{"total":26,"rows":[{"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":"2406.04112","title":"Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation","created":"2024-06-06","cited_by_count":26,"area":null},{"id":"2405.19454","title":"Deep Grokking: Would Deep Neural Networks Generalize Better?","created":"2024-05-29","cited_by_count":15,"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":"2406.01909","title":"A Global Geometric Analysis of Maximal Coding Rate Reduction","created":"2024-06-04","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":"2407.07810","title":"Transformer Block Coupling and its Correlation with Generalization in LLMs","created":"2024-07-10","cited_by_count":10,"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":"2503.19859","title":"An Overview of Low-Rank Structures in the Training and Adaptation of Large Models","created":"2025-03-25","cited_by_count":9,"area":null},{"id":"2402.09050","title":"End-to-End Training Induces Information Bottleneck through Layer-Role Differentiation: A Comparative Analysis with Layer-wise Training","created":"2024-02-14","cited_by_count":8,"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":"2605.18598","title":"Pointwise Generalization in Deep Neural Networks","created":"2026-05-18","cited_by_count":4,"area":null},{"id":"2410.21262","title":"BLAST: Block-Level Adaptive Structured Matrices for Efficient Deep Neural Network Inference","created":"2024-10-28","cited_by_count":3,"area":null},{"id":"2407.17754","title":"DualFed: Enjoying both Generalization and Personalization in Federated Learning via Hierachical Representations","created":"2024-07-25","cited_by_count":2,"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":"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":"2506.20344","title":"A Complete Loss Landscape Analysis of Regularized Deep Matrix Factorization","created":"2025-06-25","cited_by_count":2,"area":null},{"id":"2510.21078","title":"Neural Collapse under Gradient Flow on Shallow ReLU Networks for Orthogonally Separable Data","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2606.08985","title":"Beyond Neural Collapse: Task-Intrinsic Geometry Governs Neural Representations in Modular Arithmetic","created":"2026-06-08","cited_by_count":2,"area":null},{"id":"2602.06208","title":"Emergent Low-Rank Training Dynamics in MLPs with Smooth Activations","created":"2026-02-05","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":"2608.02378","title":"Gecko: Fast Private Inference via Secure Public Encoder Offloading","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2609.00472","title":"Higher Structures in Deep Learning","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.03117","title":"Kernel Reboot: Breaking the Boundaries of Neural Tangent Kernels for Neural Fields","created":"2026-09-02","cited_by_count":0,"area":null}],"next_cursor":null}