| $i$-Mix: A Domain-Agnostic Strategy for Contrastive Representation Learning |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| A Better Alternative to Error Feedback for Communication-Efficient Distributed Learning |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| A Block Minifloat Representation for Training Deep Neural Networks |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| A Critique of Self-Expressive Deep Subspace Clustering |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| A Design Space Study for LISTA and Beyond |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| A Diffusion Theory For Deep Learning Dynamics: Stochastic Gradient Descent Exponentially Favors Flat Minima |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| A Discriminative Gaussian Mixture Model with Sparsity |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
3 |
| A Distributional Approach to Controlled Text Generation |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| A Geometric Analysis of Deep Generative Image Models and Its Applications |
❌ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
3 |
| A Good Image Generator Is What You Need for High-Resolution Video Synthesis |
❌ |
✅ |
✅ |
❌ |
✅ |
✅ |
✅ |
5 |
| A Gradient Flow Framework For Analyzing Network Pruning |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| A Hypergradient Approach to Robust Regression without Correspondence |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| A Learning Theoretic Perspective on Local Explainability |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
2 |
| A Mathematical Exploration of Why Language Models Help Solve Downstream Tasks |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| A PAC-Bayesian Approach to Generalization Bounds for Graph Neural Networks |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
❌ |
1 |
| A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference |
❌ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| A Temporal Kernel Approach for Deep Learning with Continuous-time Information |
✅ |
❌ |
✅ |
✅ |
✅ |
✅ |
✅ |
6 |
| A Trainable Optimal Transport Embedding for Feature Aggregation and its Relationship to Attention |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| A Unified Approach to Interpreting and Boosting Adversarial Transferability |
❌ |
✅ |
✅ |
✅ |
✅ |
✅ |
✅ |
6 |
| A Universal Representation Transformer Layer for Few-Shot Image Classification |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| A Wigner-Eckart Theorem for Group Equivariant Convolution Kernels |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
0 |
| A statistical theory of cold posteriors in deep neural networks |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| A teacher-student framework to distill future trajectories |
✅ |
❌ |
❌ |
✅ |
❌ |
❌ |
✅ |
3 |
| A unifying view on implicit bias in training linear neural networks |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
✅ |
1 |
| ALFWorld: Aligning Text and Embodied Environments for Interactive Learning |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| ANOCE: Analysis of Causal Effects with Multiple Mediators via Constrained Structural Learning |
✅ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
5 |
| ARMOURED: Adversarially Robust MOdels using Unlabeled data by REgularizing Diversity |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| AUXILIARY TASK UPDATE DECOMPOSITION: THE GOOD, THE BAD AND THE NEUTRAL |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Accelerating Convergence of Replica Exchange Stochastic Gradient MCMC via Variance Reduction |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Accurate Learning of Graph Representations with Graph Multiset Pooling |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learning |
✅ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| Acting in Delayed Environments with Non-Stationary Markov Policies |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Activation-level uncertainty in deep neural networks |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Active Contrastive Learning of Audio-Visual Video Representations |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognition |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| AdaGCN: Adaboosting Graph Convolutional Networks into Deep Models |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| AdaSpeech: Adaptive Text to Speech for Custom Voice |
✅ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Adapting to Reward Progressivity via Spectral Reinforcement Learning |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Adaptive Extra-Gradient Methods for Min-Max Optimization and Games |
✅ |
❌ |
❌ |
❌ |
❌ |
❌ |
✅ |
2 |
| Adaptive Federated Optimization |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Adaptive Procedural Task Generation for Hard-Exploration Problems |
✅ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
5 |
| Adaptive Universal Generalized PageRank Graph Neural Network |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Adaptive and Generative Zero-Shot Learning |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Adversarial score matching and improved sampling for image generation |
✅ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
5 |
| Adversarially Guided Actor-Critic |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Adversarially-Trained Deep Nets Transfer Better: Illustration on Image Classification |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Aligning AI With Shared Human Values |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| An Unsupervised Deep Learning Approach for Real-World Image Denoising |
✅ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| Analyzing the Expressive Power of Graph Neural Networks in a Spectral Perspective |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Anchor & Transform: Learning Sparse Embeddings for Large Vocabularies |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Anytime Sampling for Autoregressive Models via Ordered Autoencoding |
❌ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Are Neural Rankers still Outperformed by Gradient Boosted Decision Trees? |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Are wider nets better given the same number of parameters? |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Ask Your Humans: Using Human Instructions to Improve Generalization in Reinforcement Learning |
❌ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| Async-RED: A Provably Convergent Asynchronous Block Parallel Stochastic Method using Deep Denoising Priors |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Attentional Constellation Nets for Few-Shot Learning |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Auction Learning as a Two-Player Game |
✅ |
❌ |
❌ |
❌ |
❌ |
❌ |
✅ |
2 |
| Augmenting Physical Models with Deep Networks for Complex Dynamics Forecasting |
✅ |
❌ |
❌ |
✅ |
❌ |
❌ |
✅ |
3 |
| Auto Seg-Loss: Searching Metric Surrogates for Semantic Segmentation |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| AutoLRS: Automatic Learning-Rate Schedule by Bayesian Optimization on the Fly |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Autoregressive Dynamics Models for Offline Policy Evaluation and Optimization |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Autoregressive Entity Retrieval |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Auxiliary Learning by Implicit Differentiation |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Average-case Acceleration for Bilinear Games and Normal Matrices |
✅ |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
1 |
| BERTology Meets Biology: Interpreting Attention in Protein Language Models |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| BOIL: Towards Representation Change for Few-shot Learning |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction |
✅ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
5 |
| BREEDS: Benchmarks for Subpopulation Shift |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| BSQ: Exploring Bit-Level Sparsity for Mixed-Precision Neural Network Quantization |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
4 |
| BUSTLE: Bottom-Up Program Synthesis Through Learning-Guided Exploration |
✅ |
❌ |
❌ |
✅ |
✅ |
❌ |
✅ |
4 |
| Bag of Tricks for Adversarial Training |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Balancing Constraints and Rewards with Meta-Gradient D4PG |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Batch Reinforcement Learning Through Continuation Method |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Bayesian Context Aggregation for Neural Processes |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Bayesian Few-Shot Classification with One-vs-Each Pólya-Gamma Augmented Gaussian Processes |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Behavioral Cloning from Noisy Demonstrations |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Benchmarks for Deep Off-Policy Evaluation |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Benefit of deep learning with non-convex noisy gradient descent: Provable excess risk bound and superiority to kernel methods |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
0 |
| Better Fine-Tuning by Reducing Representational Collapse |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Beyond Categorical Label Representations for Image Classification |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Beyond Fully-Connected Layers with Quaternions: Parameterization of Hypercomplex Multiplications with $1/n$ Parameters |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| BiPointNet: Binary Neural Network for Point Clouds |
✅ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
5 |
| Bidirectional Variational Inference for Non-Autoregressive Text-to-Speech |
✅ |
✅ |
✅ |
✅ |
✅ |
✅ |
✅ |
7 |
| Blending MPC & Value Function Approximation for Efficient Reinforcement Learning |
✅ |
❌ |
❌ |
❌ |
❌ |
❌ |
✅ |
2 |
| Boost then Convolve: Gradient Boosting Meets Graph Neural Networks |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Bowtie Networks: Generative Modeling for Joint Few-Shot Recognition and Novel-View Synthesis |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Bypassing the Ambient Dimension: Private SGD with Gradient Subspace Identification |
✅ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| Byzantine-Resilient Non-Convex Stochastic Gradient Descent |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| C-Learning: Horizon-Aware Cumulative Accessibility Estimation |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| C-Learning: Learning to Achieve Goals via Recursive Classification |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| CO2: Consistent Contrast for Unsupervised Visual Representation Learning |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| CPR: Classifier-Projection Regularization for Continual Learning |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
❌ |
2 |
| CPT: Efficient Deep Neural Network Training via Cyclic Precision |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| CT-Net: Channel Tensorization Network for Video Classification |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| CaPC Learning: Confidential and Private Collaborative Learning |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Calibration of Neural Networks using Splines |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Calibration tests beyond classification |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Can a Fruit Fly Learn Word Embeddings? |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
4 |
| Capturing Label Characteristics in VAEs |
❌ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
3 |
| Categorical Normalizing Flows via Continuous Transformations |
✅ |
✅ |
✅ |
✅ |
✅ |
✅ |
✅ |
7 |
| CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| CcGAN: Continuous Conditional Generative Adversarial Networks for Image Generation |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Certify or Predict: Boosting Certified Robustness with Compositional Architectures |
❌ |
✅ |
✅ |
❌ |
✅ |
✅ |
✅ |
5 |
