❌	✅	3
Online Matrix Completion with Side Information	✅	❌	❌	❌	❌	❌	✅	2
Online Meta-Critic Learning for Off-Policy Actor-Critic Methods	✅	✅	✅	❌	❌	❌	✅	4
Online Multitask Learning with Long-Term Memory	✅	❌	❌	❌	❌	❌	❌	1
Online Neural Connectivity Estimation with Noisy Group Testing	✅	✅	❌	❌	❌	✅	✅	4
Online Non-Convex Optimization with Imperfect Feedback	✅	❌	❌	❌	❌	❌	❌	1
Online Optimization with Memory and Competitive Control	✅	❌	❌	❌	❌	❌	❌	1
Online Planning with Lookahead Policies	✅	❌	❌	❌	❌	❌	❌	1
Online Robust Regression via SGD on the l1 loss	❌	❌	❌	❌	❌	❌	✅	1
Online Sinkhorn: Optimal Transport distances from sample streams	✅	❌	✅	❌	❌	❌	✅	3
Online Structured Meta-learning	✅	❌	✅	❌	❌	❌	✅	3
Online learning with dynamics: A minimax perspective	❌	❌	❌	❌	❌	❌	❌	0
Open Graph Benchmark: Datasets for Machine Learning on Graphs	❌	✅	✅	✅	✅	❌	✅	5
Optimal Adaptive Electrode Selection to Maximize Simultaneously Recorded Neuron Yield	❌	✅	✅	✅	❌	❌	✅	4
Optimal Algorithms for Stochastic Multi-Armed Bandits with Heavy Tailed Rewards	✅	❌	❌	❌	❌	❌	✅	2
Optimal Approximation - Smoothness Tradeoffs for Soft-Max Functions	❌	❌	❌	❌	❌	❌	❌	0
Optimal Best-arm Identification in Linear Bandits	✅	❌	❌	❌	❌	❌	✅	2
Optimal Epoch Stochastic Gradient Descent Ascent Methods for Min-Max Optimization	✅	❌	❌	❌	❌	❌	❌	1
Optimal Iterative Sketching Methods with the Subsampled Randomized Hadamard Transform	❌	❌	✅	❌	❌	❌	✅	2
Optimal Learning from Verified Training Data	✅	❌	✅	✅	❌	✅	✅	5
Optimal Lottery Tickets via Subset Sum: Logarithmic Over-Parameterization is Sufficient	❌	❌	✅	❌	✅	❌	✅	3
Optimal Prediction of the Number of Unseen Species with Multiplicity	❌	❌	❌	❌	❌	❌	✅	1
Optimal Private Median Estimation under Minimal Distributional Assumptions	✅	❌	✅	❌	❌	❌	✅	3
Optimal Query Complexity of Secure Stochastic Convex Optimization	✅	❌	❌	❌	❌	❌	❌	1
Optimal Robustness-Consistency Trade-offs for Learning-Augmented Online Algorithms	✅	❌	❌	❌	❌	❌	❌	1
Optimal Variance Control of the Score-Function Gradient Estimator for Importance-Weighted Bounds	❌	✅	✅	✅	❌	❌	✅	4
Optimal and Practical Algorithms for Smooth and Strongly Convex Decentralized Optimization	✅	❌	✅	❌	❌	❌	✅	3
Optimal visual search based on a model of target detectability in natural images	❌	✅	✅	✅	✅	❌	✅	5
Optimally Deceiving a Learning Leader in Stackelberg Games	❌	❌	❌	❌	❌	❌	❌	0
Optimistic Dual Extrapolation for Coherent Non-monotone Variational Inequalities	✅	❌	❌	❌	❌	❌	❌	1
Optimization and Generalization Analysis of Transduction through Gradient Boosting and Application to Multi-scale Graph Neural Networks	✅	✅	✅	❌	❌	❌	❌	3
Optimization and Generalization of Shallow Neural Networks with Quadratic Activation Functions	❌	❌	❌	❌	❌	❌	✅	1
Optimizing Mode Connectivity via Neuron Alignment	✅	✅	✅	✅	✅	❌	✅	6
Optimizing Neural Networks via Koopman Operator Theory	✅	❌	✅	❌	❌	❌	✅	3
OrganITE: Optimal transplant donor organ offering using an individual treatment effect	✅	❌	❌	✅	❌	❌	❌	2
Organizing recurrent network dynamics by task-computation to enable continual learning	❌	❌	✅	❌	❌	❌	✅	2
Outlier Robust Mean Estimation with Subgaussian Rates via Stability	❌	❌	❌	❌	❌	❌	❌	0
Over-parameterized Adversarial Training: An Analysis Overcoming the Curse of Dimensionality	✅	❌	✅	❌	❌	❌	❌	2
Overfitting Can Be Harmless for Basis Pursuit, But Only to a Degree	❌	✅	❌	❌	❌	❌	❌	1
PAC-Bayes Analysis Beyond the Usual Bounds	❌	❌	❌	❌	❌	❌	❌	0
PAC-Bayes Learning Bounds for Sample-Dependent Priors	❌	❌	❌	❌	❌	❌	❌	0
PAC-Bayesian Bound for the Conditional Value at Risk	❌	❌	❌	❌	❌	❌	❌	0
PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning	✅	❌	✅	❌	❌	❌	❌	2
PEP: Parameter Ensembling by Perturbation	❌	❌	✅	✅	❌	❌	✅	3
PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks	✅	✅	✅	✅	❌	❌	✅	5
PIE-NET: Parametric Inference of Point Cloud Edges	❌	❌	✅	❌	✅	❌	✅	3
PLANS: Neuro-Symbolic Program Learning from Videos	❌	✅	✅	✅	✅	❌	❌	4
PLLay: Efficient Topological Layer based on Persistent Landscapes	✅	✅	✅	❌	❌	✅	✅	5
POLY-HOOT: Monte-Carlo Planning in Continuous Space MDPs with Non-Asymptotic Analysis	✅	❌	✅	❌	✅	❌	❌	3
POMDPs in Continuous Time and Discrete Spaces	❌	✅	❌	❌	❌	❌	❌	1
POMO: Policy Optimization with Multiple Optima for Reinforcement Learning	✅	✅	✅	✅	✅	❌	✅	6
PRANK: motion Prediction based on RANKing	❌	❌	✅	✅	✅	❌	✅	4
Parabolic Approximation Line Search for DNNs	✅	❌	✅	❌	✅	✅	✅	5
Parameterized Explainer for Graph Neural Network	✅	✅	✅	❌	❌	❌	❌	3
Parametric Instance Classification for Unsupervised Visual Feature learning	❌	✅	✅	✅	✅	❌	✅	5
Part-dependent Label Noise: Towards Instance-dependent Label Noise	✅	✅	✅	✅	✅	❌	✅	6
Partial Optimal Tranport with applications on Positive-Unlabeled Learning	✅	✅	✅	❌	❌	❌	✅	4
Partially View-aligned Clustering	✅	❌	✅	✅	✅	❌	✅	5
Passport-aware Normalization for Deep Model Protection	❌	❌	✅	❌	❌	❌	✅	2
Patch2Self: Denoising Diffusion MRI with Self-Supervised Learning	✅	❌	✅	✅	❌	❌	✅	4
Path Integral Based Convolution and Pooling for Graph Neural Networks	❌	✅	✅	✅	✅	❌	✅	5
Path Sample-Analytic Gradient Estimators for Stochastic Binary Networks	✅	✅	✅	❌	❌	❌	✅	4
Penalized Langevin dynamics with vanishing penalty for smooth and log-concave targets	❌	❌	❌	❌	❌	❌	❌	0
Permute-and-Flip: A new mechanism for differentially private selection	✅	❌	✅	❌	❌	❌	❌	2
Personalized Federated Learning with Moreau Envelopes	✅	✅	✅	✅	❌	✅	✅	6
Personalized Federated Learning with Theoretical Guarantees: A Model-Agnostic Meta-Learning Approach	✅	❌	✅	❌	❌	❌	✅	3
Perturbing Across the Feature Hierarchy to Improve Standard and Strict Blackbox Attack Transferability	❌	❌	✅	✅	❌	❌	✅	3
Phase retrieval in high dimensions: Statistical and computational phase transitions	❌	❌	❌	❌	❌	❌	❌	0
Pipeline PSRO: A Scalable Approach for Finding Approximate Nash Equilibria in Large Games	✅	✅	❌	❌	❌	❌	✅	3
Pixel-Level Cycle Association: A New Perspective for Domain Adaptive Semantic Segmentation	❌	✅	✅	✅	❌	❌	✅	4
PlanGAN: Model-based Planning With Sparse Rewards and Multiple Goals	✅	❌	✅	❌	❌	❌	✅	3
Planning in Markov Decision Processes with Gap-Dependent Sample Complexity	✅	✅	❌	❌	❌	❌	✅	3
Planning with General Objective Functions: Going Beyond Total Rewards	✅	❌	❌	❌	❌	❌	❌	1
Point process models for sequence detection in high-dimensional neural spike trains	❌	✅	✅	✅	✅	❌	✅	5
Pointer Graph Networks	✅	✅	❌	✅	❌	❌	✅	4
