{"total":719,"rows":[{"id":"2405.07987","title":"The Platonic Representation Hypothesis","created":"2024-05-13","cited_by_count":382,"area":null},{"id":"2511.08544","title":"LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics","created":"2025-11-11","cited_by_count":254,"area":null},{"id":"2205.10343","title":"Towards Understanding Grokking: An Effective Theory of Representation Learning","created":"2022-05-20","cited_by_count":230,"area":null},{"id":"2105.02375","title":"A Geometric Analysis of Neural Collapse with Unconstrained Features","created":"2021-05-06","cited_by_count":227,"area":null},{"id":"2211.10154","title":"CRAFT: Concept Recursive Activation FacTorization for Explainability","created":"2022-11-17","cited_by_count":178,"area":null},{"id":"2506.21734","title":"Hierarchical Reasoning Model","created":"2025-06-26","cited_by_count":177,"area":"lr"},{"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":"2106.02073","title":"Neural Collapse Under MSE Loss: Proximity to and Dynamics on the Central Path","created":"2021-06-03","cited_by_count":158,"area":null},{"id":"2204.09179","title":"On the Representation Collapse of Sparse Mixture of Experts","created":"2022-04-20","cited_by_count":157,"area":"moe"},{"id":"2207.09052","title":"Balanced Contrastive Learning for Long-Tailed Visual Recognition","created":"2022-07-19","cited_by_count":144,"area":null},{"id":"2305.05465","title":"The emergence of clusters in self-attention dynamics","created":"2023-05-09","cited_by_count":140,"area":null},{"id":"2402.07043","title":"A Tale of Tails: Model Collapse as a Change of Scaling Laws","created":"2024-02-10","cited_by_count":130,"area":"synth"},{"id":"2210.06313","title":"The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers","created":"2022-10-12","cited_by_count":122,"area":null},{"id":"2309.10313","title":"Investigating the Catastrophic Forgetting in Multimodal Large Language Models","created":"2023-09-19","cited_by_count":119,"area":"mllm"},{"id":"2302.03004","title":"Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learning","created":"2023-02-06","cited_by_count":116,"area":null},{"id":"2306.07304","title":"A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation","created":"2023-06-11","cited_by_count":109,"area":null},{"id":"2202.08087","title":"Extended Unconstrained Features Model for Exploring Deep Neural Collapse","created":"2022-02-16","cited_by_count":102,"area":null},{"id":"2112.15121","title":"On the Role of Neural Collapse in Transfer Learning","created":"2021-12-30","cited_by_count":100,"area":null},{"id":"2203.09081","title":"Inducing Neural Collapse in Imbalanced Learning: Do We Really Need a Learnable Classifier at the End of Deep Neural Network?","created":"2022-03-17","cited_by_count":100,"area":null},{"id":"2203.01238","title":"On the Optimization Landscape of Neural Collapse under MSE Loss: Global Optimality with Unconstrained Features","created":"2022-03-02","cited_by_count":97,"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":"2206.04817","title":"The Slingshot Mechanism: An Empirical Study of Adaptive Optimizers and the Grokking Phenomenon","created":"2022-06-10","cited_by_count":94,"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":"2305.18887","title":"How Does Information Bottleneck Help Deep Learning?","created":"2023-05-30","cited_by_count":93,"area":null},{"id":"2110.02796","title":"An Unconstrained Layer-Peeled Perspective on Neural Collapse","created":"2021-10-06","cited_by_count":87,"area":null},{"id":"2105.10446","title":"ReduNet: A White-box Deep Network from the Principle of Maximizing Rate Reduction","created":"2021-05-21","cited_by_count":84,"area":null},{"id":"2208.05512","title":"Imbalance Trouble: Revisiting Neural-Collapse Geometry","created":"2022-08-10","cited_by_count":80,"area":null},{"id":"2402.19449","title":"Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models","created":"2024-02-29","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":"2103.01550","title":"Label-Imbalanced and Group-Sensitive Classification under Overparameterization","created":"2021-03-02","cited_by_count":74,"area":null},{"id":"2308.16898","title":"Transformers as Support Vector Machines","created":"2023-08-31","cited_by_count":74,"area":null},{"id":"2112.15424","title":"A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part II: Applications, Cognitive Models, and Challenges","created":"2021-11-12","cited_by_count":69,"area":null},{"id":"2102.08817","title":"Dissecting Supervised Contrastive Learning","created":"2021-02-17","cited_by_count":64,"area":null},{"id":"2202.08384","title":"Limitations of Neural Collapse for Understanding Generalization in Deep Learning","created":"2022-02-17","cited_by_count":63,"area":null},{"id":"2205.00329","title":"Continual Learning with