| Chaos of Learning Beyond Zero-sum and Coordination via Game Decompositions |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
✅ |
1 |
| Characterizing signal propagation to close the performance gap in unnormalized ResNets |
✅ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
5 |
| ChipNet: Budget-Aware Pruning with Heaviside Continuous Approximations |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Clairvoyance: A Pipeline Toolkit for Medical Time Series |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Class Normalization for (Continual)? Generalized Zero-Shot Learning |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Clustering-friendly Representation Learning via Instance Discrimination and Feature Decorrelation |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversity |
✅ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
5 |
| CoCo: Controllable Counterfactuals for Evaluating Dialogue State Trackers |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| CoCon: A Self-Supervised Approach for Controlled Text Generation |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| CoDA: Contrast-enhanced and Diversity-promoting Data Augmentation for Natural Language Understanding |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Collective Robustness Certificates: Exploiting Interdependence in Graph Neural Networks |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Colorization Transformer |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Combining Ensembles and Data Augmentation Can Harm Your Calibration |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Combining Label Propagation and Simple Models out-performs Graph Neural Networks |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Combining Physics and Machine Learning for Network Flow Estimation |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Communication in Multi-Agent Reinforcement Learning: Intention Sharing |
✅ |
❌ |
❌ |
❌ |
❌ |
❌ |
✅ |
2 |
| CompOFA – Compound Once-For-All Networks for Faster Multi-Platform Deployment |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Complex Query Answering with Neural Link Predictors |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Computational Separation Between Convolutional and Fully-Connected Networks |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Concept Learners for Few-Shot Learning |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Conditional Generative Modeling via Learning the Latent Space |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Conditional Negative Sampling for Contrastive Learning of Visual Representations |
✅ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Conditionally Adaptive Multi-Task Learning: Improving Transfer Learning in NLP Using Fewer Parameters & Less Data |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Conformation-Guided Molecular Representation with Hamiltonian Neural Networks |
❌ |
❌ |
✅ |
✅ |
❌ |
✅ |
✅ |
4 |
| Conservative Safety Critics for Exploration |
✅ |
❌ |
❌ |
❌ |
❌ |
❌ |
✅ |
2 |
| Contemplating Real-World Object Classification |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
❌ |
2 |
| Contextual Dropout: An Efficient Sample-Dependent Dropout Module |
✅ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Contextual Transformation Networks for Online Continual Learning |
✅ |
✅ |
✅ |
✅ |
✅ |
✅ |
✅ |
7 |
| Continual learning in recurrent neural networks |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
❌ |
2 |
| Continuous Wasserstein-2 Barycenter Estimation without Minimax Optimization |
✅ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
5 |
| Contrastive Learning with Adversarial Perturbations for Conditional Text Generation |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Contrastive Divergence Learning is a Time Reversal Adversarial Game |
✅ |
✅ |
❌ |
❌ |
❌ |
❌ |
✅ |
3 |
| Contrastive Explanations for Reinforcement Learning via Embedded Self Predictions |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Contrastive Learning with Hard Negative Samples |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Contrastive Syn-to-Real Generalization |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Control-Aware Representations for Model-based Reinforcement Learning |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Convex Potential Flows: Universal Probability Distributions with Optimal Transport and Convex Optimization |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
❌ |
3 |
| Convex Regularization behind Neural Reconstruction |
❌ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
3 |
| Coping with Label Shift via Distributionally Robust Optimisation |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| CopulaGNN: Towards Integrating Representational and Correlational Roles of Graphs in Graph Neural Networks |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Correcting experience replay for multi-agent communication |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Counterfactual Generative Networks |
❌ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| Coupled Oscillatory Recurrent Neural Network (coRNN): An accurate and (gradient) stable architecture for learning long time dependencies |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
4 |
| Creative Sketch Generation |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Cross-Attentional Audio-Visual Fusion for Weakly-Supervised Action Localization |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Cut out the annotator, keep the cutout: better segmentation with weak supervision |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| DARTS-: Robustly Stepping out of Performance Collapse Without Indicators |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| DC3: A learning method for optimization with hard constraints |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| DDPNOpt: Differential Dynamic Programming Neural Optimizer |
✅ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| DEBERTA: DECODING-ENHANCED BERT WITH DISENTANGLED ATTENTION |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimation |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| DINO: A Conditional Energy-Based GAN for Domain Translation |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| DOP: Off-Policy Multi-Agent Decomposed Policy Gradients |
✅ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| Data-Efficient Reinforcement Learning with Self-Predictive Representations |
✅ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
5 |
| Dataset Condensation with Gradient Matching |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Dataset Inference: Ownership Resolution in Machine Learning |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Dataset Meta-Learning from Kernel Ridge-Regression |
✅ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
5 |
| DeLighT: Deep and Light-weight Transformer |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Debiasing Concept-based Explanations with Causal Analysis |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Decentralized Attribution of Generative Models |
✅ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
5 |
| Deciphering and Optimizing Multi-Task Learning: a Random Matrix Approach |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Deconstructing the Regularization of BatchNorm |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Decoupling Global and Local Representations via Invertible Generative Flows |
❌ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| Deep Encoder, Shallow Decoder: Reevaluating Non-autoregressive Machine Translation |
❌ |
✅ |
✅ |
✅ |
✅ |
✅ |
✅ |
6 |
| Deep Equals Shallow for ReLU Networks in Kernel Regimes |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Deep Learning meets Projective Clustering |
❌ |
✅ |
✅ |
❌ |
✅ |
✅ |
✅ |
5 |
| Deep Networks and the Multiple Manifold Problem |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
0 |
| Deep Neural Network Fingerprinting by Conferrable Adversarial Examples |
❌ |
❌ |
✅ |
❌ |
✅ |
✅ |
✅ |
4 |
| Deep Neural Tangent Kernel and Laplace Kernel Have the Same RKHS |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
0 |
| Deep Partition Aggregation: Provable Defenses against General Poisoning Attacks |
❌ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| Deep Repulsive Clustering of Ordered Data Based on Order-Identity Decomposition |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Deep symbolic regression: Recovering mathematical expressions from data via risk-seeking policy gradients |
✅ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
5 |
| DeepAveragers: Offline Reinforcement Learning By Solving Derived Non-Parametric MDPs |
✅ |
✅ |
❌ |
❌ |
✅ |
❌ |
✅ |
4 |
| Deformable DETR: Deformable Transformers for End-to-End Object Detection |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Degree-Quant: Quantization-Aware Training for Graph Neural Networks |
✅ |
✅ |
✅ |
✅ |
✅ |
✅ |
✅ |
7 |
| Denoising Diffusion Implicit Models |
❌ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
3 |
| Deployment-Efficient Reinforcement Learning via Model-Based Offline Optimization |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| DialoGraph: Incorporating Interpretable Strategy-Graph Networks into Negotiation Dialogues |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| DiffWave: A Versatile Diffusion Model for Audio Synthesis |
✅ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| Differentiable Segmentation of Sequences |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Differentiable Trust Region Layers for Deep Reinforcement Learning |
✅ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
5 |
| Differentially Private Learning Needs Better Features (or Much More Data) |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Directed Acyclic Graph Neural Networks |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Direction Matters: On the Implicit Bias of Stochastic Gradient Descent with Moderate Learning Rate |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Disambiguating Symbolic Expressions in Informal Documents |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Discovering Non-monotonic Autoregressive Orderings with Variational Inference |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Discovering a set of policies for the worst case reward |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Discrete Graph Structure Learning for Forecasting Multiple Time Series |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Disentangled Recurrent Wasserstein Autoencoder |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Disentangling 3D Prototypical Networks for Few-Shot Concept Learning |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
4 |
| Distance-Based Regularisation of Deep Networks for Fine-Tuning |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Distilling Knowledge from Reader to Retriever for Question Answering |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Distributed Momentum for Byzantine-resilient Stochastic Gradient Descent |
❌ |
✅ |
✅ |
❌ |
✅ |
✅ |
✅ |
5 |
| Distributional Sliced-Wasserstein and Applications to Generative Modeling |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Diverse Video Generation using a Gaussian Process Trigger |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Do 2D GANs Know 3D Shape? Unsupervised 3D Shape Reconstruction from 2D Image GANs |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Do Wide and Deep Networks Learn the Same Things? Uncovering How Neural Network Representations Vary with Width and Depth |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Do not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Does enhanced shape bias improve neural network robustness to common corruptions? |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Domain Generalization with MixStyle |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Domain-Robust Visual Imitation Learning with Mutual Information Constraints |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| DrNAS: Dirichlet Neural Architecture Search |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Drop-Bottleneck: Learning Discrete Compressed Representation for Noise-Robust Exploration |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Dual-mode ASR: Unify and Improve Streaming ASR with Full-context Modeling |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| DynaTune: Dynamic Tensor Program Optimization in Deep Neural Network Compilation |