Policy Improvement via Imitation of Multiple Oracles	✅	✅	✅	❌	❌	❌	✅	4
Polynomial-Time Computation of Optimal Correlated Equilibria in Two-Player Extensive-Form Games with Public Chance Moves and Beyond	✅	❌	✅	❌	✅	✅	✅	5
Pontryagin Differentiable Programming: An End-to-End Learning and Control Framework	✅	✅	❌	❌	❌	❌	✅	3
Position-based Scaled Gradient for Model Quantization and Pruning	❌	✅	✅	❌	❌	❌	✅	3
Post-training Iterative Hierarchical Data Augmentation for Deep Networks	✅	❌	✅	✅	❌	❌	✅	4
Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Counts	❌	✅	✅	✅	❌	❌	✅	4
Posterior Re-calibration for Imbalanced Datasets	✅	✅	✅	✅	❌	❌	❌	4
Practical Low-Rank Communication Compression in Decentralized Deep Learning	✅	✅	✅	❌	❌	❌	✅	4
Practical No-box Adversarial Attacks against DNNs	❌	✅	✅	❌	✅	❌	✅	4
Practical Quasi-Newton Methods for Training Deep Neural Networks	✅	✅	✅	❌	✅	❌	✅	5
Pre-training via Paraphrasing	❌	❌	✅	❌	❌	❌	✅	2
Precise expressions for random projections: Low-rank approximation and randomized Newton	❌	❌	✅	❌	❌	❌	❌	1
Predicting Training Time Without Training	❌	❌	✅	❌	❌	❌	✅	2
Prediction with Corrupted Expert Advice	❌	❌	❌	❌	❌	❌	✅	1
Predictive Information Accelerates Learning in RL	✅	✅	✅	❌	❌	❌	✅	4
Predictive coding in balanced neural networks with noise, chaos and delays	❌	❌	❌	❌	❌	❌	✅	1
Predictive inference is free with the jackknife+-after-bootstrap	✅	✅	✅	❌	❌	❌	✅	4
Preference learning along multiple criteria: A game-theoretic perspective	❌	❌	❌	❌	❌	❌	✅	1
Preference-based Reinforcement Learning with Finite-Time Guarantees	✅	❌	❌	❌	❌	❌	✅	2
Primal Dual Interpretation of the Proximal Stochastic Gradient Langevin Algorithm	❌	❌	❌	❌	❌	❌	❌	0
Primal-Dual Mesh Convolutional Neural Networks	❌	✅	✅	❌	❌	❌	✅	3
Principal Neighbourhood Aggregation for Graph Nets	❌	✅	✅	✅	❌	❌	✅	4
Privacy Amplification via Random Check-Ins	✅	❌	❌	❌	❌	❌	❌	1
Private Identity Testing for High-Dimensional Distributions	✅	❌	❌	❌	❌	❌	❌	1
Private Learning of Halfspaces: Simplifying the Construction and Reducing the Sample Complexity	✅	❌	❌	❌	❌	❌	❌	1
Probabilistic Active Meta-Learning	✅	❌	❌	❌	❌	❌	✅	2
Probabilistic Circuits for Variational Inference in Discrete Graphical Models	✅	✅	✅	❌	❌	❌	❌	3
Probabilistic Fair Clustering	✅	❌	✅	❌	✅	✅	✅	5
Probabilistic Inference with Algebraic Constraints: Theoretical Limits and Practical Approximations	✅	❌	❌	❌	❌	❌	✅	2
Probabilistic Linear Solvers for Machine Learning	✅	✅	✅	❌	❌	❌	✅	4
Probabilistic Orientation Estimation with Matrix Fisher Distributions	❌	✅	✅	✅	❌	❌	✅	4
Probabilistic Time Series Forecasting with Shape and Temporal Diversity	✅	✅	✅	✅	❌	❌	❌	4
Probably Approximately Correct Constrained Learning	✅	❌	✅	❌	❌	❌	✅	3
Profile Entropy: A Fundamental Measure for the Learnability and Compressibility of Distributions	✅	❌	❌	❌	❌	❌	❌	1
Program Synthesis with Pragmatic Communication	❌	✅	❌	❌	❌	❌	✅	2
Projected Stein Variational Gradient Descent	✅	✅	✅	❌	✅	❌	✅	5
Projection Efficient Subgradient Method and Optimal Nonsmooth Frank-Wolfe Method	✅	✅	✅	❌	❌	❌	❌	3
Projection Robust Wasserstein Distance and Riemannian Optimization	✅	❌	✅	❌	❌	❌	✅	3
Promoting Coordination through Policy Regularization in Multi-Agent Deep Reinforcement Learning	✅	❌	✅	❌	❌	❌	✅	3
Promoting Stochasticity for Expressive Policies via a Simple and Efficient Regularization Method	✅	❌	✅	❌	✅	❌	✅	4
Prophet Attention: Predicting Attention with Future Attention	❌	❌	✅	✅	✅	❌	✅	4
Provable Online CP/PARAFAC Decomposition of a Structured Tensor via Dictionary Learning	✅	✅	❌	❌	❌	❌	✅	3
Provable Overlapping Community Detection in Weighted Graphs	✅	❌	✅	❌	❌	❌	✅	3
Provably Consistent Partial-Label Learning	✅	❌	✅	✅	❌	❌	✅	4
Provably Efficient Exploration for Reinforcement Learning Using Unsupervised Learning	✅	✅	❌	❌	❌	❌	❌	2
Provably Efficient Neural Estimation of Structural Equation Models: An Adversarial Approach	✅	❌	❌	❌	❌	❌	❌	1
Provably Efficient Neural GTD for Off-Policy Learning	✅	❌	❌	❌	❌	❌	✅	2
Provably Efficient Online Hyperparameter Optimization with Population-Based Bandits	✅	✅	✅	❌	❌	❌	✅	4
Provably Efficient Reinforcement Learning with Kernel and Neural Function Approximations	✅	❌	❌	❌	❌	❌	❌	1
Provably Efficient Reward-Agnostic Navigation with Linear Value Iteration	✅	❌	❌	❌	❌	❌	❌	1
Provably Good Batch Off-Policy Reinforcement Learning Without Great Exploration	✅	❌	✅	❌	❌	❌	✅	3
Provably Robust Metric Learning	✅	❌	✅	❌	✅	❌	❌	3
Provably adaptive reinforcement learning in metric spaces	✅	❌	❌	❌	❌	❌	❌	1
Proximal Mapping for Deep Regularization	❌	✅	✅	❌	✅	❌	✅	4
Proximity Operator of the Matrix Perspective Function and its Applications	✅	❌	❌	❌	✅	✅	❌	3
Pruning Filter in Filter	❌	✅	✅	❌	❌	❌	✅	3
Pruning neural networks without any data by iteratively conserving synaptic flow	✅	✅	✅	❌	❌	❌	❌	3
Pushing the Limits of Narrow Precision Inferencing at Cloud Scale with Microsoft Floating Point	❌	❌	✅	❌	✅	❌	✅	3
PyGlove: Symbolic Programming for Automated Machine Learning	❌	✅	✅	✅	✅	❌	✅	5
Quantifying Learnability and Describability of Visual Concepts Emerging in Representation Learning	❌	❌	✅	❌	❌	❌	✅	2
Quantifying the Empirical Wasserstein Distance to a Set of Measures: Beating the Curse of Dimensionality	❌	❌	❌	❌	✅	❌	✅	2
Quantile Propagation for Wasserstein-Approximate Gaussian Processes	✅	✅	✅	✅	❌	❌	✅	5
Quantitative Propagation of Chaos for SGD in Wide Neural Networks	❌	❌	✅	❌	❌	❌	✅	2
Quantized Variational Inference	✅	✅	✅	❌	❌	✅	✅	5
R-learning in actor-critic model offers a biologically relevant mechanism for sequential decision-making	❌	❌	❌	❌	❌	❌	❌	0
RANet: Region Attention Network for Semantic Segmentation	❌	✅	✅	✅	✅	❌	✅	5
RATT: Recurrent Attention to Transient Tasks for Continual Image Captioning	❌	✅	✅	✅	✅	❌	✅	5
RD$^2$: Reward Decomposition with Representation Decomposition	✅	❌	✅	❌	❌	❌	❌	2
RELATE: Physically Plausible Multi-Object Scene Synthesis Using Structured Latent Spaces	❌	✅	✅	❌	❌	❌	✅	3
RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learning	❌	✅	✅	✅	❌	❌	❌	3
RNNPool: Efficient Non-linear Pooling for RAM Constrained Inference	✅	✅	✅	✅	✅	❌	❌	5
RSKDD-Net: Random Sample-based Keypoint Detector and Descriptor	❌	✅	✅	✅	✅	❌	✅	5
RandAugment: Practical Automated Data Augmentation with a Reduced Search Space	✅	✅	✅	✅	❌	❌	✅	5
Random Reshuffling is Not Always Better	✅	❌	❌	❌	❌	❌	✅	2
Random Reshuffling: Simple Analysis with Vast Improvements	✅	✅	✅	❌	❌	❌	✅	4
