| A Comprehensive Study of Real-Time Object Detection Networks Across Multiple Domains: A Survey |
β |
β |
β
|
β
|
β
|
β
|
β
|
5 |
| A Crisis In Simulation-Based Inference? Beware, Your Posterior Approximations Can Be Unfaithful |
β |
β
|
β |
β
|
β |
β |
β
|
3 |
| A Generalist Agent |
β |
β |
β
|
β
|
β
|
β |
β
|
4 |
| A Note on "Assessing Generalization of SGD via Disagreement" |
β |
β
|
β
|
β
|
β |
β |
β
|
4 |
| A Rigorous Study Of The Deep Taylor Decomposition |
β
|
β
|
β
|
β |
β |
β |
β |
3 |
| A Self-Supervised Framework for Function Learning and Extrapolation |
β |
β |
β |
β
|
β |
β |
β
|
2 |
| A Simple Convergence Proof of Adam and Adagrad |
β |
β |
β
|
β |
β
|
β |
β
|
3 |
| A Snapshot of the Frontiers of Client Selection in Federated Learning |
β |
β |
β
|
β |
β |
β |
β |
1 |
| A Stochastic Optimization Framework for Fair Risk Minimization |
β
|
β
|
β
|
β
|
β |
β |
β
|
5 |
| A Unified Domain Adaptation Framework with Distinctive Divergence Analysis |
β |
β |
β
|
β
|
β
|
β |
β
|
4 |
| A Unified Survey on Anomaly, Novelty, Open-Set, and Out of-Distribution Detection: Solutions and Future Challenges |
β
|
β
|
β
|
β
|
β |
β |
β |
4 |
| A geometrical connection between sparse and low-rank matrices and its application to manifold learning |
β |
β |
β
|
β
|
β |
β |
β
|
3 |
| ANCER: Anisotropic Certification via Sample-wise Volume Maximization |
β
|
β
|
β
|
β
|
β
|
β |
β
|
6 |
| Action Noise in Off-Policy Deep Reinforcement Learning: Impact on Exploration and Performance |
β
|
β
|
β
|
β |
β
|
β |
β
|
5 |
| Adversarial Feature Augmentation and Normalization for Visual Recognition |
β
|
β
|
β
|
β
|
β
|
β |
β
|
6 |
| Algorithms and Theory for Supervised Gradual Domain Adaptation |
β |
β |
β
|
β |
β |
β |
β |
1 |
| An Efficient One-Class SVM for Novelty Detection in IoT |
β
|
β
|
β
|
β
|
β
|
β
|
β
|
7 |
| An approximate sampler for energy-based models with divergence diagnostics |
β
|
β |
β
|
β |
β |
β |
β
|
3 |
| An empirical study of implicit regularization in deep offline RL |
β
|
β |
β
|
β
|
β |
β |
β
|
4 |
| Approximate Policy Iteration with Bisimulation Metrics |
β
|
β |
β |
β |
β
|
β |
β
|
3 |
| Approximating 1-Wasserstein Distance with Trees |
β
|
β
|
β
|
β
|
β
|
β |
β
|
6 |
| Attentive Walk-Aggregating Graph Neural Networks |
β
|
β
|
β
|
β
|
β
|
β |
β
|
6 |
| Attribute Prediction as Multiple Instance Learning |
β |
β |
β
|
β
|
β |
β |
β
|
3 |
| Auto-Lambda: Disentangling Dynamic Task Relationships |
β |
β
|
β
|
β |
β |
β |
β
|
3 |
| Bayesian Methods for Constraint Inference in Reinforcement Learning |
β
|
β |
β
|
β |
β |
β |
β
|
3 |
| Behind the Machineβs Gaze: Neural Networks with Biologically-inspired Constraints Exhibit Human-like Visual Attention |
β |
β |
β
|
β |
β |
β |
β
|
2 |
| Benchmarking Progress to Infant-Level Physical Reasoning in AI |