✅ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| Dynamic Tensor Rematerialization |
✅ |
✅ |
❌ |
❌ |
✅ |
✅ |
✅ |
5 |
| ECONOMIC HYPERPARAMETER OPTIMIZATION WITH BLENDED SEARCH STRATEGY |
✅ |
✅ |
✅ |
✅ |
✅ |
✅ |
✅ |
7 |
| EEC: Learning to Encode and Regenerate Images for Continual Learning |
✅ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| EVALUATION OF NEURAL ARCHITECTURES TRAINED WITH SQUARE LOSS VS CROSS-ENTROPY IN CLASSIFICATION TASKS |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
4 |
| Early Stopping in Deep Networks: Double Descent and How to Eliminate it |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Effective Abstract Reasoning with Dual-Contrast Network |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Effective Distributed Learning with Random Features: Improved Bounds and Algorithms |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Effective and Efficient Vote Attack on Capsule Networks |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
4 |
| Efficient Certified Defenses Against Patch Attacks on Image Classifiers |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
4 |
| Efficient Conformal Prediction via Cascaded Inference with Expanded Admission |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Efficient Continual Learning with Modular Networks and Task-Driven Priors |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Efficient Empowerment Estimation for Unsupervised Stabilization |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Efficient Generalized Spherical CNNs |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Efficient Inference of Flexible Interaction in Spiking-neuron Networks |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Efficient Reinforcement Learning in Factored MDPs with Application to Constrained RL |
✅ |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
1 |
| Efficient Transformers in Reinforcement Learning using Actor-Learner Distillation |
❌ |
❌ |
❌ |
✅ |
✅ |
❌ |
✅ |
3 |
| Efficient Wasserstein Natural Gradients for Reinforcement Learning |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| EigenGame: PCA as a Nash Equilibrium |
✅ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| Emergent Road Rules In Multi-Agent Driving Environments |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
❌ |
3 |
| Emergent Symbols through Binding in External Memory |
✅ |
✅ |
❌ |
❌ |
❌ |
❌ |
✅ |
3 |
| Empirical Analysis of Unlabeled Entity Problem in Named Entity Recognition |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Empirical or Invariant Risk Minimization? A Sample Complexity Perspective |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| End-to-End Egospheric Spatial Memory |
✅ |
✅ |
✅ |
✅ |
✅ |
✅ |
✅ |
7 |
| End-to-end Adversarial Text-to-Speech |
✅ |
❌ |
❌ |
✅ |
✅ |
✅ |
✅ |
5 |
| Enforcing robust control guarantees within neural network policies |
✅ |
✅ |
❌ |
✅ |
✅ |
❌ |
✅ |
5 |
| Enjoy Your Editing: Controllable GANs for Image Editing via Latent Space Navigation |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Entropic gradient descent algorithms and wide flat minima |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
✅ |
5 |
| Estimating Lipschitz constants of monotone deep equilibrium models |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Estimating and Evaluating Regression Predictive Uncertainty in Deep Object Detectors |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Estimating informativeness of samples with Smooth Unique Information |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Evaluating the Disentanglement of Deep Generative Models through Manifold Topology |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Evaluation of Similarity-based Explanations |
❌ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| Evaluations and Methods for Explanation through Robustness Analysis |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Evolving Reinforcement Learning Algorithms |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Exemplary Natural Images Explain CNN Activations Better than State-of-the-Art Feature Visualization |
❌ |
✅ |
✅ |
✅ |
✅ |
✅ |
✅ |
6 |
| Explainable Deep One-Class Classification |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
✅ |
6 |
| Explainable Subgraph Reasoning for Forecasting on Temporal Knowledge Graphs |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Explaining by Imitating: Understanding Decisions by Interpretable Policy Learning |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Explaining the Efficacy of Counterfactually Augmented Data |
❌ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
3 |
| Exploring Balanced Feature Spaces for Representation Learning |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Exploring the Uncertainty Properties of Neural Networks’ Implicit Priors in the Infinite-Width Limit |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Expressive Power of Invariant and Equivariant Graph Neural Networks |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
✅ |
4 |
| Extracting Strong Policies for Robotics Tasks from Zero-Order Trajectory Optimizers |
✅ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| Extreme Memorization via Scale of Initialization |
❌ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| FOCAL: Efficient Fully-Offline Meta-Reinforcement Learning via Distance Metric Learning and Behavior Regularization |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Factorizing Declarative and Procedural Knowledge in Structured, Dynamical Environments |
✅ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| Fair Mixup: Fairness via Interpolation |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| FairBatch: Batch Selection for Model Fairness |
✅ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoders |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Fantastic Four: Differentiable and Efficient Bounds on Singular Values of Convolution Layers |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Fast And Slow Learning Of Recurrent Independent Mechanisms |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Fast Geometric Projections for Local Robustness Certification |
❌ |
✅ |
✅ |
❌ |
✅ |
✅ |
✅ |
5 |
| Fast and Complete: Enabling Complete Neural Network Verification with Rapid and Massively Parallel Incomplete Verifiers |
✅ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
5 |
| Fast convergence of stochastic subgradient method under interpolation |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| FastSpeech 2: Fast and High-Quality End-to-End Text to Speech |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
4 |
| Faster Binary Embeddings for Preserving Euclidean Distances |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| FedBE: Making Bayesian Model Ensemble Applicable to Federated Learning |
✅ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| FedBN: Federated Learning on Non-IID Features via Local Batch Normalization |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| FedMix: Approximation of Mixup under Mean Augmented Federated Learning |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Federated Learning Based on Dynamic Regularization |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Federated Learning via Posterior Averaging: A New Perspective and Practical Algorithms |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Federated Semi-Supervised Learning with Inter-Client Consistency & Disjoint Learning |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Few-Shot Bayesian Optimization with Deep Kernel Surrogates |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Few-Shot Learning via Learning the Representation, Provably |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
0 |
| Fidelity-based Deep Adiabatic Scheduling |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
✅ |
1 |
| Filtered Inner Product Projection for Crosslingual Embedding Alignment |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Fooling a Complete Neural Network Verifier |
❌ |
✅ |
✅ |
❌ |
✅ |
✅ |
✅ |
5 |
| For self-supervised learning, Rationality implies generalization, provably |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Fourier Neural Operator for Parametric Partial Differential Equations |
❌ |
❌ |
❌ |
❌ |
✅ |
❌ |
✅ |
2 |
| Free Lunch for Few-shot Learning: Distribution Calibration |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Fully Unsupervised Diversity Denoising with Convolutional Variational Autoencoders |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
4 |
| Fuzzy Tiling Activations: A Simple Approach to Learning Sparse Representations Online |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
✅ |
5 |
| GAN "Steerability" without optimization |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
❌ |
1 |
| GAN2GAN: Generative Noise Learning for Blind Denoising with Single Noisy Images |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| GANs Can Play Lottery Tickets Too |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
❌ |
3 |
| GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding |
✅ |
✅ |
❌ |
❌ |
✅ |
❌ |
✅ |
4 |
| Gauge Equivariant Mesh CNNs: Anisotropic convolutions on geometric graphs |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Generalization bounds via distillation |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Generalization in data-driven models of primary visual cortex |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Generalized Energy Based Models |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Generalized Multimodal ELBO |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Generalized Variational Continual Learning |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Generating Adversarial Computer Programs using Optimized Obfuscations |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
3 |
| Generating Furry Cars: Disentangling Object Shape and Appearance across Multiple Domains |
❌ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
3 |
| Generative Language-Grounded Policy in Vision-and-Language Navigation with Bayes' Rule |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Generative Scene Graph Networks |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Generative Time-series Modeling with Fourier Flows |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Genetic Soft Updates for Policy Evolution in Deep Reinforcement Learning |
✅ |
❌ |
❌ |
❌ |
✅ |
❌ |
✅ |
3 |
| Geometry-Aware Gradient Algorithms for Neural Architecture Search |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Geometry-aware Instance-reweighted Adversarial Training |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Getting a CLUE: A Method for Explaining Uncertainty Estimates |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Global Convergence of Three-layer Neural Networks in the Mean Field Regime |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
0 |
| Global optimality of softmax policy gradient with single hidden layer neural networks in the mean-field regime |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
✅ |
1 |
| Go with the flow: Adaptive control for Neural ODEs |
✅ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Gradient Origin Networks |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Gradient Projection Memory for Continual Learning |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Models |
✅ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| Graph Coarsening with Neural Networks |
✅ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Graph Convolution with Low-rank Learnable Local Filters |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Graph Edit Networks |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Graph Information Bottleneck for Subgraph Recognition |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Graph Traversal with Tensor Functionals: A Meta-Algorithm for Scalable Learning |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Graph-Based Continual Learning |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| GraphCodeBERT: Pre-training Code Representations with Data Flow |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Greedy-GQ with Variance Reduction: Finite-time Analysis and Improved Complexity |
