{"total":142,"rows":[{"id":"2105.02375","title":"A Geometric Analysis of Neural Collapse with Unconstrained Features","created":"2021-05-06","cited_by_count":227,"area":null},{"id":"2212.08420","title":"Fake it till you make it: Learning transferable representations from synthetic ImageNet clones","created":"2022-12-16","cited_by_count":172,"area":"diffusion"},{"id":"2101.12699","title":"Exploring Deep Neural Networks via Layer-Peeled Model: Minority Collapse in Imbalanced Training","created":"2021-01-29","cited_by_count":166,"area":null},{"id":"2206.04041","title":"Neural Collapse: A Review on Modelling Principles and Generalization","created":"2022-06-08","cited_by_count":95,"area":null},{"id":"2202.14026","title":"Robust Training under Label Noise by Over-parameterization","created":"2022-02-28","cited_by_count":93,"area":null},{"id":"2306.01129","title":"White-Box Transformers via Sparse Rate Reduction","created":"2023-06-01","cited_by_count":80,"area":null},{"id":"2210.02192","title":"Are All Losses Created Equal: A Neural Collapse Perspective","created":"2022-10-04","cited_by_count":78,"area":null},{"id":"2310.07931","title":"D2 Pruning: Message Passing for Balancing Diversity and Difficulty in Data Pruning","created":"2023-10-11","cited_by_count":69,"area":null},{"id":"2207.04630","title":"On the Principles of Parsimony and Self-Consistency for the Emergence of Intelligence","created":"2022-07-11","cited_by_count":50,"area":"lr"},{"id":"2209.09211","title":"Neural Collapse with Normalized Features: A Geometric Analysis over the Riemannian Manifold","created":"2022-09-19","cited_by_count":50,"area":null},{"id":"2403.08946","title":"Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era","created":"2024-03-13","cited_by_count":46,"area":null},{"id":"2106.09362","title":"Frustratingly Easy Transferability Estimation","created":"2021-06-17","cited_by_count":45,"area":null},{"id":"2201.10000","title":"Neural Manifold Clustering and Embedding","created":"2022-01-24","cited_by_count":44,"area":null},{"id":"2310.05351","title":"Generalized Neural Collapse for a Large Number of Classes","created":"2023-10-09","cited_by_count":39,"area":null},{"id":"2210.11464","title":"Self-Supervised Learning via Maximum Entropy Coding","created":"2022-10-20","cited_by_count":33,"area":null},{"id":"2303.03307","title":"Learning Efficient Coding of Natural Images with Maximum Manifold Capacity Representations","created":"2023-03-06","cited_by_count":31,"area":null},{"id":"2510.17314","title":"Auto-Rubric: Learning From Implicit Weights to Explicit Rubrics for Reward Modeling","created":"2025-10-20","cited_by_count":30,"area":"alignment"},{"id":"2407.03575","title":"DGR-MIL: Exploring Diverse Global Representation in Multiple Instance Learning for Whole Slide Image Classification","created":"2024-07-04","cited_by_count":25,"area":null},{"id":"2110.04318","title":"Learning a Self-Expressive Network for Subspace Clustering","created":"2021-10-08","cited_by_count":24,"area":null},{"id":"2308.16271","title":"Emergence of Segmentation with Minimalistic White-Box Transformers","created":"2023-08-30","cited_by_count":24,"area":null},{"id":"2107.11635","title":"Clustering by Maximizing Mutual Information Across Views","created":"2021-07-24","cited_by_count":23,"area":null},{"id":"2206.15369","title":"No Reason for No Supervision: Improved Generalization in Supervised Models","created":"2022-06-30","cited_by_count":23,"area":null},{"id":"2306.05272","title":"Image Clustering via the Principle of Rate Reduction in the Age of Pretrained Models","created":"2023-06-08","cited_by_count":22,"area":null},{"id":"2502.10385","title":"Simplifying DINO via Coding Rate Regularization","created":"2025-02-14","cited_by_count":21,"area":null},{"id":"2306.00788","title":"Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression","created":"2023-06-01","cited_by_count":20,"area":null},{"id":"2205.04114","title":"Localized