Random Walk Graph Neural Networks	❌	❌	✅	✅	❌	❌	✅	3
Randomized tests for high-dimensional regression: A more efficient and powerful solution	✅	❌	❌	❌	❌	❌	✅	2
Rankmax: An Adaptive Projection Alternative to the Softmax Function	✅	❌	✅	✅	❌	❌	✅	4
Ratio Trace Formulation of Wasserstein Discriminant Analysis	✅	❌	✅	❌	❌	❌	✅	3
Rational neural networks	❌	✅	✅	❌	❌	❌	✅	3
Re-Examining Linear Embeddings for High-Dimensional Bayesian Optimization	✅	✅	✅	❌	❌	❌	❌	3
Real World Games Look Like Spinning Tops	❌	❌	❌	❌	❌	❌	✅	1
Reasoning about Uncertainties in Discrete-Time Dynamical Systems using Polynomial Forms.	❌	❌	✅	❌	❌	❌	✅	2
Reciprocal Adversarial Learning via Characteristic Functions	✅	✅	✅	❌	❌	❌	✅	4
Reconciling Modern Deep Learning with Traditional Optimization Analyses: The Intrinsic Learning Rate	❌	❌	✅	❌	❌	❌	✅	2
Reconsidering Generative Objectives For Counterfactual Reasoning	✅	✅	✅	✅	❌	❌	✅	5
Reconstructing Perceptive Images from Brain Activity by Shape-Semantic GAN	❌	❌	✅	✅	❌	❌	✅	3
Recovery of sparse linear classifiers from mixture of responses	✅	❌	✅	❌	❌	❌	❌	2
Recurrent Quantum Neural Networks	❌	❌	✅	✅	❌	❌	✅	3
Recurrent Switching Dynamical Systems Models for Multiple Interacting Neural Populations	❌	✅	❌	✅	❌	❌	✅	3
Recursive Inference for Variational Autoencoders	✅	✅	✅	✅	✅	❌	✅	6
Reducing Adversarially Robust Learning to Non-Robust PAC Learning	✅	❌	❌	❌	❌	❌	❌	1
Refactoring Policy for Compositional Generalizability using Self-Supervised Object Proposals	❌	❌	✅	❌	❌	❌	✅	2
Regression with reject option and application to kNN	❌	✅	✅	✅	❌	❌	✅	4
Regret Bounds without Lipschitz Continuity: Online Learning with Relative-Lipschitz Losses	✅	❌	❌	❌	❌	❌	❌	1
Regret in Online Recommendation Systems	✅	❌	❌	❌	❌	❌	❌	1
Regularized linear autoencoders recover the principal components, eventually	✅	✅	✅	❌	❌	❌	❌	3
Regularizing Black-box Models for Improved Interpretability	✅	✅	✅	❌	✅	❌	✅	5
Regularizing Towards Permutation Invariance In Recurrent Models	❌	❌	✅	❌	❌	❌	❌	1
Reinforced Molecular Optimization with Neighborhood-Controlled Grammars	❌	✅	✅	❌	❌	❌	✅	3
Reinforcement Learning for Control with Multiple Frequencies	✅	❌	✅	❌	❌	❌	✅	3
Reinforcement Learning in Factored MDPs: Oracle-Efficient Algorithms and Tighter Regret Bounds for the Non-Episodic Setting	✅	❌	✅	❌	❌	❌	✅	3
Reinforcement Learning with Augmented Data	❌	✅	✅	❌	❌	❌	✅	3
Reinforcement Learning with Combinatorial Actions: An Application to Vehicle Routing	❌	❌	✅	❌	❌	✅	✅	3
Reinforcement Learning with Feedback Graphs	✅	❌	❌	❌	❌	❌	❌	1
Reinforcement Learning with General Value Function Approximation: Provably Efficient Approach via Bounded Eluder Dimension	✅	❌	❌	❌	❌	❌	❌	1
Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D	❌	✅	✅	✅	❌	❌	✅	4
RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder	❌	✅	✅	✅	✅	✅	✅	6
Relative gradient optimization of the Jacobian term in unsupervised deep learning	❌	✅	✅	✅	✅	❌	✅	5
Reliable Graph Neural Networks via Robust Aggregation	❌	✅	✅	✅	✅	❌	✅	5
Removing Bias in Multi-modal Classifiers: Regularization by Maximizing Functional Entropies	❌	❌	✅	✅	❌	❌	✅	3
RepPoints v2: Verification Meets Regression for Object Detection	❌	✅	✅	✅	✅	❌	✅	5
Reparameterizing Mirror Descent as Gradient Descent	❌	❌	❌	❌	❌	❌	❌	0
Replica-Exchange Nos\'e-Hoover Dynamics for Bayesian Learning on Large Datasets	✅	❌	✅	❌	✅	❌	✅	4
Representation Learning for Integrating Multi-domain Outcomes to Optimize Individualized Treatment	❌	❌	✅	✅	✅	❌	✅	4
Rescuing neural spike train models from bad MLE	❌	✅	✅	✅	❌	❌	✅	4
Reservoir Computing meets Recurrent Kernels and Structured Transforms	✅	✅	✅	❌	✅	❌	❌	4
Residual Distillation: Towards Portable Deep Neural Networks without Shortcuts	✅	✅	✅	✅	❌	❌	✅	5
Residual Force Control for Agile Human Behavior Imitation and Extended Motion Synthesis	✅	✅	✅	✅	✅	❌	✅	6
Restless-UCB, an Efficient and Low-complexity Algorithm for Online Restless Bandits	✅	❌	✅	❌	✅	❌	✅	4
Restoring Negative Information in Few-Shot Object Detection	❌	✅	✅	✅	❌	❌	✅	4
Rethinking Importance Weighting for Deep Learning under Distribution Shift	✅	✅	✅	✅	❌	❌	✅	5
Rethinking Learnable Tree Filter for Generic Feature Transform	✅	✅	✅	✅	❌	❌	✅	5
Rethinking Pre-training and Self-training	❌	✅	✅	✅	❌	❌	✅	4
Rethinking pooling in graph neural networks	❌	✅	✅	✅	❌	❌	✅	4
Rethinking the Value of Labels for Improving Class-Imbalanced Learning	❌	✅	✅	❌	❌	❌	✅	3
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks	❌	✅	✅	✅	❌	❌	✅	4
RetroXpert: Decompose Retrosynthesis Prediction Like A Chemist	❌	✅	✅	✅	✅	❌	✅	5
Reverse-engineering recurrent neural network solutions to a hierarchical inference task for mice	❌	✅	✅	✅	❌	✅	✅	5
Revisiting Frank-Wolfe for Polytopes: Strict Complementarity and Sparsity	✅	❌	❌	❌	❌	❌	✅	2
Revisiting Parameter Sharing for Automatic Neural Channel Number Search	✅	✅	✅	❌	✅	❌	✅	5
Revisiting the Sample Complexity of Sparse Spectrum Approximation of Gaussian Processes	❌	✅	✅	❌	✅	❌	❌	3
Reward Propagation Using Graph Convolutional Networks	✅	❌	✅	❌	✅	❌	✅	4
Reward-rational (implicit) choice: A unifying formalism for reward learning	❌	❌	❌	❌	❌	❌	❌	0
Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement	✅	✅	✅	❌	❌	❌	❌	3
Ridge Rider: Finding Diverse Solutions by Following Eigenvectors of the Hessian	✅	✅	✅	❌	❌	❌	✅	4
Riemannian Continuous Normalizing Flows	❌	❌	✅	❌	❌	❌	✅	2
Risk-Sensitive Reinforcement Learning: Near-Optimal Risk-Sample Tradeoff in Regret	✅	❌	❌	❌	❌	❌	❌	1
Robust Correction of Sampling Bias using Cumulative Distribution Functions	✅	❌	✅	✅	❌	❌	✅	4
Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations	✅	✅	✅	❌	❌	❌	✅	4
Robust Density Estimation under Besov IPM Losses	❌	❌	❌	❌	❌	❌	❌	0
Robust Disentanglement of a Few Factors at a Time using rPU-VAE	✅	✅	✅	✅	❌	❌	❌	4
Robust Federated Learning: The Case of Affine Distribution Shifts	✅	❌	✅	❌	❌	❌	✅	3
Robust Gaussian Covariance Estimation in Nearly-Matrix Multiplication Time	✅	❌	❌	❌	❌	❌	❌	1
Robust Meta-learning for Mixed Linear Regression with Small Batches	✅	❌	❌	❌	❌	❌	❌	1
Robust Multi-Agent Reinforcement Learning with Model Uncertainty	✅	❌	✅	❌	❌	❌	✅	3
Robust Multi-Object Matching via Iterative Reweighting of the Graph Connection Laplacian	✅	❌	✅	❌	❌	❌	✅	3
Robust Optimal Transport with Applications in Generative Modeling and Domain Adaptation	✅	✅	✅	❌	❌	❌	✅	4