✅ |
❌ |
❌ |
❌ |
❌ |
❌ |
✅ |
2 |
| Grounded Language Learning Fast and Slow |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Grounding Language to Autonomously-Acquired Skills via Goal Generation |
✅ |
✅ |
❌ |
❌ |
❌ |
❌ |
✅ |
3 |
| Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Group Equivariant Conditional Neural Processes |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Group Equivariant Generative Adversarial Networks |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Group Equivariant Stand-Alone Self-Attention For Vision |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Growing Efficient Deep Networks by Structured Continuous Sparsification |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| HW-NAS-Bench: Hardware-Aware Neural Architecture Search Benchmark |
❌ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| HalentNet: Multimodal Trajectory Forecasting with Hallucinative Intents |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Heating up decision boundaries: isocapacitory saturation, adversarial scenarios and generalization bounds |
✅ |
✅ |
✅ |
✅ |
✅ |
✅ |
✅ |
7 |
| HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Heteroskedastic and Imbalanced Deep Learning with Adaptive Regularization |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Hierarchical Autoregressive Modeling for Neural Video Compression |
✅ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| Hierarchical Reinforcement Learning by Discovering Intrinsic Options |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| High-Capacity Expert Binary Networks |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
4 |
| Hopfield Networks is All You Need |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Hopper: Multi-hop Transformer for Spatiotemporal Reasoning |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| How Benign is Benign Overfitting ? |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| How Does Mixup Help With Robustness and Generalization? |
❌ |
❌ |
✅ |
❌ |
❌ |
✅ |
✅ |
3 |
| How Much Over-parameterization Is Sufficient to Learn Deep ReLU Networks? |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
❌ |
2 |
| How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks |
❌ |
❌ |
❌ |
✅ |
❌ |
❌ |
✅ |
2 |
| How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Human-Level Performance in No-Press Diplomacy via Equilibrium Search |
❌ |
❌ |
❌ |
❌ |
✅ |
❌ |
✅ |
2 |
| HyperDynamics: Meta-Learning Object and Agent Dynamics with Hypernetworks |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| HyperGrid Transformers: Towards A Single Model for Multiple Tasks |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
4 |
| Hyperbolic Neural Networks++ |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| IDF++: Analyzing and Improving Integer Discrete Flows for Lossless Compression |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
4 |
| IEPT: Instance-Level and Episode-Level Pretext Tasks for Few-Shot Learning |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| INT: An Inequality Benchmark for Evaluating Generalization in Theorem Proving |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| IOT: Instance-wise Layer Reordering for Transformer Structures |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Identifying Physical Law of Hamiltonian Systems via Meta-Learning |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Identifying nonlinear dynamical systems with multiple time scales and long-range dependencies |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
✅ |
6 |
| Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Rendering |
❌ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
3 |
| Impact of Representation Learning in Linear Bandits |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Implicit Convex Regularizers of CNN Architectures: Convex Optimization of Two- and Three-Layer Networks in Polynomial Time |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Implicit Gradient Regularization |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Implicit Normalizing Flows |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement Learning |
✅ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| Improve Object Detection with Feature-based Knowledge Distillation: Towards Accurate and Efficient Detectors |
❌ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| Improved Autoregressive Modeling with Distribution Smoothing |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Improved Estimation of Concentration Under $\ell_p$-Norm Distance Metrics Using Half Spaces |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Improving Adversarial Robustness via Channel-wise Activation Suppressing |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Improving Relational Regularized Autoencoders with Spherical Sliced Fused Gromov Wasserstein |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Improving Transformation Invariance in Contrastive Representation Learning |
❌ |
✅ |
✅ |
❌ |
✅ |
✅ |
✅ |
5 |
| Improving VAEs' Robustness to Adversarial Attack |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Improving Zero-Shot Voice Style Transfer via Disentangled Representation Learning |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
4 |
| In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| In Search of Lost Domain Generalization |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Incorporating Symmetry into Deep Dynamics Models for Improved Generalization |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Incremental few-shot learning via vector quantization in deep embedded space |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Individually Fair Gradient Boosting |
✅ |
❌ |
✅ |
✅ |
❌ |
✅ |
✅ |
5 |
| Individually Fair Rankings |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Inductive Representation Learning in Temporal Networks via Causal Anonymous Walks |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Influence Estimation for Generative Adversarial Networks |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Influence Functions in Deep Learning Are Fragile |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Information Laundering for Model Privacy |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Initialization and Regularization of Factorized Neural Layers |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Integrating Categorical Semantics into Unsupervised Domain Translation |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
❌ |
4 |
| Interactive Weak Supervision: Learning Useful Heuristics for Data Labeling |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Interpretable Models for Granger Causality Using Self-explaining Neural Networks |
✅ |
✅ |
✅ |
❌ |
✅ |
✅ |
✅ |
6 |
| Interpretable Neural Architecture Search via Bayesian Optimisation with Weisfeiler-Lehman Kernels |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Interpreting Knowledge Graph Relation Representation from Word Embeddings |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Interpreting and Boosting Dropout from a Game-Theoretic View |
❌ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
3 |
| Into the Wild with AudioScope: Unsupervised Audio-Visual Separation of On-Screen Sounds |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Intraclass clustering: an implicit learning ability that regularizes DNNs |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Intrinsic-Extrinsic Convolution and Pooling for Learning on 3D Protein Structures |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Is Attention Better Than Matrix Decomposition? |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Is Label Smoothing Truly Incompatible with Knowledge Distillation: An Empirical Study |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| IsarStep: a Benchmark for High-level Mathematical Reasoning |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Isometric Propagation Network for Generalized Zero-shot Learning |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Isometric Transformation Invariant and Equivariant Graph Convolutional Networks |
❌ |
✅ |
✅ |
✅ |
✅ |
✅ |
✅ |
6 |
| Isotropy in the Contextual Embedding Space: Clusters and Manifolds |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
❌ |
2 |
| Iterated learning for emergent systematicity in VQA |
✅ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Iterative Empirical Game Solving via Single Policy Best Response |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Kanerva++: Extending the Kanerva Machine With Differentiable, Locally Block Allocated Latent Memory |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Knowledge Distillation as Semiparametric Inference |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Knowledge distillation via softmax regression representation learning |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| LEAF: A Learnable Frontend for Audio Classification |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| LambdaNetworks: Modeling long-range Interactions without Attention |
✅ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Language-Agnostic Representation Learning of Source Code from Structure and Context |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Large Associative Memory Problem in Neurobiology and Machine Learning |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
0 |
| Large Batch Simulation for Deep Reinforcement Learning |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Large Scale Image Completion via Co-Modulated Generative Adversarial Networks |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Large-width functional asymptotics for deep Gaussian neural networks |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
0 |
| Latent Convergent Cross Mapping |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
✅ |
4 |
| Latent Skill Planning for Exploration and Transfer |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Layer-adaptive Sparsity for the Magnitude-based Pruning |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Learnable Embedding sizes for Recommender Systems |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Learning "What-if" Explanations for Sequential Decision-Making |
✅ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Learning A Minimax Optimizer: A Pilot Study |
✅ |
✅ |
❌ |
✅ |
✅ |
❌ |
✅ |
5 |
| Learning Accurate Entropy Model with Global Reference for Image Compression |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Learning Associative Inference Using Fast Weight Memory |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Learning Better Structured Representations Using Low-rank Adaptive Label Smoothing |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
4 |
| Learning Cross-Domain Correspondence for Control with Dynamics Cycle-Consistency |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Learning Deep Features in Instrumental Variable Regression |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
✅ |
6 |
| Learning Energy-Based Generative Models via Coarse-to-Fine Expanding and Sampling |
✅ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| Learning Energy-Based Models by Diffusion Recovery Likelihood |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Learning Generalizable Visual Representations via Interactive Gameplay |
✅ |
❌ |
✅ |
✅ |
❌ |
✅ |
✅ |
5 |
| Learning Hyperbolic Representations of Topological Features |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
✅ |
5 |
| Learning Incompressible Fluid Dynamics from Scratch - Towards Fast, Differentiable Fluid Models that Generalize |
❌ |
✅ |
❌ |
❌ |
✅ |
❌ |
✅ |
3 |
| Learning Invariant Representations for Reinforcement Learning without Reconstruction |