β |
β
|
β
|
β
|
β |
β |
β |
3 |
| Benchmarking and Analyzing Unsupervised Network Representation Learning and the Illusion of Progress |
β |
β
|
β
|
β
|
β
|
β |
β
|
5 |
| Birds of a Feather Trust Together: Knowing When to Trust a Classifier via Adaptive Neighborhood Aggregation |
β
|
β
|
β
|
β |
β |
β |
β |
3 |
| Boosting Search Engines with Interactive Agents |
β
|
β
|
β
|
β
|
β
|
β |
β
|
6 |
| Bridging Offline and Online Experimentation: Constraint Active Search for Deployed Performance Optimization |
β
|
β |
β
|
β
|
β
|
β |
β
|
5 |
| COIN++: Neural Compression Across Modalities |
β |
β
|
β
|
β
|
β
|
β
|
β
|
6 |
| Calibrated Selective Classification |
β
|
β
|
β
|
β
|
β |
β |
β
|
5 |
| Can You Win Everything with A Lottery Ticket? |
β |
β
|
β
|
β
|
β |
β |
β
|
4 |
| Causal Feature Selection via Orthogonal Search |
β
|
β
|
β
|
β
|
β |
β |
β
|
5 |
| Centroids Matching: an efficient Continual Learning approach operating in the embedding space |
β |
β
|
β
|
β |
β |
β |
β
|
3 |
| Clustering units in neural networks: upstream vs downstream information |
β
|
β
|
β
|
β |
β |
β |
β
|
4 |
| CoCa: Contrastive Captioners are Image-Text Foundation Models |
β |
β |
β
|
β
|
β
|
β |
β
|
4 |
| Collaborative Algorithms for Online Personalized Mean Estimation |
β
|
β
|
β
|
β |
β |
β |
β
|
4 |
| Competition over data: how does data purchase affect users? |
β
|
β
|
β
|
β
|
β |
β |
β
|
5 |
| Completeness and Coherence Learning for Fast Arbitrary Style Transfer |
β |
β |
β
|
β |
β
|
β |
β
|
3 |
| Complex-Valued Autoencoders for Object Discovery |
β |
β
|
β
|
β
|
β
|
β
|
β
|
6 |
| Concave Utility Reinforcement Learning with Zero-Constraint Violations |
β
|
β |
β |
β |
β
|
β |
β
|
3 |
| Conformal Prediction Intervals with Temporal Dependence |
β
|
β
|
β
|
β
|
β |
β |
β
|
5 |
| Controllable Generative Modeling via Causal Reasoning |
β
|
β |
β
|
β |
β |
β |
β
|
3 |
| Convergence of denoising diffusion models under the manifold hypothesis |
β |
β |
β |
β |
β |
β |
β |
0 |
| Counterfactual Learning with Multioutput Deep Kernels |
β |
β
|
β
|
β
|
β
|
β |
β
|
5 |
| DHA: End-to-End Joint Optimization of Data Augmentation Policy, Hyper-parameter and Architecture |
β
|
β |
β
|
β |
β
|
β
|
β |
4 |
| DR-DSGD: A Distributionally Robust Decentralized Learning Algorithm over Graphs |
β
|
β |
β
|
β
|
β |
β |
β
|
4 |
| Data Leakage in Federated Averaging |
β
|
β
|
β
|
β
|
β
|
β |
β
|
6 |
| Decoder Denoising Pretraining for Semantic Segmentation |
β |
β |
β
|
β
|
β
|
β |
β
|
4 |
| Decoding EEG With Spiking Neural Networks on Neuromorphic Hardware |
β |
β
|
β
|
β
|
β
|
β |
β
|
5 |
| Deconstructing Self-Supervised Monocular Reconstruction: The Design Decisions that Matter |
β |
β
|
β
|
β
|
β
|
β |
β
|
5 |
| Deep Classifiers with Label Noise Modeling and Distance Awareness |
β
|
β
|
β
|
β
|
β
|
β |
β
|
6 |
| Deep Learning for Bayesian Optimization of Scientific Problems with High-Dimensional Structure |
β
|
β
|
β
|
β |
β
|
β |
β
|
5 |
| Deep Policies for Online Bipartite Matching: A Reinforcement Learning Approach |
β
|
β
|
β
|
β
|
β
|
β
|
β
|
7 |
| Deformation Robust Roto-Scale-Translation Equivariant CNNs |
β |
β
|
β
|
β
|
β |
β |
β
|
4 |
| Degradation Attacks on Certifiably Robust Neural Networks |
β
|
β
|
β
|
β
|
β
|
β |
β
|
6 |
| Diagnosing and Fixing Manifold Overfitting in Deep Generative Models |
β |
β
|
β
|
β |
β |
β |
β
|
3 |
| Did I do that? Blame as a means to identify controlled effects in reinforcement learning |
β |
β |
β
|
β
|
β |
β |
β
|
3 |
| Differentiable Model Compression via Pseudo Quantization Noise |
β |
β
|
β
|
β
|
β
|
β |
β
|
5 |
| Differentially Private Stochastic Expectation Propagation |
β
|
β
|
β
|
β
|
β |
β |
β
|
5 |
| DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latents |
β
|
β
|
β
|
β
|
β
|
β |
β
|
6 |
| Diffusion Models for Video Prediction and Infilling |
β
|
β
|
β
|
β
|
β
|
β |
β
|
6 |
| Direct Molecular Conformation Generation |
β |
β
|
β
|
β
|
β
|
β |
β
|
5 |
| Distributed Stochastic Algorithms for High-rate Streaming Principal Component Analysis |
β
|
β |
β
|
β |
β |
β |
β
|
3 |
| Distribution Embedding Networks for Generalization from a Diverse Set of Classification Tasks |
β |
β
|
β
|
β
|
β |
β |
β
|
4 |
| Do ReLU Networks Have An Edge When Approximating Compactly-Supported Functions? |
β |
β |
β |
β |
β |
β |
β |
0 |
| Do better ImageNet classifiers assess perceptual similarity better? |
β
|
β
|
β
|
β
|
β |
β |
β
|
5 |
| Does Entity Abstraction Help Generative Transformers Reason? |
β |
β |
β
|
β
|
β
|
β
|
β
|
5 |
| Domain Invariant Adversarial Learning |
β
|
β
|
β
|
β
|
β |
β |
β
|
5 |
| Domain-invariant Feature Exploration for Domain Generalization |
β |
β
|
β
|
β
|
β |
β |
β
|
4 |
| Efficient CDF Approximations for Normalizing Flows |
β
|
β
|
β
|
β |
β
|
β |
β
|
5 |
| Efficient Gradient Flows in Sliced-Wasserstein Space |
β
|
β |
β
|
β
|
β
|
β |
β
|
5 |
| Emergent Abilities of Large Language Models |
β |
β |
β
|
β |
β |
β |
β |
1 |
| Enhanced gradient-based MCMC in discrete spaces |
β
|
β |
β
|
β |
β |
β
|
β
|
4 |
| Ensembles of Classifiers: a Bias-Variance Perspective |
β
|
β |
β
|
β
|
β |
β |
β
|
4 |
| Equivariant Mesh Attention Networks |
β
|
β
|
β
|
β
|
β |
β |
β
|
5 |
| Estimating Potential Outcome Distributions with Collaborating Causal Networks |
β |
β
|
β
|
β
|
β
|
β |
β
|
5 |
| Evolving Decomposed Plasticity Rules for Information-Bottlenecked Meta-Learning |
β
|
β
|
β
|
β
|
β
|
β |
β
|
6 |
| Explicit Group Sparse Projection with Applications to Deep Learning and NMF |
β
|
β
|
β
|
β |
β |
β |
β
|
4 |
| Exploring Efficient Few-shot Adaptation for Vision Transformers |
β |
β
|
β
|