Robust Optimization for Fairness with Noisy Protected Groups	✅	✅	✅	✅	❌	❌	✅	5
Robust Persistence Diagrams using Reproducing Kernels	❌	✅	✅	❌	❌	❌	✅	3
Robust Pre-Training by Adversarial Contrastive Learning	✅	✅	✅	✅	❌	❌	✅	5
Robust Quantization: One Model to Rule Them All	❌	✅	✅	❌	❌	❌	❌	2
Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Over-parameterization	❌	✅	✅	❌	❌	❌	✅	3
Robust Recursive Partitioning for Heterogeneous Treatment Effects with Uncertainty Quantification	✅	✅	✅	❌	❌	❌	✅	4
Robust Reinforcement Learning via Adversarial training with Langevin Dynamics	✅	❌	✅	❌	❌	❌	✅	3
Robust Sequence Submodular Maximization	✅	❌	❌	❌	❌	❌	❌	1
Robust Sub-Gaussian Principal Component Analysis and Width-Independent Schatten Packing	✅	❌	❌	❌	❌	❌	❌	1
Robust and Heavy-Tailed Mean Estimation Made Simple, via Regret Minimization	✅	❌	❌	❌	❌	❌	❌	1
Robust compressed sensing using generative models	✅	✅	✅	❌	❌	❌	✅	4
Robust large-margin learning in hyperbolic space	✅	❌	✅	❌	❌	❌	✅	3
Robust, Accurate Stochastic Optimization for Variational Inference	✅	❌	✅	❌	❌	❌	✅	3
Robust-Adaptive Control of Linear Systems: beyond Quadratic Costs	✅	✅	✅	❌	❌	❌	❌	3
Robustness Analysis of Non-Convex Stochastic Gradient Descent using Biased Expectations	✅	❌	✅	❌	❌	❌	✅	3
Robustness of Bayesian Neural Networks to Gradient-Based Attacks	❌	✅	✅	❌	❌	❌	✅	3
Robustness of Community Detection to Random Geometric Perturbations	❌	❌	❌	❌	❌	❌	✅	1
Rotated Binary Neural Network	❌	✅	✅	❌	❌	❌	✅	3
Rotation-Invariant Local-to-Global Representation Learning for 3D Point Cloud	❌	✅	✅	✅	❌	❌	❌	3
SAC: Accelerating and Structuring Self-Attention via Sparse Adaptive Connection	❌	❌	✅	✅	✅	❌	✅	4
SCOP: Scientific Control for Reliable Neural Network Pruning	❌	✅	✅	✅	✅	❌	✅	5
SDF-SRN: Learning Signed Distance 3D Object Reconstruction from Static Images	❌	❌	✅	✅	❌	❌	✅	3
SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks	❌	✅	✅	❌	❌	❌	❌	2
SEVIR : A Storm Event Imagery Dataset for Deep Learning Applications in Radar and Satellite Meteorology	❌	✅	✅	✅	✅	❌	✅	5
SGD with shuffling: optimal rates without component convexity and large epoch requirements	❌	❌	❌	❌	❌	❌	❌	0
SIRI: Spatial Relation Induced Network For Spatial Description Resolution	❌	✅	✅	✅	✅	❌	✅	5
SLIP: Learning to predict in unknown dynamical systems with long-term memory	✅	❌	❌	❌	❌	❌	✅	2
SMYRF - Efficient Attention using Asymmetric Clustering	❌	✅	✅	❌	✅	❌	✅	4
SOLOv2: Dynamic and Fast Instance Segmentation	✅	✅	✅	✅	✅	❌	✅	6
STEER : Simple Temporal Regularization For Neural ODE	❌	❌	✅	✅	❌	❌	✅	3
STLnet: Signal Temporal Logic Enforced Multivariate Recurrent Neural Networks	✅	❌	✅	❌	✅	❌	❌	3
SURF: A Simple, Universal, Robust, Fast Distribution Learning Algorithm	❌	❌	✅	❌	❌	❌	✅	2
SVGD as a kernelized Wasserstein gradient flow of the chi-squared divergence	✅	❌	❌	❌	❌	❌	✅	2
Safe Reinforcement Learning via Curriculum Induction	✅	✅	✅	❌	❌	❌	✅	4
Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction	✅	❌	❌	❌	❌	❌	❌	1
Sample Complexity of Uniform Convergence for Multicalibration	❌	❌	❌	❌	❌	❌	❌	0
Sample Efficient Reinforcement Learning via Low-Rank Matrix Estimation	✅	❌	❌	❌	❌	❌	✅	2
Sample complexity and effective dimension for regression on manifolds	❌	❌	❌	❌	❌	❌	❌	0
Sample-Efficient Optimization in the Latent Space of Deep Generative Models via Weighted Retraining	✅	✅	✅	✅	❌	❌	✅	5
Sample-Efficient Reinforcement Learning of Undercomplete POMDPs	✅	❌	❌	❌	❌	❌	❌	1
Sampling from a k-DPP without looking at all items	✅	✅	✅	❌	✅	❌	✅	5
Sampling-Decomposable Generative Adversarial Recommender	✅	❌	✅	✅	✅	❌	✅	5
Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot	❌	✅	✅	❌	❌	❌	✅	3
Scalable Belief Propagation via Relaxed Scheduling	❌	✅	✅	❌	✅	✅	✅	5
Scalable Graph Neural Networks via Bidirectional Propagation	✅	❌	✅	✅	✅	❌	✅	5
Scalable Multi-Agent Reinforcement Learning for Networked Systems with Average Reward	✅	❌	❌	❌	❌	❌	✅	2
ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training	✅	❌	✅	❌	✅	❌	✅	4
Scattering GCN: Overcoming Oversmoothness in Graph Convolutional Networks	❌	❌	✅	✅	❌	❌	❌	2
Searching for Low-Bit Weights in Quantized Neural Networks	✅	❌	✅	❌	❌	❌	✅	3
Second Order Optimality in Decentralized Non-Convex Optimization via Perturbed Gradient Tracking	✅	❌	✅	❌	❌	❌	✅	3
Second Order PAC-Bayesian Bounds for the Weighted Majority Vote	❌	✅	✅	✅	❌	❌	✅	4
Secretary and Online Matching Problems with Machine Learned Advice	✅	❌	❌	❌	❌	❌	❌	1
Security Analysis of Safe and Seldonian Reinforcement Learning Algorithms	✅	❌	✅	❌	❌	✅	✅	4
See, Hear, Explore: Curiosity via Audio-Visual Association	❌	✅	❌	❌	❌	❌	✅	2
Self-Adaptive Training: beyond Empirical Risk Minimization	✅	✅	✅	✅	❌	❌	✅	5
Self-Adaptively Learning to Demoiré from Focused and Defocused Image Pairs	❌	❌	✅	❌	✅	✅	✅	4
Self-Distillation Amplifies Regularization in Hilbert Space	❌	✅	✅	❌	❌	❌	❌	2
Self-Distillation as Instance-Specific Label Smoothing	❌	❌	✅	✅	❌	❌	✅	3
Self-Imitation Learning via Generalized Lower Bound Q-learning	❌	✅	✅	❌	❌	❌	✅	3
Self-Learning Transformations for Improving Gaze and Head Redirection	❌	✅	✅	❌	❌	❌	✅	3
Self-Paced Deep Reinforcement Learning	✅	✅	✅	❌	❌	❌	✅	4
Self-Supervised Few-Shot Learning on Point Clouds	❌	❌	✅	❌	❌	❌	❌	1
Self-Supervised Generative Adversarial Compression	❌	❌	✅	❌	✅	❌	✅	3
Self-Supervised Graph Transformer on Large-Scale Molecular Data	❌	❌	✅	✅	✅	❌	✅	4
Self-Supervised Learning by Cross-Modal Audio-Video Clustering	❌	✅	✅	✅	❌	❌	✅	4
Self-Supervised MultiModal Versatile Networks	❌	✅	✅	✅	✅	❌	✅	5
Self-Supervised Relational Reasoning for Representation Learning	✅	✅	✅	✅	❌	❌	✅	5
Self-Supervised Relationship Probing	❌	❌	✅	✅	✅	❌	✅	4
Self-Supervised Visual Representation Learning from Hierarchical Grouping	❌	❌	✅	✅	❌	❌	✅	3
Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID	✅	✅	✅	❌	❌	❌	✅	4
Self-supervised Auxiliary Learning with Meta-paths for Heterogeneous Graphs	✅	✅	✅	✅	❌	❌	❌	4
Self-supervised Co-Training for Video Representation Learning	❌	✅	✅	✅	❌	❌	✅	4
Self-supervised learning through the eyes of a child	❌	✅	✅	❌	❌	❌	✅	3
Self-training Avoids Using Spurious Features Under Domain Shift	❌	❌	✅	❌	❌	❌	❌	1
Semantic Visual Navigation by Watching YouTube Videos	❌	✅	✅	✅	❌	❌	✅	4
Semi-Supervised Neural Architecture Search	✅	❌	✅	✅	✅	❌	✅	5
Semi-Supervised Partial Label Learning via Confidence-Rated Margin Maximization	✅	❌	✅	✅	❌	❌	✅	4