✅ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| Learning Long-term Visual Dynamics with Region Proposal Interaction Networks |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Learning Manifold Patch-Based Representations of Man-Made Shapes |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
4 |
| Learning Mesh-Based Simulation with Graph Networks |
❌ |
❌ |
❌ |
✅ |
✅ |
✅ |
✅ |
4 |
| Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Learning Neural Event Functions for Ordinary Differential Equations |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
✅ |
6 |
| Learning Neural Generative Dynamics for Molecular Conformation Generation |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
✅ |
6 |
| Learning Parametrised Graph Shift Operators |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Learning Reasoning Paths over Semantic Graphs for Video-grounded Dialogues |
✅ |
❌ |
✅ |
✅ |
❌ |
✅ |
✅ |
5 |
| Learning Robust State Abstractions for Hidden-Parameter Block MDPs |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Learning Safe Multi-agent Control with Decentralized Neural Barrier Certificates |
❌ |
✅ |
❌ |
❌ |
❌ |
❌ |
✅ |
2 |
| Learning Structural Edits via Incremental Tree Transformations |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Learning Subgoal Representations with Slow Dynamics |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Learning Task Decomposition with Ordered Memory Policy Network |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Learning Task-General Representations with Generative Neuro-Symbolic Modeling |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
❌ |
3 |
| Learning Value Functions in Deep Policy Gradients using Residual Variance |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Learning What To Do by Simulating the Past |
✅ |
✅ |
❌ |
❌ |
❌ |
❌ |
✅ |
3 |
| Learning a Latent Search Space for Routing Problems using Variational Autoencoders |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Learning a Latent Simplex in Input Sparsity Time |
✅ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| Learning advanced mathematical computations from examples |
❌ |
❌ |
❌ |
✅ |
✅ |
✅ |
✅ |
4 |
| Learning and Evaluating Representations for Deep One-Class Classification |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Learning continuous-time PDEs from sparse data with graph neural networks |
❌ |
✅ |
❌ |
❌ |
❌ |
❌ |
✅ |
2 |
| Learning explanations that are hard to vary |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Learning from Demonstration with Weakly Supervised Disentanglement |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Learning from Protein Structure with Geometric Vector Perceptrons |
✅ |
✅ |
✅ |
✅ |
✅ |
✅ |
✅ |
7 |
| Learning from others' mistakes: Avoiding dataset biases without modeling them |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
4 |
| Learning perturbation sets for robust machine learning |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Learning the Pareto Front with Hypernetworks |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Learning to Deceive Knowledge Graph Augmented Models via Targeted Perturbation |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Learning to Generate 3D Shapes with Generative Cellular Automata |
✅ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| Learning to Make Decisions via Submodular Regularization |
✅ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Learning to Reach Goals via Iterated Supervised Learning |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Learning to Recombine and Resample Data For Compositional Generalization |
❌ |
✅ |
✅ |
✅ |
✅ |
✅ |
✅ |
6 |
| Learning to Represent Action Values as a Hypergraph on the Action Vertices |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Learning to Sample with Local and Global Contexts in Experience Replay Buffer |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Learning to Set Waypoints for Audio-Visual Navigation |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Learning to live with Dale's principle: ANNs with separate excitatory and inhibitory units |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Learning with AMIGo: Adversarially Motivated Intrinsic Goals |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Learning with Feature-Dependent Label Noise: A Progressive Approach |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Learning with Instance-Dependent Label Noise: A Sample Sieve Approach |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Learning-based Support Estimation in Sublinear Time |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Lifelong Learning of Compositional Structures |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| LiftPool: Bidirectional ConvNet Pooling |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Linear Convergent Decentralized Optimization with Compression |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Linear Last-iterate Convergence in Constrained Saddle-point Optimization |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
✅ |
1 |
| Linear Mode Connectivity in Multitask and Continual Learning |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Lipschitz Recurrent Neural Networks |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Local Convergence Analysis of Gradient Descent Ascent with Finite Timescale Separation |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Local Search Algorithms for Rank-Constrained Convex Optimization |
✅ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Locally Free Weight Sharing for Network Width Search |
✅ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Long Live the Lottery: The Existence of Winning Tickets in Lifelong Learning |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Long Range Arena : A Benchmark for Efficient Transformers |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
4 |
| Long-tail learning via logit adjustment |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Long-tailed Recognition by Routing Diverse Distribution-Aware Experts |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Loss Function Discovery for Object Detection via Convergence-Simulation Driven Search |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Lossless Compression of Structured Convolutional Models via Lifting |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognition |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| MALI: A memory efficient and reverse accurate integrator for Neural ODEs |
✅ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
5 |
| MARS: Markov Molecular Sampling for Multi-objective Drug Discovery |
✅ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
5 |
| MELR: Meta-Learning via Modeling Episode-Level Relationships for Few-Shot Learning |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| MIROSTAT: A NEURAL TEXT DECODING ALGORITHM THAT DIRECTLY CONTROLS PERPLEXITY |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| MODALS: Modality-agnostic Automated Data Augmentation in the Latent Space |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| MONGOOSE: A Learnable LSH Framework for Efficient Neural Network Training |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Mapping the Timescale Organization of Neural Language Models |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Mastering Atari with Discrete World Models |
✅ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
5 |
| Mathematical Reasoning via Self-supervised Skip-tree Training |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
4 |
| Measuring Massive Multitask Language Understanding |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Memory Optimization for Deep Networks |
✅ |
✅ |
✅ |
❌ |
✅ |
✅ |
✅ |
6 |
| Meta Back-Translation |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
4 |
| Meta-GMVAE: Mixture of Gaussian VAE for Unsupervised Meta-Learning |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Meta-Learning of Structured Task Distributions in Humans and Machines |
❌ |
❌ |
❌ |
✅ |
❌ |
❌ |
✅ |
2 |
| Meta-Learning with Neural Tangent Kernels |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Meta-learning Symmetries by Reparameterization |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Meta-learning with negative learning rates |
❌ |
❌ |
❌ |
✅ |
❌ |
❌ |
✅ |
2 |
| MetaNorm: Learning to Normalize Few-Shot Batches Across Domains |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| MiCE: Mixture of Contrastive Experts for Unsupervised Image Clustering |
✅ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
5 |
| Mind the Gap when Conditioning Amortised Inference in Sequential Latent-Variable Models |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Mind the Pad -- CNNs Can Develop Blind Spots |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
❌ |
2 |
| Minimum Width for Universal Approximation |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
0 |
| MixKD: Towards Efficient Distillation of Large-scale Language Models |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
4 |
| Mixed-Features Vectors and Subspace Splitting |
❌ |
✅ |
❌ |
❌ |
❌ |
❌ |
❌ |
1 |
| MoPro: Webly Supervised Learning with Momentum Prototypes |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| MoVie: Revisiting Modulated Convolutions for Visual Counting and Beyond |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Model Patching: Closing the Subgroup Performance Gap with Data Augmentation |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
✅ |
5 |
| Model-Based Offline Planning |
✅ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Model-Based Visual Planning with Self-Supervised Functional Distances |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Model-based micro-data reinforcement learning: what are the crucial model properties and which model to choose? |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Modeling the Second Player in Distributionally Robust Optimization |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Modelling Hierarchical Structure between Dialogue Policy and Natural Language Generator with Option Framework for Task-oriented Dialogue System |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Molecule Optimization by Explainable Evolution |
✅ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
5 |
| Monotonic Kronecker-Factored Lattice |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Monte-Carlo Planning and Learning with Language Action Value Estimates |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| More or Less: When and How to Build Convolutional Neural Network Ensembles |
❌ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
3 |
| Multi-Class Uncertainty Calibration via Mutual Information Maximization-based Binning |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Multi-Level Local SGD: Distributed SGD for Heterogeneous Hierarchical Networks |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
✅ |
5 |
| Multi-Prize Lottery Ticket Hypothesis: Finding Accurate Binary Neural Networks by Pruning A Randomly Weighted Network |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Multi-Time Attention Networks for Irregularly Sampled Time Series |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Multi-resolution modeling of a discrete stochastic process identifies causes of cancer |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
4 |
| Multi-timescale Representation Learning in LSTM Language Models |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
✅ |
5 |
| MultiModalQA: complex question answering over text, tables and images |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
3 |
| Multiplicative Filter Networks |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Multiscale Score Matching for Out-of-Distribution Detection |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Multivariate Probabilistic Time Series Forecasting via Conditioned Normalizing Flows |
❌ |
✅ |
✅ |
✅ |
✅ |
✅ |
✅ |
6 |
| Mutual Information State Intrinsic Control |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| My Body is a Cage: the Role of Morphology in Graph-Based Incompatible Control |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| NAS-Bench-ASR: Reproducible Neural Architecture Search for Speech Recognition |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| NBDT: Neural-Backed Decision Tree |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| NOVAS: Non-convex Optimization via Adaptive Stochastic Search for End-to-end Learning and Control |
