{"total":36,"rows":[{"id":"2405.17767","title":"Linguistic Collapse: Neural Collapse in (Large) Language Models","created":"2024-05-28","cited_by_count":38,"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":"2401.02058","title":"Neural Collapse for Cross-entropy Class-Imbalanced Learning with Unconstrained ReLU Feature Model","created":"2024-01-04","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":"2410.04887","title":"Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural Collapse","created":"2024-10-07","cited_by_count":16,"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":"2402.03979","title":"Cross Entropy versus Label Smoothing: A Neural Collapse Perspective","created":"2024-02-06","cited_by_count":11,"area":null},{"id":"2402.03991","title":"Provable Emergence of Deep Neural Collapse and Low-Rank Bias in $L^2$-Regularized Nonlinear Networks","created":"2024-02-06","cited_by_count":11,"area":null},{"id":"2404.06106","title":"Unifying Low Dimensional Spectra in Deep Learning","created":"2024-04-09","cited_by_count":11,"area":null},{"id":"2409.01832","title":"Beyond Unconstrained Features: Neural Collapse for Shallow Neural Networks with General Data","created":"2024-09-03","cited_by_count":10,"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":"2410.05063","title":"Control-oriented Clustering of Visual Latent Representation","created":"2024-10-07","cited_by_count":8,"area":null},{"id":"2509.17738","title":"Flatness is Necessary, Neural Collapse is Not: Rethinking Generalization via Grokking","created":"2025-09-22","cited_by_count":8,"area":null},{"id":"2510.05635","title":"NEO: No-Optimization Test-Time Adaptation through Latent Re-Centering","created":"2025-10-07","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":"2309.10370","title":"Geometric structure of shallow neural networks and constructive ${\\mathcal L}^2$ cost minimization","created":"2023-09-19","cited_by_count":4,"area":null},{"id":"2410.11985","title":"The Fair Language Model Paradox","created":"2024-10-15","cited_by_count":4,"area":null},{"id":"2506.01562","title":"Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization","created":"2025-06-02","cited_by_count":3,"area":null},{"id":"2512.01766","title":"On the Unreasonable Effectiveness of Last-layer Retraining","created":"2025-12-01","cited_by_count":3,"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":"2505.08348","title":"Geometry of Semantics in Next-Token Prediction: How Optimization Implicitly Organizes Linguistic Representations","created":"2025-05-13","cited_by_count":2,"area":null},{"id":"2505.09308","title":"Neural Multivariate Regression: Qualitative Insights from the Unconstrained Feature Model","created":"2025-05-14","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":"2601.12011","title":"Why Loss Re-weighting Works If You Stop Early: Training Dynamics of Unconstrained Features","created":"2026-01-17","cited_by_count":2,"area":null},{"id":"2604.00230","title":"Neural Collapse Dynamics: Depth, Activation, Regularisation, and Feature Norm Threshold","created":"2026-03-31","cited_by_count":2,"area":null},{"id":"2510.01105","title":"Geometric Analysis of Neural Regression Collapse via Intrinsic Dimension","created":"2025-10-01","cited_by_count":1,"area":null},{"id":"2512.07400","title":"Heads collapse, features stay: Why Replay needs big buffers","created":"2025-12-08","cited_by_count":1,"area":null},{"id":"2605.01897","title":"How Label Imbalance Shapes Geometry: A General Spectral Analysis of Multi-Label Neural Collapse","created":"2026-05-03","cited_by_count":0,"area":null},{"id":"2605.10047","title":"Rethinking Loss Reweighting for Imbalance Learning as an Inverse Problem: A Neural Collapse Point of View","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.11291","title":"Optimal Representations for Generalized Contrastive Learning with Imbalanced Datasets","created":"2026-05-11","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},{"id":"2606.26839","title":"Ordinal Neural Collapse as a Representation Prior for Visual Navigation","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.09487","title":"Neural Collapse Is Forbidden: Information Floors in Language Models","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2607.12916","title":"Contrastive-Collapsed Loss for Flexible and Geometrically Optimal Embeddings and Faster Convergence","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2609.39464","title":"Understanding Head Geometry and Dynamics in Federated Regression through a Natural Solution Selection Rule: An Unconstrained Feature Model Analysis","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}