Foundation Models: An Empirical Study of Latent Replay","created":"2022-04-30","cited_by_count":61,"area":null},{"id":"2407.01800","title":"Normalization and effective learning rates in reinforcement learning","created":"2024-07-01","cited_by_count":58,"area":"deeprl"},{"id":"2303.10058","title":"No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifier","created":"2023-03-17","cited_by_count":55,"area":null},{"id":"2106.03791","title":"Learning Gaussian Mixtures with Generalised Linear Models: Precise Asymptotics in High-dimensions","created":"2021-06-07","cited_by_count":54,"area":null},{"id":"2402.15555","title":"Deep Networks Always Grok and Here is Why","created":"2024-02-23","cited_by_count":51,"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":"2505.23883","title":"BioCLIP 2: Emergent Properties from Scaling Hierarchical Contrastive Learning","created":"2025-05-29","cited_by_count":50,"area":null},{"id":"2312.11536","title":"Fast Decision Boundary based Out-of-Distribution Detector","created":"2023-12-15","cited_by_count":49,"area":null},{"id":"2303.13662","title":"Rethinking Domain Generalization for Face Anti-spoofing: Separability and Alignment","created":"2023-03-23","cited_by_count":48,"area":null},{"id":"2301.01100","title":"Understanding Imbalanced Semantic Segmentation Through Neural Collapse","created":"2023-01-03","cited_by_count":46,"area":null},{"id":"2109.06024","title":"Formalizing and Estimating Distribution Inference Risks","created":"2021-09-13","cited_by_count":43,"area":null},{"id":"2204.08735","title":"Neural Collapse Inspired Attraction-Repulsion-Balanced Loss for Imbalanced Learning","created":"2022-04-19","cited_by_count":43,"area":null},{"id":"2305.13165","title":"Deep Neural Collapse Is Provably Optimal for the Deep Unconstrained Features Model","created":"2023-05-22","cited_by_count":43,"area":null},{"id":"2106.10865","title":"Benign Overfitting in Multiclass Classification: All Roads Lead to Interpolation","created":"2021-06-21","cited_by_count":42,"area":null},{"id":"2310.06823","title":"NECO: NEural Collapse Based Out-of-distribution detection","created":"2023-10-10","cited_by_count":42,"area":null},{"id":"2106.04180","title":"Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained Models","created":"2021-06-08","cited_by_count":41,"area":null},{"id":"2204.07596","title":"Perfectly Balanced: Improving Transfer and Robustness of Supervised Contrastive Learning","created":"2022-04-15","cited_by_count":40,"area":null},{"id":"2301.00437","title":"Neural Collapse in Deep Linear Networks: From Balanced to Imbalanced Data","created":"2023-01-01","cited_by_count":40,"area":null},{"id":"2205.01789","title":"Do More Negative Samples Necessarily Hurt in Contrastive Learning?","created":"2022-05-03","cited_by_count":39,"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":"2405.09786","title":"IBD-PSC: Input-level Backdoor Detection via Parameter-oriented Scaling Consistency","created":"2024-05-16","cited_by_count":39,"area":null},{"id":"2305.16292","title":"Sharpness-Aware Minimization Leads to Low-Rank Features","created":"2023-05-25","cited_by_count":38,"area":null},{"id":"2309.09725","title":"Neural Collapse for Unconstrained Feature Model under Cross-entropy Loss with Imbalanced Data","created":"2023-09-18","cited_by_count":38,"area":null},{"id":"2405.17767","title":"Linguistic Collapse: Neural Collapse in (Large) Language Models","created":"2024-05-28","cited_by_count":38,"area":null},{"id":"2507.08802","title":"The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?","created":"2025-07-11","cited_by_count":37,"area":"mechinterp"},{"id":"2210.17020","title":"A Law of Data Separation in Deep Learning","created":"2022-10-31","cited_by_count":36,"area":null},{"id":"2404.02117","title":"Pre-trained Vision and Language Transformers Are Few-Shot Incremental Learners","created":"2024-04-02","cited_by_count":36,"area":"distill"},{"id":"2406.14479","title":"Tracing Representation Progression: Analyzing and Enhancing Layer-Wise Similarity","created":"2024-06-20","cited_by_count":36,"area":null},{"id":"2503.21073","title":"Shared Global and Local Geometry of Language Model Embeddings","created":"2025-03-27","cited_by_count":36,"area":null},{"id":"2210.16658","title":"Perturbation Analysis of Neural Collapse","created":"2022-10-29","cited_by_count":35,"area":null},{"id":"2205.14566","title":"ProxyMix: Proxy-based Mixup Training with Label Refinery for Source-Free Domain Adaptation","created":"2022-05-29","cited_by_count":34,"area":null},{"id":"2209.06235","title":"Improving Self-Supervised Learning by Characterizing Idealized Representations","created":"2022-09-13","cited_by_count":34,"area":null},{"id":"2305.19753","title":"The Tunnel Effect: Building Data Representations in Deep Neural