{"total":36,"rows":[{"id":"2306.01129","title":"White-Box Transformers via Sparse Rate Reduction","created":"2023-06-01","cited_by_count":80,"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":"2405.17767","title":"Linguistic Collapse: Neural Collapse in (Large) Language Models","created":"2024-05-28","cited_by_count":38,"area":null},{"id":"2406.14479","title":"Tracing Representation Progression: Analyzing and Enhancing Layer-Wise Similarity","created":"2024-06-20","cited_by_count":36,"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":"2406.04112","title":"Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation","created":"2024-06-06","cited_by_count":26,"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":"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":"2409.04180","title":"The Prevalence of Neural Collapse in Neural Multivariate Regression","created":"2024-09-06","cited_by_count":21,"area":null},{"id":"2306.01154","title":"The Law of Parsimony in Gradient Descent for Learning Deep Linear Networks","created":"2023-06-01","cited_by_count":20,"area":null},{"id":"2307.01951","title":"A Neural Collapse Perspective on Feature Evolution in Graph Neural Networks","created":"2023-07-04","cited_by_count":19,"area":null},{"id":"2405.14468","title":"Neural Collapse versus Low-rank Bias: Is Deep Neural Collapse Really Optimal?","created":"2024-05-23","cited_by_count":17,"area":null},{"id":"2408.13442","title":"A Law of Next-Token Prediction in Large Language Models","created":"2024-08-24","cited_by_count":15,"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":"2410.23169","title":"The Persistence of Neural Collapse Despite Low-Rank Bias","created":"2024-10-30","cited_by_count":13,"area":null},{"id":"2405.00985","title":"Progressive Feedforward Collapse of ResNet Training","created":"2024-05-02","cited_by_count":12,"area":null},{"id":"2404.06106","title":"Unifying Low Dimensional Spectra in Deep Learning","created":"2024-04-09","cited_by_count":11,"area":null},{"id":"2505.15239","title":"Neural Collapse is Globally Optimal in Deep Regularized ResNets and Transformers","created":"2025-05-21","cited_by_count":10,"area":null},{"id":"2306.03440","title":"Quantifying the Variability Collapse of Neural Networks","created":"2023-06-06","cited_by_count":9,"area":null},{"id":"2311.07444","title":"On the Robustness of Neural Collapse and the Neural Collapse of Robustness","created":"2023-11-13","cited_by_count":9,"area":null},{"id":"2405.08920","title":"Neural Collapse Meets Differential Privacy: Curious Behaviors of NoisyGD with Near-perfect Representation Learning","created":"2024-05-14","cited_by_count":8,"area":null},{"id":"2506.05801","title":"Neural Collapse in Cumulative Link Models for Ordinal Regression: An Analysis with Unconstrained Feature Model","created":"2025-06-06","cited_by_count":6,"area":null},{"id":"2406.02105","title":"Can Kernel Methods Explain How the Data Affects Neural Collapse?","created":"2024-06-04","cited_by_count":4,"area":null},{"id":"2406.05222","title":"Towards Interpretable Deep Local Learning with Successive Gradient Reconciliation","created":"2024-06-07","cited_by_count":4,"area":null},{"id":"2407.19353","title":"Spring-block theory of feature learning in deep neural networks","created":"2024-07-28","cited_by_count":2,"area":null},{"id":"2410.04264","title":"Decoupling Dynamical Richness from Representation Learning: Towards Practical Measurement","created":"2024-10-05","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":"2512.04006","title":"Diagonalizing the Softmax: Hadamard Initialization for Tractable Cross-Entropy Dynamics","created":"2025-12-03","cited_by_count":2,"area":null},{"id":"2410.04472","title":"Collapsed Language Models Promote Fairness","created":"2024-10-06","cited_by_count":1,"area":null},{"id":"2501.05017","title":"Continuous Knowledge-Preserving Decomposition with Adaptive Layer Selection for Few-Shot Class-Incremental Learning","created":"2025-01-09","cited_by_count":1,"area":null},{"id":"2505.05181","title":"Stochastic Layer-wise Learning: Scalable and Efficient Alternative to Backpropagation","created":"2025-05-08","cited_by_count":1,"area":null},{"id":"2603.15299","title":"Enhancing classification accuracy through chaos","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2603.23805","title":"Deep Neural Regression Collapse","created":"2026-03-25","cited_by_count":1,"area":null},{"id":"2506.02016","title":"Are classical deep neural networks weakly adversarially robust?","created":"2025-05-28","cited_by_count":0,"area":null},{"id":"2509.01235","title":"Geometric origin of adversarial vulnerability in deep learning","created":"2025-09-01","cited_by_count":0,"area":null},{"id":"2605.23087","title":"The Implicit Bias of Depth: From Neural Collapse to Softmax Codes","created":"2026-05-21","cited_by_count":0,"area":null}],"next_cursor":null}