{"total":69,"rows":[{"id":"2306.01129","title":"White-Box Transformers via Sparse Rate Reduction","created":"2023-06-01","cited_by_count":80,"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":"2304.09355","title":"To Compress or Not to Compress- Self-Supervised Learning and Information Theory: A Review","created":"2023-04-19","cited_by_count":72,"area":null},{"id":"2304.05215","title":"A Billion-scale Foundation Model for Remote Sensing Images","created":"2023-04-11","cited_by_count":62,"area":null},{"id":"2409.07402","title":"What to align in multimodal contrastive learning?","created":"2024-09-11","cited_by_count":47,"area":null},{"id":"2303.05251","title":"Masked Image Modeling with Local Multi-Scale Reconstruction","created":"2023-03-09","cited_by_count":43,"area":null},{"id":"2303.00633","title":"An Information-Theoretic Perspective on Variance-Invariance-Covariance Regularization","created":"2023-03-01","cited_by_count":25,"area":null},{"id":"2308.11164","title":"Decoupled Contrastive Multi-View Clustering with High-Order Random Walks","created":"2023-08-22","cited_by_count":23,"area":null},{"id":"2412.11863","title":"GeoX: Geometric Problem Solving Through Unified Formalized Vision-Language Pre-training","created":"2024-12-16","cited_by_count":23,"area":"mllm"},{"id":"2305.04691","title":"Self-supervised Learning for Pre-Training 3D Point Clouds: A Survey","created":"2023-05-08","cited_by_count":21,"area":null},{"id":"2307.09023","title":"LA-Net: Landmark-Aware Learning for Reliable Facial Expression Recognition under Label Noise","created":"2023-07-18","cited_by_count":17,"area":null},{"id":"2206.04028","title":"CO^3: Cooperative Unsupervised 3D Representation Learning for Autonomous Driving","created":"2022-06-08","cited_by_count":15,"area":null},{"id":"2409.10473","title":"MacDiff: Unified Skeleton Modeling with Masked Conditional Diffusion","created":"2024-09-16","cited_by_count":15,"area":"diffusion"},{"id":"2308.01578","title":"Unsupervised Representation Learning for Time Series: A Review","created":"2023-08-03","cited_by_count":14,"area":null},{"id":"2402.17510","title":"Demonstrating and Reducing Shortcuts in Vision-Language Representation Learning","created":"2024-02-27","cited_by_count":14,"area":"mllm"},{"id":"2212.13835","title":"Representation Learning in Deep RL via Discrete Information Bottleneck","created":"2022-12-28","cited_by_count":13,"area":null},{"id":"2302.03357","title":"Towards Enhancing Time Series Contrastive Learning: A Dynamic Bad Pair Mining Approach","created":"2023-02-07","cited_by_count":13,"area":null},{"id":"2506.04870","title":"Aligning Multimodal Representations through an Information Bottleneck","created":"2025-06-05","cited_by_count":13,"area":null},{"id":"2205.12239","title":"Gacs-Korner Common Information Variational Autoencoder","created":"2022-05-24","cited_by_count":12,"area":null},{"id":"2305.12743","title":"Semantic Invariant Multi-view Clustering with Fully Incomplete Information","created":"2023-05-22","cited_by_count":12,"area":null},{"id":"2409.17386","title":"Beyond Redundancy: Information-aware Unsupervised Multiplex Graph Structure Learning","created":"2024-09-25","cited_by_count":12,"area":null},{"id":"2210.00132","title":"Alignment-guided Temporal Attention for Video Action Recognition","created":"2022-09-30","cited_by_count":10,"area":null},{"id":"2309.00885","title":"A Generic Fundus Image Enhancement Network Boosted by Frequency Self-supervised Representation Learning","created":"2023-09-02","cited_by_count":10,"area":null},{"id":"2410.22217","title":"Towards Unifying Understanding and Generation in the Era of Vision Foundation Models: A