Networks","created":"2023-05-31","cited_by_count":34,"area":null},{"id":"2311.01479","title":"Detecting Out-of-Distribution Through the Lens of Neural Collapse","created":"2023-11-02","cited_by_count":34,"area":null},{"id":"2305.15614","title":"Reverse Engineering Self-Supervised Learning","created":"2023-05-24","cited_by_count":33,"area":null},{"id":"2310.12244","title":"A Unified Approach to Domain Incremental Learning with Memory: Theory and Algorithm","created":"2023-10-18","cited_by_count":33,"area":null},{"id":"2108.12099","title":"Learning to Give Checkable Answers with Prover-Verifier Games","created":"2021-08-27","cited_by_count":32,"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":"2505.10465","title":"Superposition Yields Robust Neural Scaling","created":"2025-05-15","cited_by_count":31,"area":"mechinterp"},{"id":"2305.16536","title":"Which Features are Learnt by Contrastive Learning? On the Role of Simplicity Bias in Class Collapse and Feature Suppression","created":"2023-05-25","cited_by_count":30,"area":null},{"id":"2310.04400","title":"On the Embedding Collapse when Scaling up Recommendation Models","created":"2023-10-06","cited_by_count":29,"area":null},{"id":"2604.21691","title":"There Will Be a Scientific Theory of Deep Learning","created":"2026-04-23","cited_by_count":29,"area":null},{"id":"2210.15435","title":"Grokking phase transitions in learning local rules with gradient descent","created":"2022-10-26","cited_by_count":28,"area":null},{"id":"2302.12453","title":"Inducing Neural Collapse in Deep Long-tailed Learning","created":"2023-02-24","cited_by_count":28,"area":null},{"id":"2105.10585","title":"Properties of the After Kernel","created":"2021-05-21","cited_by_count":27,"area":null},{"id":"2205.13303","title":"Gaussian Universality of Perceptrons with Random Labels","created":"2022-05-26","cited_by_count":26,"area":null},{"id":"2309.17230","title":"Spurious Feature Diversification Improves Out-of-distribution Generalization","created":"2023-09-29","cited_by_count":26,"area":null},{"id":"2412.07909","title":"Explaining and Mitigating the Modality Gap in Contrastive Multimodal Learning","created":"2024-12-10","cited_by_count":26,"area":null},{"id":"2210.03820","title":"The Asymmetric Maximum Margin Bias of Quasi-Homogeneous Neural Networks","created":"2022-10-07","cited_by_count":25,"area":null},{"id":"2308.06764","title":"Few-shot Class-incremental Learning for Classification and Object Detection: A Survey","created":"2023-08-13","cited_by_count":25,"area":null},{"id":"2309.16932","title":"Symmetry Induces Structure and Constraint of Learning","created":"2023-09-29","cited_by_count":25,"area":null},{"id":"2212.12206","title":"Understanding and Improving Transfer Learning of Deep Models via Neural Collapse","created":"2022-12-23","cited_by_count":24,"area":null},{"id":"2305.17608","title":"Reward Collapse in Aligning Large Language Models","created":"2023-05-28","cited_by_count":24,"area":"alignment"},{"id":"2405.05012","title":"The Entropy Enigma: Success and Failure of Entropy Minimization","created":"2024-05-08","cited_by_count":24,"area":null},{"id":"2408.15417","title":"Implicit Geometry of Next-token Prediction: From Language Sparsity Patterns to Model Representations","created":"2024-08-27","cited_by_count":24,"area":null},{"id":"2206.12314","title":"Learning sparse features can lead to overfitting in neural networks","created":"2022-06-24","cited_by_count":23,"area":null},{"id":"2209.08378","title":"Linking Neural Collapse and L2 Normalization with Improved Out-of-Distribution Detection in Deep Neural Networks","created":"2022-09-17","cited_by_count":23,"area":null},{"id":"2303.07608","title":"On the Implicit Geometry of Cross-Entropy Parameterizations for Label-Imbalanced Data","created":"2023-03-14","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":"2402.10688","title":"Towards Uncovering How Large Language Model Works: An Explainability Perspective","created":"2024-02-16","cited_by_count":22,"area":"lr"},{"id":"2402.13728","title":"Average gradient outer product as a mechanism for deep neural collapse","created":"2024-02-21","cited_by_count":22,"area":null},{"id":"2508.17689","title":"On the Edge of Memorization in Diffusion Models","created":"2025-08-25","cited_by_count":22,"area":"diffusion"},{"id":"2103.01499","title":"Demystifying Batch Normalization in ReLU Networks: Equivalent Convex Optimization Models and Implicit Regularization","created":"2021-03-02","cited_by_count":21,"area":null},{"id":"2206.08704","title":"Maximum Class Separation as Inductive Bias in One Matrix","created":"2022-06-17","cited_by_count":21,"area":null},{"id":"2303.09674","title":"DiGeo: Discriminative Geometry-Aware Learning for Generalized Few-Shot Object Detection","created":"2023-03-16","cited_by_count":21,"area":null}],"next_cursor":"100"}