Semialgebraic Optimization for Lipschitz Constants of ReLU Networks	❌	❌	✅	❌	✅	❌	✅	3
Sense and Sensitivity Analysis: Simple Post-Hoc Analysis of Bias Due to Unobserved Confounding	❌	✅	✅	✅	❌	❌	❌	3
Sequence to Multi-Sequence Learning via Conditional Chain Mapping for Mixture Signals	❌	✅	✅	✅	❌	❌	❌	3
Sequential Bayesian Experimental Design with Variable Cost Structure	✅	❌	❌	❌	❌	❌	✅	2
Set2Graph: Learning Graphs From Sets	❌	❌	❌	✅	❌	❌	✅	2
ShapeFlow: Learnable Deformation Flows Among 3D Shapes	❌	❌	✅	✅	❌	❌	❌	2
Shared Experience Actor-Critic for Multi-Agent Reinforcement Learning	✅	✅	✅	❌	❌	❌	✅	4
Shared Space Transfer Learning for analyzing multi-site fMRI data	❌	✅	✅	✅	✅	✅	✅	6
Sharp Representation Theorems for ReLU Networks with Precise Dependence on Depth	❌	❌	❌	❌	❌	❌	❌	0
Sharp uniform convergence bounds through empirical centralization	❌	✅	❌	❌	❌	❌	✅	2
Sharpened Generalization Bounds based on Conditional Mutual Information and an Application to Noisy, Iterative Algorithms	❌	❌	✅	❌	❌	❌	❌	1
Sharper Generalization Bounds for Pairwise Learning	❌	❌	❌	❌	❌	❌	❌	0
ShiftAddNet: A Hardware-Inspired Deep Network	❌	✅	✅	❌	✅	❌	✅	4
Simple and Fast Algorithm for Binary Integer and Online Linear Programming	✅	❌	❌	❌	❌	❌	❌	1
Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness	✅	✅	✅	❌	❌	❌	✅	4
Simple and Scalable Sparse k-means Clustering via Feature Ranking	✅	❌	✅	❌	❌	❌	✅	3
Simplify and Robustify Negative Sampling for Implicit Collaborative Filtering	✅	✅	✅	✅	❌	❌	✅	5
Simplifying Hamiltonian and Lagrangian Neural Networks via Explicit Constraints	❌	✅	❌	❌	❌	❌	✅	2
Simulating a Primary Visual Cortex at the Front of CNNs Improves Robustness to Image Perturbations	❌	✅	✅	✅	❌	❌	✅	4
Simultaneous Preference and Metric Learning from Paired Comparisons	❌	✅	❌	❌	❌	✅	✅	3
Simultaneously Learning Stochastic and Adversarial Episodic MDPs with Known Transition	✅	❌	❌	❌	❌	❌	❌	1
Sinkhorn Barycenter via Functional Gradient Descent	✅	❌	✅	❌	❌	❌	✅	3
Sinkhorn Natural Gradient for Generative Models	❌	❌	✅	❌	❌	❌	✅	2
Skeleton-bridged Point Completion: From Global Inference to Local Adjustment	❌	❌	✅	✅	❌	❌	✅	3
Sliding Window Algorithms for k-Clustering Problems	✅	✅	✅	❌	❌	❌	✅	4
Small Nash Equilibrium Certificates in Very Large Games	✅	❌	✅	❌	❌	✅	❌	3
Smooth And Consistent Probabilistic Regression Trees	❌	✅	✅	✅	✅	❌	✅	5
Smoothed Analysis of Online and Differentially Private Learning	❌	❌	❌	❌	❌	❌	❌	0
Smoothed Geometry for Robust Attribution	❌	✅	✅	❌	✅	❌	✅	4
Smoothly Bounding User Contributions in Differential Privacy	✅	❌	✅	❌	❌	❌	✅	3
SnapBoost: A Heterogeneous Boosting Machine	✅	❌	✅	✅	✅	✅	✅	6
Soft Contrastive Learning for Visual Localization	❌	✅	✅	❌	❌	❌	✅	3
SoftFlow: Probabilistic Framework for Normalizing Flow on Manifolds	❌	✅	✅	✅	✅	❌	✅	5
Softmax Deep Double Deterministic Policy Gradients	✅	✅	✅	❌	❌	❌	✅	4
Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solvers	❌	✅	❌	❌	❌	❌	✅	2
Space-Time Correspondence as a Contrastive Random Walk	✅	❌	✅	❌	❌	❌	✅	3
Sparse Graphical Memory for Robust Planning	✅	✅	✅	❌	❌	❌	✅	4
Sparse Learning with CART	❌	❌	✅	❌	❌	❌	❌	1
Sparse Spectrum Warped Input Measures for Nonstationary Kernel Learning	✅	✅	✅	❌	✅	❌	✅	5
Sparse Symplectically Integrated Neural Networks	❌	✅	❌	✅	✅	❌	✅	4
Sparse Weight Activation Training	✅	✅	✅	✅	✅	✅	✅	7
Sparse and Continuous Attention Mechanisms	✅	✅	✅	❌	❌	❌	✅	4
Spectra of the Conjugate Kernel and Neural Tangent Kernel for linear-width neural networks	❌	❌	✅	❌	❌	❌	✅	2
Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting	❌	❌	✅	✅	❌	❌	✅	3
Spike and slab variational Bayes for high dimensional logistic regression	✅	✅	❌	❌	❌	❌	✅	3
Spin-Weighted Spherical CNNs	❌	✅	✅	✅	❌	❌	✅	4
Stability of Stochastic Gradient Descent on Nonsmooth Convex Losses	✅	❌	❌	❌	❌	❌	❌	1
Stable and expressive recurrent vision models	❌	✅	✅	✅	✅	❌	✅	5
Stage-wise Conservative Linear Bandits	✅	❌	❌	❌	❌	❌	✅	2
Stateful Posted Pricing with Vanishing Regret via Dynamic Deterministic Markov Decision Processes	✅	❌	❌	❌	❌	❌	❌	1
Stationary Activations for Uncertainty Calibration in Deep Learning	❌	✅	✅	✅	❌	❌	❌	3
Statistical Efficiency of Thompson Sampling for Combinatorial Semi-Bandits	✅	❌	✅	❌	❌	❌	✅	3
Statistical Guarantees of Distributed Nearest Neighbor Classification	✅	❌	✅	❌	✅	❌	❌	3
Statistical Optimal Transport posed as Learning Kernel Embedding	❌	✅	✅	❌	❌	❌	✅	3
Statistical and Topological Properties of Sliced Probability Divergences	❌	✅	✅	❌	❌	❌	✅	3
Statistical control for spatio-temporal MEG/EEG source imaging with desparsified mutli-task Lasso	✅	✅	✅	❌	❌	❌	✅	4
Statistical-Query Lower Bounds via Functional Gradients	✅	❌	❌	❌	❌	❌	❌	1
Steady State Analysis of Episodic Reinforcement Learning	❌	❌	✅	❌	❌	❌	✅	2
Steering Distortions to Preserve Classes and Neighbors in Supervised Dimensionality Reduction	❌	✅	✅	❌	❌	✅	✅	4
Stein Self-Repulsive Dynamics: Benefits From Past Samples	❌	✅	✅	❌	❌	❌	✅	3
Stochastic Deep Gaussian Processes over Graphs	❌	✅	✅	✅	✅	❌	✅	5
Stochastic Gradient Descent in Correlated Settings: A Study on Gaussian Processes	✅	✅	✅	✅	✅	❌	✅	6
Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model	✅	✅	✅	❌	❌	❌	✅	4
Stochastic Normalization	✅	✅	✅	✅	❌	❌	✅	5
Stochastic Normalizing Flows	❌	✅	✅	❌	❌	❌	❌	2
Stochastic Optimization for Performative Prediction	✅	❌	✅	❌	❌	❌	✅	3
Stochastic Optimization with Heavy-Tailed Noise via Accelerated Gradient Clipping	✅	✅	✅	❌	❌	❌	✅	4
Stochastic Optimization with Laggard Data Pipelines	✅	❌	✅	❌	❌	❌	✅	3
Stochastic Recursive Gradient Descent Ascent for Stochastic Nonconvex-Strongly-Concave Minimax Problems	✅	❌	✅	❌	✅	✅	✅	5
Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty	❌	✅	✅	✅	❌	❌	✅	4
Stochastic Stein Discrepancies	✅	✅	✅	❌	❌	❌	✅	4
Stochasticity of Deterministic Gradient Descent: Large Learning Rate for Multiscale Objective Function	❌	❌	✅	❌	❌	❌	✅	2
Storage Efficient and Dynamic Flexible Runtime Channel Pruning via Deep Reinforcement Learning	✅	✅	✅	❌	✅	❌	✅	5
StratLearner: Learning a Strategy for Misinformation Prevention in Social Networks	✅	✅	❌	❌	❌	❌	✅	3
Strictly Batch Imitation Learning by Energy-based Distribution Matching	✅	✅	✅	✅	❌	❌	✅	5
Strongly Incremental Constituency Parsing with Graph Neural Networks	❌	✅	✅	✅	✅	❌	✅	5
Strongly local p-norm-cut algorithms for semi-supervised learning and local graph clustering	✅	✅	✅	❌	✅	❌	✅	5
