{"total":32,"rows":[{"id":"2503.21073","title":"Shared Global and Local Geometry of Language Model Embeddings","created":"2025-03-27","cited_by_count":36,"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":"2604.01472","title":"The Newton-Muon Optimizer","created":"2026-04-01","cited_by_count":18,"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":"2410.23169","title":"The Persistence of Neural Collapse Despite Low-Rank Bias","created":"2024-10-30","cited_by_count":13,"area":null},{"id":"2502.05300","title":"Parameter Symmetry Potentially Unifies Deep Learning Theory","created":"2025-02-07","cited_by_count":12,"area":null},{"id":"2407.07810","title":"Transformer Block Coupling and its Correlation with Generalization in LLMs","created":"2024-07-10","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":"2406.11624","title":"Words in Motion: Extracting Interpretable Control Vectors for Motion Transformers","created":"2024-06-17","cited_by_count":9,"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":"2505.24254","title":"Rethinking Continual Learning with Progressive Neural Collapse","created":"2025-05-30","cited_by_count":4,"area":null},{"id":"2511.07380","title":"Mining Useful General Data for Low-Resource Domain Adaptation","created":"2025-11-10","cited_by_count":4,"area":null},{"id":"2410.07820","title":"Mitigating Gender Bias in Code Large Language Models via Model Editing","created":"2024-10-10","cited_by_count":3,"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":"2512.04006","title":"Diagonalizing the Softmax: Hadamard Initialization for Tractable Cross-Entropy Dynamics","created":"2025-12-03","cited_by_count":2,"area":null},{"id":"2606.26749","title":"Structure Before Collapse: Transient semantic geometry in next-token prediction","created":"2026-06-25","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":"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":"2602.16642","title":"Optimizer choice matters for the emergence of Neural Collapse","created":"2026-02-18","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":"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":"2606.00344","title":"The role of class encoding in neural collapse","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.30813","title":"Gradient Smoothing: Coupling Layer-wise Updates for Improved Optimization","created":"2026-06-29","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":"2607.14116","title":"ReportMedSAM: Guiding Segmentation Through Radiology Reports","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2609.37824","title":"The Geometry of Inference in Transformer Residual Streams","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.03052","title":"The Geometry of Knowledge Accessibility in Large Language Models","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.16660","title":"Compression Through Time: An Interplay of Separability, Stationarity and Capacity","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}