✅ |
✅ |
❌ |
✅ |
✅ |
✅ |
✅ |
6 |
| NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimation |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Nearest Neighbor Machine Translation |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Negative Data Augmentation |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Net-DNF: Effective Deep Modeling of Tabular Data |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Network Pruning That Matters: A Case Study on Retraining Variants |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Neural Approximate Sufficient Statistics for Implicit Models |
✅ |
✅ |
❌ |
✅ |
❌ |
❌ |
✅ |
4 |
| Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Neural Delay Differential Equations |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Neural Jump Ordinary Differential Equations: Consistent Continuous-Time Prediction and Filtering |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Neural Learning of One-of-Many Solutions for Combinatorial Problems in Structured Output Spaces |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Neural Mechanics: Symmetry and Broken Conservation Laws in Deep Learning Dynamics |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Neural Networks for Learning Counterfactual G-Invariances from Single Environments |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Neural ODE Processes |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Neural Pruning via Growing Regularization |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Neural Spatio-Temporal Point Processes |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Neural Synthesis of Binaural Speech From Mono Audio |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Neural Thompson Sampling |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Neural Topic Model via Optimal Transport |
✅ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| Neural gradients are near-lognormal: improved quantized and sparse training |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
4 |
| Neural networks with late-phase weights |
✅ |
✅ |
✅ |
❌ |
✅ |
✅ |
✅ |
6 |
| Neural representation and generation for RNA secondary structures |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Neurally Augmented ALISTA |
✅ |
✅ |
❌ |
❌ |
✅ |
❌ |
✅ |
4 |
| New Bounds For Distributed Mean Estimation and Variance Reduction |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
✅ |
1 |
| No Cost Likelihood Manipulation at Test Time for Making Better Mistakes in Deep Networks |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| No MCMC for me: Amortized sampling for fast and stable training of energy-based models |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Noise against noise: stochastic label noise helps combat inherent label noise |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Noise or Signal: The Role of Image Backgrounds in Object Recognition |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Non-asymptotic Confidence Intervals of Off-policy Evaluation: Primal and Dual Bounds |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Nonseparable Symplectic Neural Networks |
✅ |
❌ |
❌ |
✅ |
❌ |
❌ |
✅ |
3 |
| OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Offline Model-Based Optimization via Normalized Maximum Likelihood Estimation |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| On Data-Augmentation and Consistency-Based Semi-Supervised Learning |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
✅ |
1 |
| On Dyadic Fairness: Exploring and Mitigating Bias in Graph Connections |
✅ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| On Graph Neural Networks versus Graph-Augmented MLPs |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| On InstaHide, Phase Retrieval, and Sparse Matrix Factorization |
✅ |
❌ |
❌ |
✅ |
❌ |
❌ |
✅ |
3 |
| On Learning Universal Representations Across Languages |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
4 |
| On Position Embeddings in BERT |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| On Self-Supervised Image Representations for GAN Evaluation |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| On Statistical Bias In Active Learning: How and When to Fix It |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
4 |
| On the Bottleneck of Graph Neural Networks and its Practical Implications |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| On the Critical Role of Conventions in Adaptive Human-AI Collaboration |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| On the Curse of Memory in Recurrent Neural Networks: Approximation and Optimization Analysis |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
0 |
| On the Dynamics of Training Attention Models |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| On the Impossibility of Global Convergence in Multi-Loss Optimization |
❌ |
✅ |
❌ |
❌ |
❌ |
❌ |
✅ |
2 |
| On the Origin of Implicit Regularization in Stochastic Gradient Descent |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| On the Theory of Implicit Deep Learning: Global Convergence with Implicit Layers |
❌ |
❌ |
✅ |
❌ |
❌ |
✅ |
✅ |
3 |
| On the Transfer of Disentangled Representations in Realistic Settings |
❌ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
3 |
| On the Universality of Rotation Equivariant Point Cloud Networks |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
4 |
| On the Universality of the Double Descent Peak in Ridgeless Regression |
❌ |
✅ |
❌ |
❌ |
❌ |
❌ |
✅ |
2 |
| On the geometry of generalization and memorization in deep neural networks |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| On the mapping between Hopfield networks and Restricted Boltzmann Machines |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| On the role of planning in model-based deep reinforcement learning |
✅ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| One Network Fits All? Modular versus Monolithic Task Formulations in Neural Networks |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Online Adversarial Purification based on Self-supervised Learning |
✅ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
5 |
| Open Question Answering over Tables and Text |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
4 |
| Optimal Conversion of Conventional Artificial Neural Networks to Spiking Neural Networks |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Optimal Rates for Averaged Stochastic Gradient Descent under Neural Tangent Kernel Regime |
✅ |
❌ |
❌ |
❌ |
❌ |
❌ |
✅ |
2 |
| Optimal Regularization can Mitigate Double Descent |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Optimism in Reinforcement Learning with Generalized Linear Function Approximation |
✅ |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
1 |
| Optimizing Memory Placement using Evolutionary Graph Reinforcement Learning |
✅ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| Orthogonalizing Convolutional Layers with the Cayley Transform |
✅ |
✅ |
✅ |
❌ |
✅ |
✅ |
✅ |
6 |
| Overfitting for Fun and Profit: Instance-Adaptive Data Compression |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Overparameterisation and worst-case generalisation: friend or foe? |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| PAC Confidence Predictions for Deep Neural Network Classifiers |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| PC2WF: 3D Wireframe Reconstruction from Raw Point Clouds |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
2 |
| PDE-Driven Spatiotemporal Disentanglement |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
✅ |
5 |
| PMI-Masking: Principled masking of correlated spans |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
4 |
| Parameter Efficient Multimodal Transformers for Video Representation Learning |
❌ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
3 |
| Parameter-Based Value Functions |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Parrot: Data-Driven Behavioral Priors for Reinforcement Learning |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Partitioned Learned Bloom Filters |
✅ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| Perceptual Adversarial Robustness: Defense Against Unseen Threat Models |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Personalized Federated Learning with First Order Model Optimization |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Physics-aware, probabilistic model order reduction with guaranteed stability |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
✅ |
1 |
| Plan-Based Relaxed Reward Shaping for Goal-Directed Tasks |
❌ |
✅ |
❌ |
❌ |
❌ |
❌ |
✅ |
2 |
| Planning from Pixels using Inverse Dynamics Models |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physics |
✅ |
✅ |
❌ |
❌ |
✅ |
❌ |
✅ |
4 |
| PolarNet: Learning to Optimize Polar Keypoints for Keypoint Based Object Detection |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Policy-Driven Attack: Learning to Query for Hard-label Black-box Adversarial Examples |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Practical Massively Parallel Monte-Carlo Tree Search Applied to Molecular Design |
✅ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
5 |
| Practical Real Time Recurrent Learning with a Sparse Approximation |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Pre-training Text-to-Text Transformers for Concept-centric Common Sense |
✅ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Predicting Classification Accuracy When Adding New Unobserved Classes |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
✅ |
6 |
| Predicting Inductive Biases of Pre-Trained Models |
❌ |
✅ |
❌ |
✅ |
❌ |
❌ |
✅ |
3 |
| Predicting Infectiousness for Proactive Contact Tracing |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Prediction and generalisation over directed actions by grid cells |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Primal Wasserstein Imitation Learning |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Private Image Reconstruction from System Side Channels Using Generative Models |
❌ |
✅ |
✅ |
❌ |
✅ |
✅ |
✅ |
5 |
| Private Post-GAN Boosting |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Probabilistic Numeric Convolutional Neural Networks |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Probing BERT in Hyperbolic Spaces |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Progressive Skeletonization: Trimming more fat from a network at initialization |
✅ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Projected Latent Markov Chain Monte Carlo: Conditional Sampling of Normalizing Flows |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Property Controllable Variational Autoencoder via Invertible Mutual Dependence |
❌ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| Protecting DNNs from Theft using an Ensemble of Diverse Models |
❌ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
3 |
| Prototypical Contrastive Learning of Unsupervised Representations |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Prototypical Representation Learning for Relation Extraction |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Provable Rich Observation Reinforcement Learning with Combinatorial Latent States |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
✅ |
5 |
| Provably robust classification of adversarial examples with detection |
✅ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
5 |
| Proximal Gradient Descent-Ascent: Variable Convergence under KŁ Geometry |
✅ |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
1 |
| Pruning Neural Networks at Initialization: Why Are We Missing the Mark? |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| PseudoSeg: Designing Pseudo Labels for Semantic Segmentation |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| QPLEX: Duplex Dueling Multi-Agent Q-Learning |
❌ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
3 |
| Quantifying Differences in Reward Functions |