Adversarial Domain Generalization","created":"2022-05-09","cited_by_count":19,"area":null},{"id":"2304.03977","title":"EMP-SSL: Towards Self-Supervised Learning in One Training Epoch","created":"2023-04-08","cited_by_count":19,"area":null},{"id":"2306.04785","title":"Interpretable Deep Clustering for Tabular Data","created":"2023-06-07","cited_by_count":19,"area":null},{"id":"2303.08207","title":"Is forgetting less a good inductive bias for forward transfer?","created":"2023-03-14","cited_by_count":18,"area":null},{"id":"2308.02346","title":"Class Incremental Learning with Self-Supervised Pre-Training and Prototype Learning","created":"2023-08-04","cited_by_count":18,"area":null},{"id":"2111.06636","title":"Closed-Loop Data Transcription to an LDR via Minimaxing Rate Reduction","created":"2021-11-12","cited_by_count":17,"area":null},{"id":"2202.05411","title":"Incremental Learning of Structured Memory via Closed-Loop Transcription","created":"2022-02-11","cited_by_count":17,"area":null},{"id":"2405.21074","title":"Latent Intrinsics Emerge from Training to Relight","created":"2024-05-31","cited_by_count":17,"area":null},{"id":"2111.13336","title":"MAE-DET: Revisiting Maximum Entropy Principle in Zero-Shot NAS for Efficient Object Detection","created":"2021-11-26","cited_by_count":16,"area":null},{"id":"2309.17281","title":"Information Flow in Self-Supervised Learning","created":"2023-09-29","cited_by_count":16,"area":null},{"id":"2202.00035","title":"Learning Fair Representations via Rate-Distortion Maximization","created":"2022-01-31","cited_by_count":15,"area":null},{"id":"2506.01701","title":"Data Pruning by Information Maximization","created":"2025-06-02","cited_by_count":15,"area":null},{"id":"2112.03657","title":"Understanding Square Loss in Training Overparametrized Neural Network Classifiers","created":"2021-12-07","cited_by_count":14,"area":null},{"id":"2303.02165","title":"DeepMAD: Mathematical Architecture Design for Deep Convolutional Neural Network","created":"2023-03-05","cited_by_count":14,"area":null},{"id":"2310.15903","title":"Neural Collapse in Multi-label Learning with Pick-all-label Loss","created":"2023-10-24","cited_by_count":14,"area":null},{"id":"2411.01248","title":"Guiding Neural Collapse: Optimising Towards the Nearest Simplex Equiangular Tight Frame","created":"2024-11-02","cited_by_count":14,"area":null},{"id":"2307.07942","title":"KECOR: Kernel Coding Rate Maximization for Active 3D Object Detection","created":"2023-07-16","cited_by_count":13,"area":null},{"id":"2406.01909","title":"A Global Geometric Analysis of Maximal Coding Rate Reduction","created":"2024-06-04","cited_by_count":13,"area":null},{"id":"2301.01805","title":"Unsupervised Manifold Linearizing and Clustering","created":"2023-01-04","cited_by_count":12,"area":null},{"id":"2303.09165","title":"A New Benchmark: On the Utility of Synthetic Data with Blender for Bare Supervised Learning and Downstream Domain Adaptation","created":"2023-03-16","cited_by_count":11,"area":null},{"id":"2305.01777","title":"Representation Learning via Manifold Flattening and Reconstruction","created":"2023-05-02","cited_by_count":11,"area":null},{"id":"2312.00194","title":"Robust Concept Erasure via Kernelized Rate-Distortion Maximization","created":"2023-11-30","cited_by_count":11,"area":null},{"id":"2312.08852","title":"ERASE: Error-Resilient Representation Learning on Graphs for Label Noise Tolerance","created":"2023-12-13","cited_by_count":11,"area":null},{"id":"2105.03705","title":"Understanding Neural Networks with Logarithm Determinant Entropy Estimator","created":"2021-05-08","cited_by_count":10,"area":null},{"id":"2305.13764","title":"Mitigating Label Noise through Data Ambiguation","created":"2023-05-23","cited_by_count":10,"area":null},{"id":"2602.01456","title":"Rectified LpJEPA: Joint-Embedding Predictive Architectures with