{"total":19,"rows":[{"id":"2502.00264","title":"Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion","created":"2025-02-01","cited_by_count":16,"area":null},{"id":"2502.05300","title":"Parameter Symmetry Potentially Unifies Deep Learning Theory","created":"2025-02-07","cited_by_count":12,"area":null},{"id":"2410.03006","title":"Formation of Representations in Neural Networks","created":"2024-10-03","cited_by_count":10,"area":null},{"id":"2505.12387","title":"Neural Thermodynamics: Entropic Forces in Deep and Universal Representation Learning","created":"2025-05-18","cited_by_count":9,"area":null},{"id":"2408.15495","title":"Remove Symmetries to Control Model Expressivity and Improve Optimization","created":"2024-08-28","cited_by_count":8,"area":null},{"id":"2507.01098","title":"Proof of a perfect platonic representation hypothesis","created":"2025-07-01","cited_by_count":8,"area":null},{"id":"2605.26895","title":"Negligible in Size, Significant in Effect: On Scale Vectors in Large Language Models","created":"2026-05-26","cited_by_count":4,"area":null},{"id":"2509.23898","title":"Differentiable Sparsity via $D$-Gating: Simple and Versatile Structured Penalization","created":"2025-09-28","cited_by_count":3,"area":null},{"id":"2601.06597","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","created":"2026-01-10","cited_by_count":3,"area":null},{"id":"2603.22030","title":"On the Interplay of Priors and Overparametrization in Bayesian Neural Network Posteriors","created":"2026-03-23","cited_by_count":3,"area":null},{"id":"2509.01349","title":"Phase diagram and eigenvalue dynamics of stochastic gradient descent in multilayer neural networks","created":"2025-09-01","cited_by_count":1,"area":null},{"id":"2602.05065","title":"Does SGD Seek Flatness or Sharpness? An Exactly Solvable Model","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2603.10074","title":"Marginals Before Conditionals","created":"2026-03-10","cited_by_count":1,"area":null},{"id":"2607.12332","title":"Gradient Flow Dynamics and Implicit Bias of Diagonal Linear Networks under Infinitesimal Initialization","created":"2026-07-14","cited_by_count":1,"area":null},{"id":"2409.07275","title":"Tuning-Free Online Robust Principal Component Analysis through Implicit Regularization","created":"2024-09-11","cited_by_count":0,"area":null},{"id":"2410.07719","title":"How Learning Dynamics Drive Adversarially Robust Generalization?","created":"2024-10-10","cited_by_count":0,"area":null},{"id":"2510.05606","title":"Fractal basin geometry and the limits to predictability and reproducibility in deep learning","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2512.21447","title":"An Equivariance Toolbox for Learning Dynamics","created":"2025-12-24","cited_by_count":0,"area":null},{"id":"2610.00615","title":"Learning the identity: a case study of how SGD selects among functional decompositions","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}