{"total":59,"rows":[{"id":"2110.06848","title":"Decoupled Contrastive Learning","created":"2021-10-13","cited_by_count":143,"area":null},{"id":"2204.01696","title":"Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos","created":"2022-04-04","cited_by_count":111,"area":null},{"id":"2310.08887","title":"METRA: Scalable Unsupervised RL with Metric-Aware Abstraction","created":"2023-10-13","cited_by_count":86,"area":null},{"id":"2306.05268","title":"Factorized Contrastive Learning: Going Beyond Multi-view Redundancy","created":"2023-06-08","cited_by_count":75,"area":null},{"id":"2201.04309","title":"Robust Contrastive Learning against Noisy Views","created":"2022-01-12","cited_by_count":45,"area":null},{"id":"2310.08303","title":"Multimodal Variational Auto-encoder based Audio-Visual Segmentation","created":"2023-10-12","cited_by_count":38,"area":null},{"id":"2101.02055","title":"Geometric Entropic Exploration","created":"2021-01-06","cited_by_count":32,"area":null},{"id":"2103.11275","title":"Self-supervised Representation Learning with Relative Predictive Coding","created":"2021-03-21","cited_by_count":28,"area":null},{"id":"2104.13712","title":"A Note on Connecting Barlow Twins with Negative-Sample-Free Contrastive Learning","created":"2021-04-28","cited_by_count":26,"area":null},{"id":"2106.02866","title":"Conditional Contrastive Learning for Improving Fairness in Self-Supervised Learning","created":"2021-06-05","cited_by_count":25,"area":null},{"id":"2101.07496","title":"Disentangled Recurrent Wasserstein Autoencoder","created":"2021-01-19","cited_by_count":22,"area":null},{"id":"2107.01152","title":"Simpler, Faster, Stronger: Breaking The log-K Curse On Contrastive Learners With FlatNCE","created":"2021-07-02","cited_by_count":22,"area":null},{"id":"2110.07940","title":"Wasserstein Unsupervised Reinforcement Learning","created":"2021-10-15","cited_by_count":22,"area":null},{"id":"2305.00869","title":"Estimating the Density Ratio between Distributions with High Discrepancy using Multinomial Logistic Regression","created":"2023-05-01","cited_by_count":17,"area":null},{"id":"2406.06615","title":"Language Guided Skill Discovery","created":"2024-06-07","cited_by_count":16,"area":null},{"id":"2109.00922","title":"Improving Multimodal fusion via Mutual Dependency Maximisation","created":"2021-08-31","cited_by_count":15,"area":null},{"id":"2311.01066","title":"Dynamic Multimodal Information Bottleneck for Multimodality Classification","created":"2023-11-02","cited_by_count":14,"area":null},{"id":"2402.10150","title":"$f$-MICL: Understanding and Generalizing InfoNCE-based Contrastive Learning","created":"2024-02-15","cited_by_count":13,"area":null},{"id":"2206.10698","title":"TiCo: Transformation Invariance and Covariance Contrast for Self-Supervised Visual Representation Learning","created":"2022-06-21","cited_by_count":12,"area":null},{"id":"2211.10370","title":"Invariant Learning via Diffusion Dreamed Distribution Shifts","created":"2022-11-18","cited_by_count":10,"area":null},{"id":"2112.15265","title":"Entropy Regularized Optimal Transport Independence Criterion","created":"2021-12-31","cited_by_count":9,"area":null},{"id":"2202.07260","title":"Learning Disentangled Behaviour Patterns for Wearable-based Human Activity Recognition","created":"2022-02-15","cited_by_count":9,"area":null},{"id":"2210.03164","title":"InfoOT: Information Maximizing Optimal Transport","created":"2022-10-06","cited_by_count":9,"area":null},{"id":"2112.14754","title":"Disentanglement and Generalization Under Correlation Shifts","created":"2021-12-29","cited_by_count":8,"area":null},{"id":"2208.06270","title":"RenyiCL: Contrastive Representation Learning with Skew Renyi Divergence","created":"2022-08-12","cited_by_count":8,"area":null},{"id":"2406.00324","title":"Do's and Don'ts: Learning Desirable Skills with Instruction Videos","created":"2024-06-01","cited_by_count":8,"area":null},{"id":"2106.02869","title":"Integrating Auxiliary Information in Self-supervised Learning","created":"2021-06-05","cited_by_count":6,"area":null},{"id":"2202.06670","title":"Learning Weakly-Supervised Contrastive Representations","created":"2022-02-14","cited_by_count":6,"area":null},{"id":"2502.20141","title":"Your contrastive learning problem is secretly a distribution alignment problem","created":"2025-02-27","cited_by_count":6,"area":null},{"id":"2508.08982","title":"Unsupervised Skill Discovery as Exploration for Learning Agile Locomotion","created":"2025-08-12","cited_by_count":6,"area":null},{"id":"2102.13416","title":"Moreau-Yosida $f$-divergences","created":"2021-02-26","cited_by_count":5,"area":null},{"id":"2603.09036","title":"SCALAR: Learning and Composing Skills through LLM Guided Symbolic Planning and Deep RL Grounding","created":"2026-03-10","cited_by_count":5,"area":null},{"id":"2301.12038","title":"STEERING: Stein Information Directed Exploration for Model-Based Reinforcement Learning","created":"2023-01-28","cited_by_count":4,"area":null},{"id":"2311.12689","title":"Fair Text Classification with Wasserstein Independence","created":"2023-11-21","cited_by_count":4,"area":null},{"id":"2405.15505","title":"Revisiting Counterfactual Regression through the Lens of Gromov-Wasserstein Information Bottleneck","created":"2024-05-24","cited_by_count":4,"area":null},{"id":"2109.15030","title":"On the Convergence of Projected Alternating Maximization for Equitable and Optimal Transport","created":"2021-09-29","cited_by_count":3,"area":null},{"id":"2110.00385","title":"Neural Dependency Coding inspired Multimodal Fusion","created":"2021-09-28","cited_by_count":3,"area":null},{"id":"2111.02947","title":"Variational Inference with Holder Bounds","created":"2021-11-04","cited_by_count":3,"area":null},{"id":"2210.16645","title":"Solving a Special Type of Optimal Transport Problem by a Modified Hungarian Algorithm","created":"2022-10-29","cited_by_count":3,"area":null},{"id":"2301.12197","title":"Mutual Wasserstein Discrepancy Minimization for Sequential Recommendation","created":"2023-01-28","cited_by_count":3,"area":null},{"id":"2304.03486","title":"Can we learn better with hard samples?","created":"2023-04-07","cited_by_count":3,"area":null},{"id":"2402.03456","title":"Constrained Multiview Representation for Self-supervised Contrastive Learning","created":"2024-02-05","cited_by_count":3,"area":null},{"id":"2503.07691","title":"Fair Text Classification via Transferable Representations","created":"2025-03-10","cited_by_count":3,"area":null},{"id":"2510.14848","title":"A Geometric Approach to Optimal Experimental Design","created":"2025-10-16","cited_by_count":3,"area":null},{"id":"2210.04076","title":"Robustness of Unsupervised Representation Learning without Labels","created":"2022-10-08","cited_by_count":2,"area":null},{"id":"2312.13985","title":"R\\'enyi Pufferfish Privacy: General Additive Noise Mechanisms and Privacy Amplification by Iteration","created":"2023-12-21","cited_by_count":2,"area":null},{"id":"2510.06203","title":"Reference Grounded Skill Discovery","created":"2025-10-07","cited_by_count":2,"area":null},{"id":"2207.09783","title":"Cancer Subtyping by Improved Transcriptomic Features Using Vector Quantized Variational Autoencoder","created":"2022-07-20","cited_by_count":1,"area":null},{"id":"2310.02925","title":"Optimal Transport with Adaptive Regularisation","created":"2023-10-04","cited_by_count":1,"area":null},{"id":"2504.18897","title":"ReLU integral probability metric and its applications","created":"2025-04-26","cited_by_count":1,"area":null},{"id":"2509.13846","title":"Consistent View Alignment Improves Foundation Models for 3D Medical Image Segmentation","created":"2025-09-17","cited_by_count":1,"area":null},{"id":"2201.13127","title":"Unified Perspective on Probability Divergence via Maximum Likelihood Density Ratio Estimation: Bridging KL-Divergence and Integral Probability Metrics","created":"2022-01-31","cited_by_count":0,"area":null},{"id":"2308.00989","title":"Wasserstein Diversity-Enriched Regularizer for Hierarchical Reinforcement Learning","created":"2023-08-02","cited_by_count":0,"area":null},{"id":"2310.08762","title":"Stabilizing Subject Transfer in EEG Classification with Divergence Estimation","created":"2023-10-12","cited_by_count":0,"area":null},{"id":"2511.12180","title":"Understanding InfoNCE: Transition Probability Matrix Induced Feature Clustering","created":"2025-11-15","cited_by_count":0,"area":null},{"id":"2511.12881","title":"On the Information Processing of One-Dimensional Wasserstein Distances with Finite Samples","created":"2025-11-17","cited_by_count":0,"area":null},{"id":"2601.04193","title":"A discrete Benamou-Brenier formulation of Optimal Transport on graphs","created":"2026-01-07","cited_by_count":0,"area":null},{"id":"2601.14000","title":"Group-Invariant Unsupervised Skill Discovery: Symmetry-aware Skill Representations for Generalizable Behavior","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2609.13966","title":"SGWIB:Sliced Gromov-Wasserstein Information Bottleneck for Video Highlight Detection","created":"2026-09-12","cited_by_count":0,"area":null}],"next_cursor":null}