Sparse and Maximum-Entropy Representations","created":"2026-02-01","cited_by_count":10,"area":null},{"id":"2202.06241","title":"Geometric Graph Representation Learning via Maximizing Rate Reduction","created":"2022-02-13","cited_by_count":9,"area":null},{"id":"2305.12715","title":"Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations","created":"2023-05-22","cited_by_count":9,"area":null},{"id":"2402.05970","title":"Modeling Spatio-temporal Dynamical Systems with Neural Discrete Learning and Levels-of-Experts","created":"2024-02-06","cited_by_count":9,"area":null},{"id":"2404.02446","title":"Masked Completion via Structured Diffusion with White-Box Transformers","created":"2024-04-03","cited_by_count":9,"area":null},{"id":"2203.15361","title":"Self-Supervised Image Representation Learning with Geometric Set Consistency","created":"2022-03-29","cited_by_count":7,"area":null},{"id":"2209.07902","title":"MetaMask: Revisiting Dimensional Confounder for Self-Supervised Learning","created":"2022-09-16","cited_by_count":7,"area":null},{"id":"2210.16782","title":"Unsupervised Learning of Structured Representations via Closed-Loop Transcription","created":"2022-10-30","cited_by_count":7,"area":null},{"id":"2307.04047","title":"Threshold-Consistent Margin Loss for Open-World Deep Metric Learning","created":"2023-07-08","cited_by_count":7,"area":null},{"id":"2309.08971","title":"Regularized Contrastive Pre-training for Few-shot Bioacoustic Sound Detection","created":"2023-09-16","cited_by_count":7,"area":null},{"id":"2410.20349","title":"Idempotent Unsupervised Representation Learning for Skeleton-Based Action Recognition","created":"2024-10-27","cited_by_count":7,"area":null},{"id":"2503.17288","title":"Exploring a Principled Framework for Deep Subspace Clustering","created":"2025-03-21","cited_by_count":7,"area":null},{"id":"2204.00077","title":"Efficient Maximal Coding Rate Reduction by Variational Forms","created":"2022-03-31","cited_by_count":6,"area":null},{"id":"2505.17322","title":"From Compression to Expression: A Layerwise Analysis of In-Context Learning","created":"2025-05-22","cited_by_count":6,"area":"offlinerl"},{"id":"2103.00381","title":"Adversarial Information Bottleneck","created":"2021-02-28","cited_by_count":5,"area":null},{"id":"2208.12212","title":"Sustaining Fairness via Incremental Learning","created":"2022-08-25","cited_by_count":5,"area":null},{"id":"2302.11984","title":"Unsupervised Domain Adaptation via Distilled Discriminative Clustering","created":"2023-02-23","cited_by_count":5,"area":null},{"id":"2303.02693","title":"Maximizing Spatio-Temporal Entropy of Deep 3D CNNs for Efficient Video Recognition","created":"2023-03-05","cited_by_count":5,"area":null},{"id":"2510.17299","title":"Exploring Structural Degradation in Dense Representations for Self-supervised Learning","created":"2025-10-20","cited_by_count":5,"area":null},{"id":"2104.04665","title":"On Universal Black-Box Domain Adaptation","created":"2021-04-10","cited_by_count":4,"area":null},{"id":"2206.09120","title":"Pursuit of a Discriminative Representation for Multiple Subspaces via Sequential Games","created":"2022-06-18","cited_by_count":4,"area":null},{"id":"2302.09347","title":"Closed-Loop Transcription via Convolutional Sparse Coding","created":"2023-02-18","cited_by_count":4,"area":null},{"id":"2304.04137","title":"RD-DPP: Rate-Distortion Theory Meets Determinantal Point Process to Diversify Learning Data Samples","created":"2023-04-09","cited_by_count":4,"area":null},{"id":"2407.13841","title":"Many Perception Tasks are Highly Redundant Functions of their Input Data","created":"2024-07-18","cited_by_count":4,"area":null},{"id":"2411.17182","title":"An In-depth Investigation of Sparse Rate Reduction in Transformer-like Models","created":"2024-11-26","cited_by_count":4,"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":"2308.01547","title":"Get the Best of Both Worlds: Improving Accuracy and Transferability by Grassmann Class Representation","created":"2023-08-03","cited_by_count":3,"area":null},{"id":"2411.03033","title":"Rethinking Decoders for Transformer-based Semantic Segmentation: A Compression Perspective","created":"2024-11-05","cited_by_count":3,"area":null},{"id":"2506.00432","title":"Channel Normalization for Time Series Channel Identification","created":"2025-05-31","cited_by_count":3,"area":null},{"id":"2602.20205","title":"OTPrune: Distribution-Aligned Visual Token Pruning via Optimal Transport","created":"2026-02-22","cited_by_count":3,"area":"lr"},{"id":"2107.00195","title":"Non-parametric Semi-Supervised Learning in Many-body Hilbert Space with Rescaled Logarithmic Fidelity","created":"2021-07-01","cited_by_count":2,"area":null},{"id":"2202.04632","title":"A Local Geometric Interpretation of Feature Extraction in Deep Feedforward Neural Networks","created":"2022-02-09","cited_by_count":2,"area":null},{"id":"2210.10300","title":"Dense but Efficient VideoQA for Intricate Compositional Reasoning","created":"2022-10-19","cited_by_count":2,"area":"lr"},{"id":"2407.09524","title":"Geometric Understanding of Discriminability and Transferability for Visual Domain Adaptation","created":"2024-06-24","cited_by_count":2,"area":null},{"id":"2501.02364","title":"Linearly Separable Features in Shallow Nonlinear Networks: Width Scales Polynomially with Intrinsic Data Dimension","created":"2025-01-04","cited_by_count":2,"area":null},{"id":"2503.09260","title":"Neural Normalized Cut: A Differential and Generalizable Approach for Spectral Clustering","created":"2025-03-12","cited_by_count":2,"area":null},{"id":"2509.01360","title":"M3Ret: Unleashing Zero-shot Multimodal Medical Image Retrieval via Self-Supervision","created":"2025-09-01","cited_by_count":2,"area":null},{"id":"2509.16875","title":"Towards Interpretable and Efficient Attention: Compressing All by Contracting a Few","created":"2025-09-21","cited_by_count":2,"area":null},{"id":"2602.09764","title":"Self-Supervised Learning as Discrete Communication","created":"2026-02-10","cited_by_count":2,"area":null},{"id":"2607.18433","title":"Intelligence from Learnable Novelty","created":"2026-07-20","cited_by_count":2,"area":null},{"id":"2111.12232","title":"PMSSC: Parallelizable multi-subset based self-expressive model for subspace clustering","created":"2021-11-24","cited_by_count":1,"area":null},{"id":"2210.00299","title":"Federated Representation Learning via Maximal Coding Rate Reduction","created":"2022-10-01","cited_by_count":1,"area":null},{"id":"2211.05433","title":"A classification performance evaluation measure considering data separability","created":"2022-11-10","cited_by_count":1,"area":null},{"id":"2304.12674","title":"Compressing Sentence Representation with maximum Coding Rate Reduction","created":"2023-04-25","cited_by_count":1,"area":null},{"id":"2403.18291","title":"Towards Non-Exemplar Semi-Supervised Class-Incremental Learning","created":"2024-03-27","cited_by_count":1,"area":null},{"id":"2407.01017","title":"Coding for Intelligence from the Perspective of Category","created":"2024-07-01","cited_by_count":1,"area":null},{"id":"2410.09749","title":"EMWaveNet: Physically Explainable Neural Network Based on Electromagnetic Propagation for SAR Target Recognition","created":"2024-10-13","cited_by_count":1,"area":null},{"id":"2410.16443","title":"Improving Neuron-level Interpretability with White-box Language Models","created":"2024-10-21","cited_by_count":1,"area":null},{"id":"2411.06785","title":"White-Box Diffusion Transformer for single-cell RNA-seq generation","created":"2024-11-11","cited_by_count":1,"area":"diffusion"},{"id":"2411.17961","title":"ESS-ReduNet: Enhancing Subspace Separability of ReduNet via Dynamic Expansion with Bayesian Inference","created":"2024-11-27","cited_by_count":1,"area":null}],"next_cursor":"100"}