Structured Convolutions for Efficient Neural Network Design	❌	❌	✅	❌	✅	❌	✅	3
Structured Prediction for Conditional Meta-Learning	✅	✅	✅	✅	✅	❌	✅	6
Sub-linear Regret Bounds for Bayesian Optimisation in Unknown Search Spaces	✅	✅	✅	❌	❌	❌	✅	4
Sub-sampling for Efficient Non-Parametric Bandit Exploration	✅	✅	❌	❌	❌	❌	✅	3
Subgraph Neural Networks	✅	✅	✅	❌	✅	❌	✅	5
Subgroup-based Rank-1 Lattice Quasi-Monte Carlo	❌	❌	✅	❌	❌	❌	✅	2
Submodular Maximization Through Barrier Functions	✅	❌	✅	❌	❌	❌	✅	3
Submodular Meta-Learning	✅	❌	✅	❌	❌	❌	❌	2
Succinct and Robust Multi-Agent Communication With Temporal Message Control	✅	✅	✅	❌	❌	❌	✅	4
Sufficient dimension reduction for classification using principal optimal transport direction	✅	❌	✅	✅	❌	❌	✅	4
SuperLoss: A Generic Loss for Robust Curriculum Learning	❌	❌	✅	✅	❌	❌	✅	3
Supermasks in Superposition	✅	✅	✅	✅	✅	❌	✅	6
Supervised Contrastive Learning	❌	✅	✅	✅	✅	❌	✅	5
SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flows	✅	✅	✅	❌	✅	❌	❌	4
Swapping Autoencoder for Deep Image Manipulation	❌	❌	✅	❌	❌	❌	✅	2
Synbols: Probing Learning Algorithms with Synthetic Datasets	❌	✅	✅	✅	✅	❌	✅	5
Synthesize, Execute and Debug: Learning to Repair for Neural Program Synthesis	✅	❌	✅	✅	❌	❌	✅	4
Synthesizing Tasks for Block-based Programming	❌	✅	✅	❌	❌	❌	✅	3
Synthetic Data Generators -- Sequential and Private	❌	❌	❌	❌	❌	❌	❌	0
System Identification with Biophysical Constraints: A Circuit Model of the Inner Retina	❌	✅	❌	❌	❌	❌	✅	2
TSPNet: Hierarchical Feature Learning via Temporal Semantic Pyramid for Sign Language Translation	❌	✅	✅	✅	✅	❌	✅	5
Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization	✅	✅	✅	❌	❌	❌	✅	4
Taming Discrete Integration via the Boon of Dimensionality	✅	✅	✅	❌	✅	❌	✅	5
Targeted Adversarial Perturbations for Monocular Depth Prediction	✅	❌	✅	✅	✅	❌	✅	5
Task-Agnostic Amortized Inference of Gaussian Process Hyperparameters	❌	✅	✅	✅	❌	❌	✅	4
Task-Agnostic Online Reinforcement Learning with an Infinite Mixture of Gaussian Processes	✅	✅	❌	❌	❌	❌	❌	2
Task-Oriented Feature Distillation	❌	✅	✅	❌	❌	❌	✅	3
Task-Robust Model-Agnostic Meta-Learning	✅	✅	✅	✅	❌	❌	✅	5
Task-agnostic Exploration in Reinforcement Learning	✅	❌	❌	❌	❌	❌	❌	1
TaylorGAN: Neighbor-Augmented Policy Update Towards Sample-Efficient Natural Language Generation	❌	✅	✅	✅	✅	❌	✅	5
Teaching a GAN What Not to Learn	❌	❌	✅	❌	❌	✅	✅	3
Telescoping Density-Ratio Estimation	❌	❌	✅	❌	❌	❌	✅	2
Temporal Positive-unlabeled Learning for Biomedical Hypothesis Generation via Risk Estimation	✅	❌	❌	❌	✅	❌	✅	3
Temporal Spike Sequence Learning via Backpropagation for Deep Spiking Neural Networks	❌	✅	✅	❌	❌	❌	✅	3
Temporal Variability in Implicit Online Learning	✅	❌	✅	❌	❌	❌	✅	3
Tensor Completion Made Practical	✅	✅	❌	❌	❌	❌	✅	3
Testing Determinantal Point Processes	✅	❌	❌	❌	❌	❌	❌	1
Texture Interpolation for Probing Visual Perception	❌	✅	✅	❌	❌	❌	✅	3
The Adaptive Complexity of Maximizing a Gross Substitutes Valuation	✅	❌	❌	❌	❌	❌	✅	2
The Advantage of Conditional Meta-Learning for Biased Regularization and Fine Tuning	✅	✅	✅	❌	❌	❌	✅	4
The All-or-Nothing Phenomenon in Sparse Tensor PCA	❌	❌	❌	❌	❌	❌	❌	0
The Autoencoding Variational Autoencoder	✅	❌	✅	❌	❌	❌	✅	3
The Complete Lasso Tradeoff Diagram	❌	✅	❌	❌	❌	❌	✅	2
The Complexity of Adversarially Robust Proper Learning of Halfspaces with Agnostic Noise	✅	❌	❌	❌	❌	❌	❌	1
The Cone of Silence: Speech Separation by Localization	✅	❌	✅	❌	❌	❌	✅	3
The Convex Relaxation Barrier, Revisited: Tightened Single-Neuron Relaxations for Neural Network Verification	✅	✅	✅	❌	✅	✅	✅	6
The Convolution Exponential and Generalized Sylvester Flows	✅	✅	✅	❌	✅	❌	✅	5
The Devil is in the Detail: A Framework for Macroscopic Prediction via Microscopic Models	✅	❌	✅	❌	❌	❌	✅	3
The Dilemma of TriHard Loss and an Element-Weighted TriHard Loss for Person Re-Identification	❌	✅	✅	❌	❌	❌	✅	3
The Discrete Gaussian for Differential Privacy	✅	✅	❌	❌	❌	❌	❌	2
The Diversified Ensemble Neural Network	✅	❌	✅	✅	✅	❌	✅	5
The Flajolet-Martin Sketch Itself Preserves Differential Privacy: Private Counting with Minimal Space	✅	❌	❌	❌	❌	❌	✅	2
The Generalization-Stability Tradeoff In Neural Network Pruning	❌	✅	✅	❌	❌	❌	✅	3
The Generalized Lasso with Nonlinear Observations and Generative Priors	❌	❌	❌	❌	❌	❌	❌	0
The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes	❌	✅	✅	✅	❌	❌	✅	4
The Implications of Local Correlation on Learning Some Deep Functions	✅	❌	✅	❌	❌	❌	✅	3
The LoCA Regret: A Consistent Metric to Evaluate Model-Based Behavior in Reinforcement Learning	❌	✅	❌	❌	❌	❌	✅	2
The Lottery Ticket Hypothesis for Pre-trained BERT Networks	✅	✅	✅	✅	❌	❌	✅	5
The MAGICAL Benchmark for Robust Imitation	❌	✅	✅	❌	❌	❌	✅	3
The Mean-Squared Error of Double Q-Learning	❌	✅	✅	❌	❌	❌	✅	3
The NetHack Learning Environment	❌	✅	✅	✅	❌	✅	✅	5
The Origins and Prevalence of Texture Bias in Convolutional Neural Networks	❌	❌	✅	✅	❌	❌	✅	3
The Pitfalls of Simplicity Bias in Neural Networks	❌	✅	✅	✅	❌	❌	❌	3
The Potts-Ising model for discrete multivariate data	❌	✅	✅	✅	❌	✅	✅	5
The Power of Comparisons for Actively Learning Linear Classifiers	✅	❌	❌	❌	❌	❌	✅	2
The Power of Predictions in Online Control	✅	❌	❌	❌	❌	❌	✅	2
The Primal-Dual method for Learning Augmented Algorithms	✅	✅	❌	❌	❌	❌	✅	3
The Smoothed Possibility of Social Choice	❌	❌	❌	❌	❌	❌	❌	0
The Statistical Complexity of Early-Stopped Mirror Descent	❌	❌	❌	❌	❌	❌	❌	0
The Statistical Cost of Robust Kernel Hyperparameter Turning	✅	❌	❌	❌	❌	❌	❌	1
The Strong Screening Rule for SLOPE	✅	✅	✅	❌	❌	✅	✅	5
The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks	❌	❌	✅	❌	❌	❌	❌	1
The Value Equivalence Principle for Model-Based Reinforcement Learning	❌	❌	❌	❌	❌	❌	✅	1
The Wasserstein Proximal Gradient Algorithm	❌	❌	❌	❌	❌	❌	✅	1
The interplay between randomness and structure during learning in RNNs	❌	❌	✅	❌	❌	❌	✅	2
The phase diagram of approximation rates for deep neural networks	❌	❌	❌	❌	❌	❌	❌	0
The route to chaos in routing games: When is price of anarchy too optimistic?	❌	❌	❌	❌	❌	❌	❌	0
Theoretical Insights Into Multiclass Classification: A High-dimensional Asymptotic View	❌	❌	❌	❌	❌	❌	✅	1
Theory-Inspired Path-Regularized Differential Network Architecture Search	✅	✅	✅	✅	✅	❌	✅	6
Throughput-Optimal Topology Design for Cross-Silo Federated Learning	✅	✅	✅	❌	✅	❌	✅	5
Thunder: a Fast Coordinate Selection Solver for Sparse Learning	✅	✅	✅	❌	❌	❌	✅	4
Tight First- and Second-Order Regret Bounds for Adversarial Linear Bandits	✅	❌	❌	❌	❌	❌	❌	1
Tight Nonparametric Convergence Rates for Stochastic Gradient Descent under the Noiseless Linear Model	❌	❌	❌	❌	❌	❌	❌	0
Tight last-iterate convergence rates for no-regret learning in multi-player games	❌	❌	❌	❌	❌	❌	❌	0
Time-Reversal Symmetric ODE Network	❌	✅	✅	❌	❌	❌	✅	3
Timeseries Anomaly Detection using Temporal Hierarchical One-Class Network	✅	❌	✅	✅	❌	❌	❌	3
TinyTL: Reduce Memory, Not Parameters for Efficient On-Device Learning	❌	❌	✅	❌	❌	❌	✅	2
Top-KAST: Top-K Always Sparse Training	❌	❌	✅	❌	❌	❌	❌	1
Top-k Training of GANs: Improving GAN Performance by Throwing Away Bad Samples	✅	❌	✅	❌	✅	❌	✅	4
TorsionNet: A Reinforcement Learning Approach to Sequential Conformer Search	✅	✅	❌	❌	❌	❌	✅	3
Toward the Fundamental Limits of Imitation Learning	✅	❌	❌	❌	❌	❌	❌	1
Towards Better Generalization of Adaptive Gradient Methods	✅	❌	✅	✅	❌	❌	✅	4
Towards Convergence Rate Analysis of Random Forests for Classification	✅	❌	❌	❌	❌	❌	❌	1
Towards Crowdsourced Training of Large Neural Networks using Decentralized Mixture-of-Experts	❌	✅	✅	❌	✅	❌	✅	4
Towards Deeper Graph Neural Networks with Differentiable Group Normalization	❌	✅	✅	❌	❌	❌	✅	3
Towards Interpretable Natural Language Understanding with Explanations as Latent Variables	✅	✅	✅	✅	❌	❌	✅	5
Towards Learning Convolutions from Scratch	✅	❌	✅	❌	❌	❌	✅	3
Towards Maximizing the Representation Gap between In-Domain & Out-of-Distribution Examples	❌	✅	✅	❌	❌	❌	❌	2
Towards Minimax Optimal Reinforcement Learning in Factored Markov Decision Processes	✅	❌	❌	❌	❌	❌	❌	1
Towards More Practical Adversarial Attacks on Graph Neural Networks	✅	❌	✅	✅	❌	❌	✅	4
Towards Neural Programming Interfaces	✅	✅	✅	❌	❌	❌	✅	4
Towards Playing Full MOBA Games with Deep Reinforcement Learning	❌	❌	❌	❌	❌	❌	✅	1
Towards Problem-dependent Optimal Learning Rates	❌	❌	❌	❌	❌	❌	❌	0
Towards Safe Policy Improvement for Non-Stationary MDPs	✅	❌	✅	✅	❌	❌	✅	4
Towards Scalable Bayesian Learning of Causal DAGs	✅	✅	✅	❌	❌	❌	✅	4
Towards Scale-Invariant Graph-related Problem Solving by Iterative Homogeneous GNNs	✅	❌	❌	✅	❌	❌	✅	3
Towards Theoretically Understanding Why Sgd Generalizes Better Than Adam in Deep Learning	❌	✅	✅	❌	❌	❌	❌	2
Towards Understanding Hierarchical Learning: Benefits of Neural Representations	✅	❌	❌	❌	❌	❌	❌	1
Towards a Better Global Loss Landscape of GANs	❌	✅	✅	❌	❌	❌	✅	3
Towards a Combinatorial Characterization of Bounded-Memory Learning	❌	❌	❌	❌	❌	❌	❌	0
Towards practical differentially private causal graph discovery	✅	✅	✅	❌	✅	❌	✅	5
Trade-offs and Guarantees of Adversarial Representation Learning for Information Obfuscation	❌	❌	✅	❌	❌	❌	❌	1
Trading Personalization for Accuracy: Data Debugging in Collaborative Filtering	✅	✅	✅	✅	❌	❌	✅	5
Train-by-Reconnect: Decoupling Locations of Weights from Their Values	✅	❌	✅	❌	❌	❌	✅	3
Training Generative Adversarial Networks by Solving Ordinary Differential Equations	✅	✅	✅	❌	❌	❌	✅	4
Training Generative Adversarial Networks with Limited Data	❌	✅	✅	❌	✅	❌	✅	4
Training Linear Finite-State Machines	✅	❌	✅	❌	✅	❌	✅	4
Training Normalizing Flows with the Information Bottleneck for Competitive Generative Classification	❌	✅	✅	❌	❌	❌	✅	3
Training Stronger Baselines for Learning to Optimize	✅	✅	✅	✅	❌	❌	✅	5
Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning	✅	✅	✅	❌	❌	❌	❌	3
Transfer Learning via $\ell_1$ Regularization	✅	❌	✅	✅	❌	❌	✅	4
Transferable Calibration with Lower Bias and Variance in Domain Adaptation	✅	❌	✅	❌	❌	❌	❌	2
Transferable Graph Optimizers for ML Compilers	❌	❌	✅	✅	✅	❌	❌	3
Tree! I am no Tree! I am a low dimensional Hyperbolic Embedding	✅	✅	✅	❌	❌	❌	❌	3
Triple descent and the two kinds of overfitting: where & why do they appear?	❌	✅	❌	❌	❌	❌	✅	2
Truncated Linear Regression in High Dimensions	✅	❌	❌	❌	❌	❌	❌	1
Trust the Model When It Is Confident: Masked Model-based Actor-Critic	✅	❌	✅	❌	❌	❌	✅	3
Truthful Data Acquisition via Peer Prediction	❌	❌	❌	❌	❌	❌	❌	0
UCLID-Net: Single View Reconstruction in Object Space	❌	✅	✅	✅	❌	❌	✅	4
UCSG-NET- Unsupervised Discovering of Constructive Solid Geometry Tree	❌	✅	✅	✅	✅	❌	✅	5
UDH: Universal Deep Hiding for Steganography, Watermarking, and Light Field Messaging	❌	✅	✅	✅	❌	❌	✅	4
UWSOD: Toward Fully-Supervised-Level Capacity Weakly Supervised Object Detection	❌	✅	✅	✅	❌	❌	✅	4
Ultra-Low Precision 4-bit Training of Deep Neural Networks	✅	❌	✅	❌	❌	❌	❌	2
Ultrahyperbolic Representation Learning	✅	❌	✅	❌	❌	❌	✅	3
UnModNet: Learning to Unwrap a Modulo Image for High Dynamic Range Imaging	❌	❌	❌	❌	✅	❌	✅	2
Unbalanced Sobolev Descent	✅	✅	✅	❌	❌	❌	✅	4
Uncertainty Aware Semi-Supervised Learning on Graph Data	❌	✅	✅	❌	❌	❌	❌	2
Uncertainty Quantification for Inferring Hawkes Networks	✅	❌	❌	❌	❌	❌	✅	2
Uncertainty-Aware Learning for Zero-Shot Semantic Segmentation	❌	❌	✅	✅	✅	❌	✅	4
Uncertainty-aware Self-training for Few-shot Text Classification	✅	✅	✅	✅	✅	❌	✅	6
Uncovering the Topology of Time-Varying fMRI Data using Cubical Persistence	❌	✅	✅	✅	❌	❌	✅	4
Understanding Anomaly Detection with Deep Invertible Networks through Hierarchies of Distributions and Features	❌	✅	✅	❌	❌	❌	❌	2
Understanding Approximate Fisher Information for Fast Convergence of Natural Gradient Descent in Wide Neural Networks	❌	✅	✅	❌	❌	❌	✅	3
Understanding Deep Architecture with Reasoning Layer	❌	✅	✅	❌	❌	❌	✅	3
Understanding Double Descent Requires A Fine-Grained Bias-Variance Decomposition	❌	❌	❌	❌	❌	❌	✅	1
Understanding Global Feature Contributions With Additive Importance Measures	✅	✅	✅	✅	❌	❌	❌	4
Understanding Gradient Clipping in Private SGD: A Geometric Perspective	❌	❌	✅	❌	❌	❌	✅	2
Understanding and Exploring the Network with Stochastic Architectures	❌	❌	✅	❌	✅	❌	✅	3
Understanding and Improving Fast Adversarial Training	❌	✅	✅	❌	✅	❌	✅	4
Understanding spiking networks through convex optimization	❌	✅	❌	❌	❌	❌	✅	2
Understanding the Role of Training Regimes in Continual Learning	❌	✅	✅	✅	❌	❌	✅	4
Unfolding recurrence by Green’s functions for optimized reservoir computing	❌	❌	✅	❌	❌	❌	✅	2
Unfolding the Alternating Optimization for Blind Super Resolution	❌	✅	✅	❌	✅	❌	✅	4
Unifying Activation- and Timing-based Learning Rules for Spiking Neural Networks	❌	✅	✅	✅	❌	❌	✅	4