Survey from the Autoregression Perspective","created":"2024-10-29","cited_by_count":10,"area":null},{"id":"2310.17764","title":"SynergyNet: Bridging the Gap between Discrete and Continuous Representations for Precise Medical Image Segmentation","created":"2023-10-26","cited_by_count":9,"area":null},{"id":"2403.05490","title":"Poly-View Contrastive Learning","created":"2024-03-08","cited_by_count":9,"area":null},{"id":"2301.02780","title":"Rethinking Explaining Graph Neural Networks via Non-parametric Subgraph Matching","created":"2023-01-07","cited_by_count":8,"area":null},{"id":"2312.02151","title":"Guarding Barlow Twins Against Overfitting with Mixed Samples","created":"2023-12-04","cited_by_count":8,"area":null},{"id":"2312.10680","title":"DomainForensics: Exposing Face Forgery across Domains via Bi-directional Adaptation","created":"2023-12-17","cited_by_count":8,"area":null},{"id":"2209.06954","title":"Correlation Information Bottleneck: Towards Adapting Pretrained Multimodal Models for Robust Visual Question Answering","created":"2022-09-14","cited_by_count":7,"area":"mllm"},{"id":"2509.25270","title":"InfMasking: Unleashing Synergistic Information by Contrastive Multimodal Interactions","created":"2025-09-28","cited_by_count":7,"area":null},{"id":"2407.08448","title":"Paving the way toward foundation models for irregular and unaligned Satellite Image Time Series","created":"2024-07-11","cited_by_count":6,"area":null},{"id":"2303.01239","title":"MixPHM: Redundancy-Aware Parameter-Efficient Tuning for Low-Resource Visual Question Answering","created":"2023-03-02","cited_by_count":5,"area":"mllm"},{"id":"2305.12959","title":"Contrastive Predictive Autoencoders for Dynamic Point Cloud Self-Supervised Learning","created":"2023-05-22","cited_by_count":5,"area":null},{"id":"2307.01053","title":"ENGAGE: Explanation Guided Data Augmentation for Graph Representation Learning","created":"2023-07-03","cited_by_count":5,"area":null},{"id":"2308.01606","title":"Unsupervised Multiplex Graph Learning with Complementary and Consistent Information","created":"2023-08-03","cited_by_count":5,"area":null},{"id":"2309.10527","title":"SPOT: Scalable 3D Pre-training via Occupancy Prediction for Learning Transferable 3D Representations","created":"2023-09-19","cited_by_count":5,"area":null},{"id":"2403.15516","title":"CTSM: Combining Trait and State Emotions for Empathetic Response Model","created":"2024-03-22","cited_by_count":5,"area":null},{"id":"2410.02086","title":"Anchors Aweigh! Sail for Optimal Unified Multi-Modal Representations","created":"2024-10-02","cited_by_count":5,"area":null},{"id":"2506.07413","title":"Variational Supervised Contrastive Learning","created":"2025-06-09","cited_by_count":5,"area":null},{"id":"2403.19078","title":"MVEB: Self-Supervised Learning with Multi-View Entropy Bottleneck","created":"2024-03-28","cited_by_count":4,"area":null},{"id":"2510.13025","title":"Information Shapes Koopman Representation","created":"2025-10-14","cited_by_count":4,"area":null},{"id":"2303.15467","title":"Enlarging Instance-specific and Class-specific Information for Open-set Action Recognition","created":"2023-03-25","cited_by_count":3,"area":null},{"id":"2306.11526","title":"Understanding Contrastive Learning Through the Lens of Margins","created":"2023-06-20","cited_by_count":3,"area":null},{"id":"2307.03856","title":"Novel Categories Discovery Via Constraints on Empirical Prediction Statistics","created":"2023-07-07","cited_by_count":3,"area":null},{"id":"2310.03977","title":"Perfect Alignment May be Poisonous to Graph Contrastive Learning","created":"2023-10-06","cited_by_count":3,"area":null},{"id":"2408.10292","title":"Leveraging Superfluous Information in Contrastive Representation Learning","created":"2024-08-19","cited_by_count":3,"area":null},{"id":"2211.09013","title":"Masked Reconstruction Contrastive Learning with Information Bottleneck Principle","created":"2022-11-15","cited_by_count":2,"area":null},{"id":"2305.02324","title":"Cross-Stream Contrastive Learning for Self-Supervised Skeleton-Based Action Recognition","created":"2023-05-03","cited_by_count":2,"area":null},{"id":"2308.15704","title":"Towards a Rigorous Analysis of Mutual Information in Contrastive Learning","created":"2023-08-30","cited_by_count":2,"area":null},{"id":"2403.18699","title":"Preventing Collapse in Contrastive Learning with Orthonormal Prototypes (CLOP)","created":"2024-03-27","cited_by_count":2,"area":null},{"id":"2412.03054","title":"TREND: Unsupervised 3D Representation Learning via Temporal Forecasting for LiDAR Perception","created":"2024-12-04","cited_by_count":2,"area":null},{"id":"2509.01119","title":"SC-GIR: Goal-oriented Semantic Communication via Invariant Representation Learning","created":"2025-09-01","cited_by_count":2,"area":null},{"id":"2309.16564","title":"Augment to Interpret: Unsupervised and Inherently Interpretable Graph Embeddings","created":"2023-09-28","cited_by_count":1,"area":null},{"id":"2311.11821","title":"Cross-View Graph Consistency Learning for Invariant Graph Representations","created":"2023-11-20","cited_by_count":1,"area":null},{"id":"2501.06524","title":"Multi-View Factorizing and Disentangling: A Novel Framework for Incomplete Multi-View Multi-Label Classification","created":"2025-01-11","cited_by_count":1,"area":null},{"id":"2507.10215","title":"A Graph Sufficiency Perspective for Neural Networks","created":"2025-07-14","cited_by_count":1,"area":null},{"id":"2509.15791","title":"Minimal Semantic Sufficiency Meets Unsupervised Domain Generalization","created":"2025-09-19","cited_by_count":1,"area":null},{"id":"2510.12070","title":"MEASURE: Multi-scale Minimal Sufficient Representation Learning for Domain Generalization in Sleep Staging","created":"2025-10-14","cited_by_count":1,"area":null},{"id":"2510.21686","title":"Multimodal Datasets with Controllable Mutual Information","created":"2025-10-24","cited_by_count":1,"area":null},{"id":"2309.07616","title":"Road Disease Detection based on Latent Domain Background Feature Separation and Suppression","created":"2023-09-14","cited_by_count":0,"area":null},{"id":"2310.18080","title":"Unveiling the Potential of Probabilistic Embeddings in Self-Supervised Learning","created":"2023-10-27","cited_by_count":0,"area":null},{"id":"2405.07306","title":"Point Resampling and Ray Transformation Aid to Editable NeRF Models","created":"2024-05-12","cited_by_count":0,"area":null},{"id":"2503.07444","title":"Divide and Conquer Self-Supervised Learning for High-Content Imaging","created":"2025-03-10","cited_by_count":0,"area":null},{"id":"2512.07880","title":"Semi-Supervised Contrastive Learning with Orthonormal Prototypes","created":"2025-11-27","cited_by_count":0,"area":null},{"id":"2601.04563","title":"A Vision for Multisensory Intelligence: Sensing, Science, and Synergy","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2608.17203","title":"Expressivity In Multimodal Contrastive Learning","created":"2026-08-17","cited_by_count":0,"area":"mllm"},{"id":"2610.07906","title":"Isotropic Yet Undecodable: The Sequential Content-Sufficiency Gap in Latent-Predictive Text Representations","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.18375","title":"Beyond Task Success: A Theory of Representation Reuse","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}