❌ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| R-GAP: Recursive Gradient Attack on Privacy |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| RMSprop converges with proper hyper-parameter |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| RODE: Learning Roles to Decompose Multi-Agent Tasks |
❌ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
3 |
| Random Feature Attention |
✅ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Randomized Automatic Differentiation |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Randomized Ensembled Double Q-Learning: Learning Fast Without a Model |
✅ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
5 |
| Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated Environments |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Rao-Blackwellizing the Straight-Through Gumbel-Softmax Gradient Estimator |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Rapid Task-Solving in Novel Environments |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Recurrent Independent Mechanisms |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Reducing the Computational Cost of Deep Generative Models with Binary Neural Networks |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Refining Deep Generative Models via Discriminator Gradient Flow |
✅ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
5 |
| Regularization Matters in Policy Optimization - An Empirical Study on Continuous Control |
❌ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| Regularized Inverse Reinforcement Learning |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Reinforcement Learning with Random Delays |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Relating by Contrasting: A Data-efficient Framework for Multimodal Generative Models |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Remembering for the Right Reasons: Explanations Reduce Catastrophic Forgetting |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Removing Undesirable Feature Contributions Using Out-of-Distribution Data |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Representation Balancing Offline Model-based Reinforcement Learning |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Representation Learning for Sequence Data with Deep Autoencoding Predictive Components |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Representation Learning via Invariant Causal Mechanisms |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
❌ |
1 |
| Representation learning for improved interpretability and classification accuracy of clinical factors from EEG |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Representing Partial Programs with Blended Abstract Semantics |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Repurposing Pretrained Models for Robust Out-of-domain Few-Shot Learning |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| ResNet After All: Neural ODEs and Their Numerical Solution |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
✅ |
5 |
| Reset-Free Lifelong Learning with Skill-Space Planning |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Rethinking Architecture Selection in Differentiable NAS |
✅ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| Rethinking Attention with Performers |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Rethinking Embedding Coupling in Pre-trained Language Models |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Rethinking Positional Encoding in Language Pre-training |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Rethinking Soft Labels for Knowledge Distillation: A Bias–Variance Tradeoff Perspective |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Rethinking the Role of Gradient-based Attribution Methods for Model Interpretability |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Retrieval-Augmented Generation for Code Summarization via Hybrid GNN |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Return-Based Contrastive Representation Learning for Reinforcement Learning |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Revisiting Dynamic Convolution via Matrix Decomposition |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Revisiting Few-sample BERT Fine-tuning |
✅ |
❌ |
✅ |
✅ |
❌ |
✅ |
✅ |
5 |
| Revisiting Hierarchical Approach for Persistent Long-Term Video Prediction |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Revisiting Locally Supervised Learning: an Alternative to End-to-end Training |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Reweighting Augmented Samples by Minimizing the Maximal Expected Loss |
✅ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Ringing ReLUs: Harmonic Distortion Analysis of Nonlinear Feedforward Networks |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
✅ |
5 |
| Risk-Averse Offline Reinforcement Learning |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Robust Curriculum Learning: from clean label detection to noisy label self-correction |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Robust Learning of Fixed-Structure Bayesian Networks in Nearly-Linear Time |
✅ |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
1 |
| Robust Overfitting may be mitigated by properly learned smoothening |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
✅ |
5 |
| Robust Pruning at Initialization |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Robust Reinforcement Learning on State Observations with Learned Optimal Adversary |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Robust and Generalizable Visual Representation Learning via Random Convolutions |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Robust early-learning: Hindering the memorization of noisy labels |
✅ |
✅ |
✅ |
✅ |
✅ |
✅ |
✅ |
7 |
| SAFENet: A Secure, Accurate and Fast Neural Network Inference |
✅ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| SALD: Sign Agnostic Learning with Derivatives |
❌ |
❌ |
✅ |
✅ |
✅ |
✅ |
✅ |
5 |
| SCoRe: Pre-Training for Context Representation in Conversational Semantic Parsing |
✅ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| SEDONA: Search for Decoupled Neural Networks toward Greedy Block-wise Learning |
✅ |
❌ |
✅ |
✅ |
✅ |
✅ |
✅ |
6 |
| SEED: Self-supervised Distillation For Visual Representation |
✅ |
❌ |
✅ |
✅ |
❌ |
✅ |
✅ |
5 |
| SMiRL: Surprise Minimizing Reinforcement Learning in Unstable Environments |
✅ |
❌ |
❌ |
❌ |
❌ |
❌ |
✅ |
2 |
| SOLAR: Sparse Orthogonal Learned and Random Embeddings |
❌ |
❌ |
✅ |
✅ |
✅ |
✅ |
✅ |
5 |
| SSD: A Unified Framework for Self-Supervised Outlier Detection |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Saliency is a Possible Red Herring When Diagnosing Poor Generalization |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularization |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Sample-Efficient Automated Deep Reinforcement Learning |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Scalable Bayesian Inverse Reinforcement Learning |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Scalable Learning and MAP Inference for Nonsymmetric Determinantal Point Processes |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Scalable Transfer Learning with Expert Models |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
3 |
| Scaling Symbolic Methods using Gradients for Neural Model Explanation |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Scaling the Convex Barrier with Active Sets |
✅ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
5 |
| Score-Based Generative Modeling through Stochastic Differential Equations |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Selective Classification Can Magnify Disparities Across Groups |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Selectivity considered harmful: evaluating the causal impact of class selectivity in DNNs |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Self-Supervised Learning of Compressed Video Representations |
✅ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Self-Supervised Policy Adaptation during Deployment |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Self-supervised Adversarial Robustness for the Low-label, High-data Regime |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
4 |
| Self-supervised Learning from a Multi-view Perspective |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Self-supervised Representation Learning with Relative Predictive Coding |
❌ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| Self-supervised Visual Reinforcement Learning with Object-centric Representations |
✅ |
❌ |
❌ |
❌ |
❌ |
❌ |
✅ |
2 |
| Self-training For Few-shot Transfer Across Extreme Task Differences |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Semantic Re-tuning with Contrastive Tension |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Semi-supervised Keypoint Localization |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| SenSeI: Sensitive Set Invariance for Enforcing Individual Fairness |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Separation and Concentration in Deep Networks |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Seq2Tens: An Efficient Representation of Sequences by Low-Rank Tensor Projections |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Sequential Density Ratio Estimation for Simultaneous Optimization of Speed and Accuracy |
❌ |
✅ |
✅ |
✅ |
✅ |
✅ |
✅ |
6 |
| Set Prediction without Imposing Structure as Conditional Density Estimation |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Shape or Texture: Understanding Discriminative Features in CNNs |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Shape-Texture Debiased Neural Network Training |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Shapley Explanation Networks |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Shapley explainability on the data manifold |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Share or Not? Learning to Schedule Language-Specific Capacity for Multilingual Translation |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Sharper Generalization Bounds for Learning with Gradient-dominated Objective Functions |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Sharpness-aware Minimization for Efficiently Improving Generalization |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Signatory: differentiable computations of the signature and logsignature transforms, on both CPU and GPU |
❌ |
✅ |
❌ |
❌ |
✅ |
✅ |
❌ |
3 |
| Simple Augmentation Goes a Long Way: ADRL for DNN Quantization |
✅ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| Simple Spectral Graph Convolution |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Single-Photon Image Classification |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
❌ |
2 |
| Single-Timescale Actor-Critic Provably Finds Globally Optimal Policy |
✅ |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
1 |
| SkipW: Resource Adaptable RNN with Strict Upper Computational Limit |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
4 |
| Sliced Kernelized Stein Discrepancy |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Solving Compositional Reinforcement Learning Problems via Task Reduction |
✅ |
✅ |
❌ |
❌ |
❌ |
❌ |
✅ |
3 |
| Sparse Quantized Spectral Clustering |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Sparse encoding for more-interpretable feature-selecting representations in probabilistic matrix factorization |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Spatial Dependency Networks: Neural Layers for Improved Generative Image Modeling |
✅ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
5 |
| Spatially Structured Recurrent Modules |
❌ |
❌ |
✅ |
✅ |
✅ |
✅ |
✅ |
5 |
| Spatio-Temporal Graph Scattering Transform |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Stabilized Medical Image Attacks |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Statistical inference for individual fairness |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Stochastic Security: Adversarial Defense Using Long-Run Dynamics of Energy-Based Models |
✅ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
5 |