Universal Domain Adaptation through Self Supervision	❌	✅	✅	✅	❌	❌	✅	4
Universal Function Approximation on Graphs	✅	✅	✅	✅	❌	❌	✅	5
Universal guarantees for decision tree induction via a higher-order splitting criterion	✅	❌	❌	❌	❌	❌	❌	1
Universally Quantized Neural Compression	❌	❌	✅	❌	✅	❌	✅	3
Unreasonable Effectiveness of Greedy Algorithms in Multi-Armed Bandit with Many Arms	✅	✅	✅	❌	❌	❌	✅	4
Unsupervised Data Augmentation for Consistency Training	❌	✅	✅	❌	❌	❌	✅	3
Unsupervised Joint k-node Graph Representations with Compositional Energy-Based Models	❌	✅	✅	❌	❌	❌	✅	3
Unsupervised Learning of Dense Visual Representations	❌	❌	✅	✅	❌	❌	✅	3
Unsupervised Learning of Lagrangian Dynamics from Images for Prediction and Control	❌	✅	✅	❌	❌	❌	✅	3
Unsupervised Learning of Object Landmarks via Self-Training Correspondence	❌	✅	✅	✅	❌	❌	✅	4
Unsupervised Learning of Visual Features by Contrasting Cluster Assignments	❌	✅	✅	✅	✅	❌	✅	5
Unsupervised Representation Learning by Invariance Propagation	❌	❌	✅	✅	❌	❌	✅	3
Unsupervised Semantic Aggregation and Deformable Template Matching for Semi-Supervised Learning	❌	✅	✅	✅	✅	❌	✅	5
Unsupervised Sound Separation Using Mixture Invariant Training	❌	✅	✅	❌	✅	❌	✅	4
Unsupervised Text Generation by Learning from Search	✅	✅	✅	✅	✅	❌	✅	6
Unsupervised Translation of Programming Languages	❌	✅	✅	✅	✅	❌	✅	5
Unsupervised object-centric video generation and decomposition in 3D	❌	✅	❌	✅	❌	❌	✅	3
Untangling tradeoffs between recurrence and self-attention in artificial neural networks	✅	❌	✅	❌	✅	❌	✅	4
Upper Confidence Primal-Dual Reinforcement Learning for CMDP with Adversarial Loss	✅	❌	❌	❌	❌	❌	❌	1
User-Dependent Neural Sequence Models for Continuous-Time Event Data	❌	✅	✅	✅	❌	❌	✅	4
Using noise to probe recurrent neural network structure and prune synapses	❌	❌	❌	❌	❌	❌	✅	1
VAEM: a Deep Generative Model for Heterogeneous Mixed Type Data	❌	✅	✅	❌	❌	❌	❌	2
VIME: Extending the Success of Self- and Semi-supervised Learning to Tabular Domain	❌	✅	✅	❌	❌	❌	✅	3
Value-driven Hindsight Modelling	❌	❌	✅	❌	❌	❌	✅	2
VarGrad: A Low-Variance Gradient Estimator for Variational Inference	✅	✅	✅	✅	❌	❌	✅	5
Variance Reduction via Accelerated Dual Averaging for Finite-Sum Optimization	✅	❌	✅	❌	❌	❌	✅	3
Variance reduction for Random Coordinate Descent-Langevin Monte Carlo	✅	❌	❌	❌	❌	❌	✅	2
Variance-Reduced Off-Policy TDC Learning: Non-Asymptotic Convergence Analysis	✅	❌	✅	❌	❌	❌	✅	3
Variational Amodal Object Completion	❌	❌	✅	✅	❌	❌	❌	2
Variational Bayesian Monte Carlo with Noisy Likelihoods	❌	✅	✅	❌	❌	❌	✅	3
Variational Bayesian Unlearning	❌	❌	✅	✅	❌	❌	✅	3
Variational Inference for Graph Convolutional Networks in the Absence of Graph Data and Adversarial Settings	❌	✅	✅	✅	❌	❌	✅	4
Variational Interaction Information Maximization for Cross-domain Disentanglement	❌	❌	✅	✅	❌	❌	❌	2
Variational Policy Gradient Method for Reinforcement Learning with General Utilities	✅	❌	✅	❌	❌	❌	✅	3
Video Frame Interpolation without Temporal Priors	❌	✅	✅	❌	✅	❌	✅	4
Video Object Segmentation with Adaptive Feature Bank and Uncertain-Region Refinement	❌	✅	✅	✅	✅	❌	✅	5
WOR and $p$'s: Sketches for $\ell_p$-Sampling Without Replacement	✅	✅	❌	❌	❌	❌	✅	3
Walking in the Shadow: A New Perspective on Descent Directions for Constrained Minimization	✅	❌	✅	❌	❌	✅	❌	3
Walsh-Hadamard Variational Inference for Bayesian Deep Learning	✅	❌	✅	✅	✅	❌	✅	5
Wasserstein Distances for Stereo Disparity Estimation	❌	✅	✅	✅	❌	❌	✅	4
Watch out! Motion is Blurring the Vision of Your Deep Neural Networks	✅	✅	✅	❌	❌	❌	✅	4
Wavelet Flow: Fast Training of High Resolution Normalizing Flows	❌	✅	✅	✅	✅	❌	✅	5
Weak Form Generalized Hamiltonian Learning	❌	✅	❌	❌	✅	❌	✅	3
Weakly Supervised Deep Functional Maps for Shape Matching	❌	✅	✅	✅	❌	❌	✅	4
Weakly-Supervised Reinforcement Learning for Controllable Behavior	✅	❌	❌	❌	❌	❌	✅	2
Weighted QMIX: Expanding Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning	❌	✅	✅	❌	❌	✅	✅	4
Weisfeiler and Leman go sparse: Towards scalable higher-order graph embeddings	❌	✅	✅	❌	❌	❌	❌	2
Weston-Watkins Hinge Loss and Ordered Partitions	❌	❌	❌	❌	❌	❌	❌	0
What Did You Think Would Happen? Explaining Agent Behaviour through Intended Outcomes	❌	✅	✅	❌	❌	❌	✅	3
What Do Neural Networks Learn When Trained With Random Labels?	❌	❌	✅	❌	❌	❌	✅	2
What Makes for Good Views for Contrastive Learning?	❌	❌	✅	❌	❌	❌	✅	2
What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation	✅	✅	✅	❌	❌	❌	✅	4
What if Neural Networks had SVDs?	✅	✅	❌	❌	✅	❌	✅	4
What is being transferred in transfer learning?	❌	❌	✅	❌	❌	❌	✅	2
What shapes feature representations? Exploring datasets, architectures, and training	❌	❌	✅	✅	❌	❌	✅	3
What went wrong and when? Instance-wise feature importance for time-series black-box models	✅	✅	✅	❌	❌	❌	❌	3
When Counterpoint Meets Chinese Folk Melodies	❌	❌	✅	✅	❌	❌	❌	2
When Do Neural Networks Outperform Kernel Methods?	❌	✅	✅	❌	❌	❌	✅	3
When and How to Lift the Lockdown? Global COVID-19 Scenario Analysis and Policy Assessment using Compartmental Gaussian Processes	✅	✅	✅	❌	❌	❌	✅	4
Why Do Deep Residual Networks Generalize Better than Deep Feedforward Networks? --- A Neural Tangent Kernel Perspective	❌	❌	✅	❌	❌	❌	✅	2
Why Normalizing Flows Fail to Detect Out-of-Distribution Data	❌	✅	✅	✅	❌	❌	✅	4
Why are Adaptive Methods Good for Attention Models?	✅	❌	✅	✅	❌	❌	✅	4
Winning the Lottery with Continuous Sparsification	✅	✅	✅	❌	❌	❌	✅	4
Wisdom of the Ensemble: Improving Consistency of Deep Learning Models	✅	✅	✅	✅	❌	❌	✅	5
WoodFisher: Efficient Second-Order Approximation for Neural Network Compression	❌	✅	✅	❌	✅	❌	✅	4
Woodbury Transformations for Deep Generative Flows	❌	❌	✅	❌	✅	❌	✅	3
Worst-Case Analysis for Randomly Collected Data	✅	✅	❌	❌	❌	✅	✅	4
X-CAL: Explicit Calibration for Survival Analysis	❌	✅	✅	✅	❌	❌	❌	3
Your Classifier can Secretly Suffice Multi-Source Domain Adaptation	✅	✅	✅	✅	❌	❌	✅	5
Your GAN is Secretly an Energy-based Model and You Should Use Discriminator Driven Latent Sampling	❌	❌	✅	❌	❌	❌	❌	1
Zap Q-Learning With Nonlinear Function Approximation	❌	❌	✅	❌	❌	❌	✅	2
Zero-Resource Knowledge-Grounded Dialogue Generation	✅	✅	✅	✅	❌	❌	✅	5
f-Divergence Variational Inference	❌	❌	✅	✅	❌	❌	✅	3
f-GAIL: Learning f-Divergence for Generative Adversarial Imitation Learning	✅	✅	✅	✅	❌	❌	✅	5
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations	❌	✅	✅	✅	✅	❌	✅	5