β
|
β |
β |
β
|
4 |
| Exploring Generative Neural Temporal Point Process |
β
|
β
|
β
|
β
|
β
|
β |
β
|
6 |
| Exploring the Learning Mechanisms of Neural Division Modules |
β |
β
|
β
|
β
|
β
|
β |
β
|
5 |
| Exposing Outlier Exposure: What Can Be Learned From Few, One, and Zero Outlier Images |
β
|
β
|
β
|
β
|
β |
β |
β
|
5 |
| Extracting Local Reasoning Chains of Deep Neural Networks |
β |
β |
β
|
β
|
β
|
β |
β
|
4 |
| FLEA: Provably Robust Fair Multisource Learning from Unreliable Training Data |
β
|
β
|
β
|
β
|
β |
β |
β
|
5 |
| Fail-Safe Adversarial Generative Imitation Learning |
β |
β
|
β
|
β
|
β |
β |
β |
3 |
| Failure Detection in Medical Image Classification: A Reality Check and Benchmarking Testbed |
β |
β
|
β
|
β
|
β |
β |
β
|
4 |
| Faking Interpolation Until You Make It |
β
|
β
|
β
|
β
|
β
|
β |
β
|
6 |
| Fast and Accurate Spreading Process Temporal Scale Estimation |
β
|
β |
β
|
β |
β |
β |
β
|
3 |
| FedShuffle: Recipes for Better Use of Local Work in Federated Learning |
β
|
β |
β
|
β
|
β |
β
|
β
|
5 |
| Finding and Fixing Spurious Patterns with Explanations |
β
|
β
|
β
|
β
|
β |
β |
β
|
5 |
| Fingerprints of Super Resolution Networks |
β |
β |
β
|
β
|
β |
β |
β
|
3 |
| Flipped Classroom: Effective Teaching for Time Series Forecasting |
β |
β
|
β
|
β
|
β |
β |
β
|
4 |
| Fourier Sensitivity and Regularization of Computer Vision Models |
β
|
β |
β
|
β
|
β |
β |
β
|
4 |
| From Optimization Dynamics to Generalization Bounds via Εojasiewicz Gradient Inequality |
β
|
β |
β
|
β |
β |
β |
β
|
3 |
| GFNet: Geometric Flow Network for 3D Point Cloud Semantic Segmentation |
β
|
β
|
β
|
β
|
β
|
β |
β
|
6 |
| GIT: A Generative Image-to-text Transformer for Vision and Language |
β |
β |
β
|
β
|
β |
β |
β
|
3 |
| GemNet-OC: Developing Graph Neural Networks for Large and Diverse Molecular Simulation Datasets |
β |
β
|
β
|
β
|
β
|
β |
β
|
5 |
| Generative Adversarial Neural Operators |
β
|
β
|
β
|
β |
β |
β |
β
|
4 |
| GhostSR: Learning Ghost Features for Efficient Image Super-Resolution |
β |
β |
β
|
β
|
β
|
β |
β
|
4 |
| Greedy Bayesian Posterior Approximation with Deep Ensembles |
β
|
β
|
β
|
β
|
β
|
β |
β
|
6 |
| HEAT: Hyperedge Attention Networks |
β
|
β
|
β
|
β |
β |
β |
β
|
4 |
| High Fidelity Visualization of What Your Self-Supervised Representation Knows About |
β |
β
|
β
|
β
|
β |
β |
β |
3 |
| How Expressive are Transformers in Spectral Domain for Graphs? |
β |
β |
β
|
β
|
β
|
β |
β
|
4 |
| How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers |
β |
β
|
β
|
β
|
β
|
β |
β
|
5 |
| INR-V: A Continuous Representation Space for Video-based Generative Tasks |
β |
β
|
β
|
β
|
β
|
β |
β
|
5 |
| Identifiable Deep Generative Models via Sparse Decoding |
β
|
β
|
β
|
β
|
β
|
β |
β
|
6 |
| Identifying Causal Structure in Dynamical Systems |
β
|
β
|
β |
β |
β |
β |
β
|
3 |
| If your data distribution shifts, use self-learning |
β |
β
|
β
|
β
|
β
|
β
|
β
|
6 |
| Improving the Trainability of Deep Neural Networks through Layerwise Batch-Entropy Regularization |
β |
β
|
β
|
β
|
β |
β |
β
|
4 |
| Incorporating Sum Constraints into Multitask Gaussian Processes |
β
|
β
|
β
|
β
|
β
|
β |
β
|
6 |
| Indiscriminate Data Poisoning Attacks on Neural Networks |
β
|
β |
β
|
β
|
β
|
β |
β
|
5 |
| Infinitely wide limits for deep Stable neural networks: sub-linear, linear and super-linear activation functions |
β |
β |
β |
β |
β |
β |
β |
0 |
| Integrating Rankings into Quantized Scores in Peer Review |
β
|
β
|
β
|
β |
β |
β |
β
|
4 |
| Interpretable Node Representation with Attribute Decoding |
β
|
β |
β
|
β
|
β |
β |
β
|
4 |
| Iterative State Estimation in Non-linear Dynamical Systems Using Approximate Expectation Propagation |
β
|
β
|
β
|
β |
β |
β |
β
|
4 |
| LIMIS: Locally Interpretable Modeling using Instance-wise Subsampling |
β
|
β |
β
|
β |
β
|
β |
β
|
4 |
| Lazy vs hasty: linearization in deep networks impacts learning schedule based on example difficulty |
β |
β |
β
|
β
|
β |
β |
β
|
3 |
| Learning Accurate Decision Trees with Bandit Feedback via Quantized Gradient Descent |
β
|
β
|
β
|
β
|
β |
β
|
β
|
6 |
| Learning Algorithms for Markovian Bandits:\\Is Posterior Sampling more Scalable than Optimism? |
β
|
β
|
β
|
β |
β |
β |
β
|
4 |
| Learning Two-Step Hybrid Policy for Graph-Based Interpretable Reinforcement Learning |
β |
β |
β
|
β
|
β |
β |
β
|
3 |
| Learning the Transformer Kernel |
β |
β
|
β
|
β
|
β
|
β |
β
|
5 |
| Learning to Switch Among Agents in a Team via 2-Layer Markov Decision Processes |
β
|
β |
β
|
β |
β |
β |
β
|
3 |
| Linear algebra with transformers |
β |
β
|
β |
β
|
β
|
β |
β
|
4 |
| Local Kernel Ridge Regression for Scalable, Interpolating, Continuous Regression |
β
|
β |
β
|
β
|
β |
β |
β
|
4 |
| Lookback for Learning to Branch |
β |
β |
β
|
β
|
β
|
β
|
β
|
5 |
| MVSFormer: Multi-View Stereo by Learning Robust Image Features and Temperature-based Depth |
β
|
β
|
β
|
β
|
β
|
β |
β
|
6 |
| Mace: A flexible framework for membership privacy estimation in generative models |
β
|
β |
β
|
β
|
β |
β |
β
|
4 |
| Max-Affine Spline Insights Into Deep Network Pruning |
β
|
β
|
β
|
β
|
β
|
β |
β
|
6 |
| Mean-Field Langevin Dynamics : Exponential Convergence and Annealing |
β |
β
|
β |
β |
β |
β |
β
|
2 |
| Meta-Learning Sparse Compression Networks |
β |
β |
β
|
β |
β |
β |
β
|
2 |
| Mitigating Catastrophic Forgetting in Spiking Neural Networks through Threshold Modulation |
β
|
β
|
β
|
β
|
β |
β |
β
|
5 |
| MixTailor: Mixed Gradient Aggregation for Robust Learning Against Tailored Attacks |
β |
β |
β
|
β
|
β
|
β |
β
|
4 |
| Modeling Bounded Rationality in Multi-Agent Simulations Using Rationally Inattentive Reinforcement Learning |
β |
β |
β |
β |
β |
β |
β
|
1 |
| Modeling Object Dissimilarity for Deep Saliency Prediction |
β |
β
|
β
|
β
|
β
|
β |
β
|
5 |
| Momentum Capsule Networks |
β
|
β
|
β
|
β |
β |
β |
β
|
4 |
| Multi-Agent Off-Policy TDC with Near-Optimal Sample and Communication Complexities |
β
|
β |
β |
β |
β |
β |
β
|
2 |
| Multi-Source Causal Inference Using Control Variates under Outcome Selection Bias |
β |
β |
β
|
β |
β |
β |
β |
1 |
| Multitask Online Mirror Descent |
β
|
β |
β
|
β |
β |
β |
β
|
3 |
| NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenes |
β |
β |
β
|
β
|
β
|
β |
β
|
4 |
| No More Pesky Hyperparameters: Offline Hyperparameter Tuning for RL |
β
|
β |
β |
β |
β |
β |
β
|
2 |
| NoiLin: Improving adversarial training and correcting stereotype of noisy labels |
β
|
β
|
β
|
β
|
β
|
β |
β
|
6 |
| Non-Deterministic Behavior of Thompson Sampling with Linear Payoffs and How to Avoid It |
β
|
β
|
β
|
β
|
β |
β |
β |
4 |
| Nonparametric Learning of Two-Layer ReLU Residual Units |
β
|
β
|
β
|
β
|
β
|
β
|
β
|
7 |
| Nonstationary Reinforcement Learning with Linear Function Approximation |
β
|
β |
β |
β |
β
|
β |
β
|
3 |
| Object-aware Cropping for Self-Supervised Learning |
β |
β |
β
|
β
|
β |
β |
β
|
3 |
| On Characterizing the Trade-off in Invariant Representation Learning |
β |
β
|
β
|
β
|
β |
β |
β
|
4 |
| On Noise Abduction for Answering Counterfactual Queries: A Practical Outlook |
β |
β
|
β
|
β |
β
|
β |
β
|
4 |
| On Pseudo-Labeling for Class-Mismatch Semi-Supervised Learning |
β
|
β |
β
|
β
|
β |
β |
β
|
4 |
| On Robustness to Missing Video for Audiovisual Speech Recognition |
β |
β
|
β
|
β
|
β |
β |
β
|
4 |
| On Sample Complexity of Offline Reinforcement Learning with Deep ReLU Networks in Besov Spaces |
β
|
β |
β |
β |
β |
β |
β |
1 |
| On Uncertainty in Deep State Space Models for Model-Based Reinforcement Learning |
β |
β
|
β
|
β |
β |
β |
β
|
3 |
| On the Adversarial Robustness of Vision Transformers |
β |
β
|
β
|
β
|
β |
β |
β
|
4 |
| On the Choice of Interpolation Scheme for Neural CDEs |
β |
β
|
β
|
β
|
β
|
β |
β
|
5 |
| On the Convergence of Shallow Neural Network Training with Randomly Masked Neurons |
β
|
β |
β
|
β |
β |
β |
β
|
3 |
| On the Near-Optimality of Local Policies in Large Cooperative Multi-Agent Reinforcement Learning |
β
|
β
|
β |
β |
β |
β |
β
|
3 |
| On the Origins of the Block Structure Phenomenon in Neural Network Representations |
β |
β |
β
|
β
|
β |
β |
β
|
3 |
| On the Paradox of Certified Training |
β |
β |
β
|
β
|
β
|
β |
β
|
4 |
| On the link between conscious function and general intelligence in humans and machines |
β |
β |
β |
β |
β |
β |
β |
0 |
| Online Coresets for Parameteric and Non-Parametric Bregman Clustering |
β
|
β |
β
|
β |
β |
β |
β
|
3 |
| Online Double Oracle |
β
|
β
|
β
|
β |
β |
β |
β
|
4 |
| Optimal Client Sampling for Federated Learning |
β
|
β
|
β
|
β |
β |
β |
β
|
4 |
| Optimizing Functionals on the Space of Probabilities with Input Convex Neural Networks |
β
|
β |
β
|
β
|
β
|
β |
β
|
5 |
| Optimizing Intermediate Representations of Generative Models for Phase Retrieval |
β |
β |
β
|
β
|
β
|
β |
β
|
4 |
| Practicality of generalization guarantees for unsupervised domain adaptation with neural networks |
β |
β |
β
|
β
|
β |
β |
β
|
3 |
| Probabilistic Autoencoder |
β |
β
|
β
|
β
|
β |
β |
β
|
4 |
| QuaRL: Quantization for Fast and Environmentally Sustainable Reinforcement Learning |
β |
β
|
β
|
β |
β
|
β |
β
|
4 |
| Queried Unlabeled Data Improves and Robustifies Class-Incremental Learning |
β
|
β
|
β
|
β
|
β |
β |
β
|
5 |
| Ranking Recovery under Privacy Considerations |
β |
β |
β |
β |
β |
β |
β
|
1 |
| Reasonable Effectiveness of Random Weighting: A Litmus Test for Multi-Task Learning |
β
|
β
|
β
|
β
|
β
|
β |
β
|
6 |
| Recurrent networks, hidden states and beliefs in partially observable environments |
β
|
β |
β
|
β |
β |
β |
β
|
3 |
| Reinventing Policy Iteration under Time Inconsistency |
β
|
β |
β |
β |
β |
β |
β
|
2 |
| Representation Alignment in Neural Networks |
β |
β
|
β
|
β
|
β
|
β |
β
|
5 |
| Robust and Data-efficient Q-learning by Composite Value-estimation |
β
|
β
|
β
|
β |
β |
β |
β
|
4 |
| SFP: State-free Priors for Exploration in Off-Policy Reinforcement Learning |
β
|
β
|
β
|
β
|
β |
β |
β
|
5 |
| Scaling Autoregressive Models for Content-Rich Text-to-Image Generation |
β |
β |
β
|
β
|
β
|
β |
β
|
4 |
| Secure Domain Adaptation with Multiple Sources |
β
|
β
|
β
|
β |
β
|
β |
β
|
5 |
| Self-supervise, Refine, Repeat: Improving Unsupervised Anomaly Detection |
β
|
β |
β
|
β
|
β
|
β |
β
|
5 |
| SemiNLL: A Framework of Noisy-Label Learning by Semi-Supervised Learning |
β
|
β |
β
|
β
|
β
|
β |
β
|
5 |
| Sequentially learning the topological ordering of directed acyclic graphs with likelihood ratio scores |
β
|
β
|
β
|
β
|
β
|
β |
β
|
6 |
| Simplifying Node Classification on Heterophilous Graphs with Compatible Label Propagation |
β |
β
|
β
|
β
|
β |
β |
β |
3 |
| Sparse Coding with Multi-layer Decoders using Variance Regularization |
β
|
β
|
β
|
β
|
β
|
β |
β
|
6 |
| Sparse MoEs meet Efficient Ensembles |
β |
β
|
β
|
β
|
β |
β |
β
|
4 |
| Stable and Interpretable Unrolled Dictionary Learning |
β
|
β
|
β
|
β
|
β
|
β
|
β
|
7 |
| Stochastic Douglas-Rachford Splitting for Regularized Empirical Risk Minimization: Convergence, Mini-batch, and Implementation |
β
|
β |
β
|
β
|
β |
β |
β
|
4 |
| Structural Learning in Artificial Neural Networks: A Neural Operator Perspective |
β |
β |
β |
β |
β |
β |
β |
0 |
| Structured Uncertainty in the Observation Space of Variational Autoencoders |
β |
β
|
β
|
β |
β
|
β |
β
|
4 |
| Symbolic Regression is NP-hard |
β |
β |
β |
β |
β |
β |
β |
0 |
| Systematically and efficiently improving $k$-means initialization by pairwise-nearest-neighbor smoothing |
β
|
β
|
β
|
β |
β
|
β
|
β
|
6 |
| TITRATED: Learned Human Driving Behavior without Infractions via Amortized Inference |
β
|
β |
β
|
β
|
β
|
β |
β
|
5 |
| TLDR: Twin Learning for Dimensionality Reduction |
β
|
β
|
β
|
β
|
β
|
β |
β
|
6 |
| Teacherβs pet: understanding and mitigating biases in distillation |
β |
β |
β
|
β
|
β |
β |
β
|
3 |
| Teaching Models to Express Their Uncertainty in Words |
β |
β |
β |
β
|
β |
β |
β
|
2 |
| The Evolution of Out-of-Distribution Robustness Throughout Fine-Tuning |
β |
β |
β
|
β
|
β |
β
|
β
|
4 |
| The Fundamental Limits of Neural Networks for Interval Certified Robustness |
β |
β |
β |
β |
β |
β |
β |
0 |
| The Graph Cut Kernel for Ranked Data |
β
|
β
|
β
|
β
|
β
|
β |
β
|
6 |
| Time Series Alignment with Global Invariances |
β
|
β |
β
|
β
|
β |
β |
β
|
4 |
| Towards Accurate Subgraph Similarity Computation via Neural Graph Pruning |
β
|
β
|
β
|
β
|
β |
β |
β
|
5 |
| Uncertainty-Based Active Learning for Reading Comprehension |
β
|
β |
β
|
β
|
β |
β |
β
|
4 |
| Understanding AdamW through Proximal Methods and Scale-Freeness |
β
|
β |
β
|
β |
β |
β |
β
|
3 |
| Understanding Linearity of Cross-Lingual Word Embedding Mappings |
β
|
β
|
β
|
β |
β |
β |
β
|
4 |
| Unifying Approaches in Active Learning and Active Sampling via Fisher Information and Information-Theoretic Quantities |
β |
β
|
β
|
β
|
β |
β
|
β
|
5 |
| Unimodal Likelihood Models for Ordinal Data |
β |
β
|
β
|
β
|
β |
β |
β
|
4 |
| Unsupervised Dense Information Retrieval with Contrastive Learning |
β |
β
|
β
|
β
|
β |
β |
β
|
4 |
| Unsupervised Learning of Neurosymbolic Encoders |
β
|
β
|
β
|
β
|
β
|
β |
β
|
6 |
| Unsupervised Mismatch Localization in Cross-Modal Sequential Data with Application to Mispronunciations Localization |
β
|
β |
β
|
β
|
β |
β |
β
|
4 |
| Unsupervised Network Embedding Beyond Homophily |
β
|
β
|
β
|
β |
β |
β |
β |
3 |
| Using unsupervised learning to detect broken symmetries, with relevance to searches for parity violation in nature. |
β |
β
|
β
|
β |
β |
β |
β
|
3 |
| Variational Disentanglement for Domain Generalization |
β
|
β |
β
|
β
|
β
|
β
|
β
|
6 |
| Weight Expansion: A New Perspective on Dropout and Generalization |
β
|
β |
β
|
β
|
β |
β |
β
|
4 |
| Your Policy Regularizer is Secretly an Adversary |
β |
β |
β |
β |
β |
β |
β
|
1 |
| ZerO Initialization: Initializing Neural Networks with only Zeros and Ones |
β
|
β
|
β
|
β
|
β |
β |
β
|
5 |
| Zero-Shot Learning with Common Sense Knowledge Graphs |
β
|
β
|
β
|
β
|
β
|
β |
β
|
6 |
| sigmoidF1: A Smooth F1 Score Surrogate Loss for Multilabel Classification |
β
|
β
|
β
|
β
|
β
|
β |
β
|
6 |