| Structured Prediction as Translation between Augmented Natural Languages |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Supervised Contrastive Learning for Pre-trained Language Model Fine-tuning |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Support-set bottlenecks for video-text representation learning |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
4 |
| Symmetry-Aware Actor-Critic for 3D Molecular Design |
✅ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
5 |
| Systematic generalisation with group invariant predictions |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Taking Notes on the Fly Helps Language Pre-Training |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Taming GANs with Lookahead-Minmax |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Targeted Attack against Deep Neural Networks via Flipping Limited Weight Bits |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Task-Agnostic Morphology Evolution |
✅ |
✅ |
❌ |
❌ |
❌ |
❌ |
✅ |
3 |
| Teaching Temporal Logics to Neural Networks |
❌ |
❌ |
❌ |
✅ |
✅ |
❌ |
✅ |
3 |
| Teaching with Commentaries |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Temporally-Extended ε-Greedy Exploration |
✅ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| Tent: Fully Test-Time Adaptation by Entropy Minimization |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Text Generation by Learning from Demonstrations |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| The Deep Bootstrap Framework: Good Online Learners are Good Offline Generalizers |
❌ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| The Importance of Pessimism in Fixed-Dataset Policy Optimization |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| The Intrinsic Dimension of Images and Its Impact on Learning |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
❌ |
2 |
| The Recurrent Neural Tangent Kernel |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| The Risks of Invariant Risk Minimization |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
✅ |
1 |
| The Role of Momentum Parameters in the Optimal Convergence of Adaptive Polyak's Heavy-ball Methods |
✅ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| The Traveling Observer Model: Multi-task Learning Through Spatial Variable Embeddings |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| The Unreasonable Effectiveness of Patches in Deep Convolutional Kernels Methods |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| The geometry of integration in text classification RNNs |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| The inductive bias of ReLU networks on orthogonally separable data |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| The role of Disentanglement in Generalisation |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Theoretical bounds on estimation error for meta-learning |
❌ |
✅ |
❌ |
❌ |
❌ |
❌ |
✅ |
2 |
| Tilted Empirical Risk Minimization |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Tomographic Auto-Encoder: Unsupervised Bayesian Recovery of Corrupted Data |
✅ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| Topology-Aware Segmentation Using Discrete Morse Theory |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis |
❌ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| Towards Impartial Multi-task Learning |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Towards Resolving the Implicit Bias of Gradient Descent for Matrix Factorization: Greedy Low-Rank Learning |
✅ |
❌ |
❌ |
❌ |
❌ |
❌ |
✅ |
2 |
| Towards Robust Neural Networks via Close-loop Control |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Towards Robustness Against Natural Language Word Substitutions |
✅ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
5 |
| Tradeoffs in Data Augmentation: An Empirical Study |
❌ |
❌ |
✅ |
✅ |
❌ |
✅ |
✅ |
4 |
| Training BatchNorm and Only BatchNorm: On the Expressive Power of Random Features in CNNs |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Training GANs with Stronger Augmentations via Contrastive Discriminator |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Training independent subnetworks for robust prediction |
✅ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
5 |
| Training with Quantization Noise for Extreme Model Compression |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Trajectory Prediction using Equivariant Continuous Convolution |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Transformer protein language models are unsupervised structure learners |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Transient Non-stationarity and Generalisation in Deep Reinforcement Learning |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| TropEx: An Algorithm for Extracting Linear Terms in Deep Neural Networks |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Trusted Multi-View Classification |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| UMEC: Unified model and embedding compression for efficient recommendation systems |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| UPDeT: Universal Multi-agent RL via Policy Decoupling with Transformers |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Unbiased Teacher for Semi-Supervised Object Detection |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Uncertainty Estimation and Calibration with Finite-State Probabilistic RNNs |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Uncertainty Estimation in Autoregressive Structured Prediction |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
4 |
| Uncertainty Sets for Image Classifiers using Conformal Prediction |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Uncertainty in Gradient Boosting via Ensembles |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Uncertainty-aware Active Learning for Optimal Bayesian Classifier |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Understanding Over-parameterization in Generative Adversarial Networks |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Understanding and Improving Encoder Layer Fusion in Sequence-to-Sequence Learning |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Understanding and Improving Lexical Choice in Non-Autoregressive Translation |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Understanding the effects of data parallelism and sparsity on neural network training |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Understanding the failure modes of out-of-distribution generalization |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Understanding the role of importance weighting for deep learning |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
✅ |
1 |
| Undistillable: Making A Nasty Teacher That CANNOT teach students |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Universal Weakly Supervised Segmentation by Pixel-to-Segment Contrastive Learning |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Universal approximation power of deep residual neural networks via nonlinear control theory |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
0 |
| Unlearnable Examples: Making Personal Data Unexploitable |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| Unsupervised Audiovisual Synthesis via Exemplar Autoencoders |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Unsupervised Discovery of 3D Physical Objects from Video |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Unsupervised Meta-Learning through Latent-Space Interpolation in Generative Models |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Unsupervised Object Keypoint Learning using Local Spatial Predictability |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Unsupervised Representation Learning for Time Series with Temporal Neighborhood Coding |
❌ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| Usable Information and Evolution of Optimal Representations During Training |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Using latent space regression to analyze and leverage compositionality in GANs |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| VA-RED$^2$: Video Adaptive Redundancy Reduction |
❌ |
✅ |
✅ |
✅ |
✅ |
✅ |
✅ |
6 |
| VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models |
❌ |
❌ |
✅ |
❌ |
✅ |
✅ |
✅ |
4 |
| VCNet and Functional Targeted Regularization For Learning Causal Effects of Continuous Treatments |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| VTNet: Visual Transformer Network for Object Goal Navigation |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Variational Information Bottleneck for Effective Low-Resource Fine-Tuning |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Variational Intrinsic Control Revisited |
✅ |
❌ |
❌ |
❌ |
❌ |
❌ |
✅ |
2 |
| Variational State-Space Models for Localisation and Dense 3D Mapping in 6 DoF |
❌ |
❌ |
✅ |
✅ |
✅ |
✅ |
✅ |
5 |
| Vector-output ReLU Neural Network Problems are Copositive Programs: Convex Analysis of Two Layer Networks and Polynomial-time Algorithms |
✅ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images |
❌ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| Viewmaker Networks: Learning Views for Unsupervised Representation Learning |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Vulnerability-Aware Poisoning Mechanism for Online RL with Unknown Dynamics |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| WaNet - Imperceptible Warping-based Backdoor Attack |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Wandering within a world: Online contextualized few-shot learning |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Wasserstein Embedding for Graph Learning |
❌ |
✅ |
✅ |
✅ |
✅ |
✅ |
✅ |
6 |
| Wasserstein-2 Generative Networks |
✅ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
5 |
| Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| WaveGrad: Estimating Gradients for Waveform Generation |
✅ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| What Can You Learn From Your Muscles? Learning Visual Representation from Human Interactions |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| What Makes Instance Discrimination Good for Transfer Learning? |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| What Matters for On-Policy Deep Actor-Critic Methods? A Large-Scale Study |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
✅ |
4 |
| What Should Not Be Contrastive in Contrastive Learning |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| What are the Statistical Limits of Offline RL with Linear Function Approximation? |
✅ |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
1 |
| What they do when in doubt: a study of inductive biases in seq2seq learners |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| When Do Curricula Work? |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| When Optimizing $f$-Divergence is Robust with Label Noise |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| When does preconditioning help or hurt generalization? |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Why Are Convolutional Nets More Sample-Efficient than Fully-Connected Nets? |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Why resampling outperforms reweighting for correcting sampling bias with stochastic gradients |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Winning the L2RPN Challenge: Power Grid Management via Semi-Markov Afterstate Actor-Critic |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| WrapNet: Neural Net Inference with Ultra-Low-Precision Arithmetic |
✅ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| X2T: Training an X-to-Text Typing Interface with Online Learning from User Feedback |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| You Only Need Adversarial Supervision for Semantic Image Synthesis |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Zero-Cost Proxies for Lightweight NAS |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Zero-shot Synthesis with Group-Supervised Learning |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| gradSim: Differentiable simulation for system identification and visuomotor control |
✅ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
5 |
| not-MIWAE: Deep Generative Modelling with Missing not at Random Data |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |