{"total":34,"rows":[{"id":"2504.05295","title":"Dion: Distributed Orthonormalized Updates","created":"2025-04-07","cited_by_count":68,"area":null},{"id":"2502.19002","title":"The Sharpness Disparity Principle in Transformers for Accelerating Language Model Pre-Training","created":"2025-02-26","cited_by_count":30,"area":null},{"id":"2501.12666","title":"Explicit Eigenvalue Regularization Improves Sharpness-Aware Minimization","created":"2025-01-22","cited_by_count":21,"area":null},{"id":"2506.15872","title":"Hidden Breakthroughs in Language Model Training","created":"2025-06-18","cited_by_count":15,"area":null},{"id":"2602.11948","title":"Insights on Muon from Simple Quadratics","created":"2026-02-12","cited_by_count":13,"area":null},{"id":"2507.09846","title":"Through the River: Understanding the Benefit of Schedule-Free Methods for Language Model Training","created":"2025-07-14","cited_by_count":9,"area":null},{"id":"2505.24275","title":"GradPower: Powering Gradients for Faster Language Model Pre-Training","created":"2025-05-30","cited_by_count":8,"area":null},{"id":"2602.22681","title":"Accelerating LLM Pre-Training through Flat-Direction Dynamics Enhancement","created":"2026-02-26","cited_by_count":8,"area":null},{"id":"2502.05790","title":"Breaking the Frozen Subspace: Importance Sampling for Low-Rank Optimization in LLM Pretraining","created":"2025-02-09","cited_by_count":7,"area":null},{"id":"2512.22768","title":"Understanding the Mechanisms of Fast Hyperparameter Transfer","created":"2025-12-28","cited_by_count":7,"area":null},{"id":"2605.18632","title":"Position: Weight Space Should Be a First-Class Generative AI Modality","created":"2026-05-18","cited_by_count":6,"area":null},{"id":"2604.09258","title":"Nexus: Same Pretraining Loss, Better Downstream Generalization via Common Minima","created":"2026-04-10","cited_by_count":4,"area":null},{"id":"2605.22432","title":"AMUSE: Anytime Muon with Stable Gradient Evaluation","created":"2026-05-21","cited_by_count":4,"area":null},{"id":"2412.07003","title":"Understanding Gradient Descent through the Training Jacobian","created":"2024-12-09","cited_by_count":3,"area":null},{"id":"2510.25244","title":"BSFA: Leveraging the Subspace Dichotomy to Accelerate Neural Network Training","created":"2025-10-29","cited_by_count":3,"area":null},{"id":"2604.20614","title":"Too Sharp, Too Sure: When Calibration Follows Curvature","created":"2026-04-22","cited_by_count":3,"area":null},{"id":"2507.03545","title":"DOME: Improving Signal-to-Noise in Stochastic Gradient Descent via Sharp-Direction Subspace Filtering","created":"2025-07-04","cited_by_count":2,"area":null},{"id":"2605.26484","title":"Extra-Merge: Tracing the Rank-1 Subspace of Model Merging in Language Model Pre-Training","created":"2026-05-26","cited_by_count":2,"area":null},{"id":"2505.11972","title":"Accelerating Neural Network Training Along Sharp and Flat Directions","created":"2025-05-17","cited_by_count":1,"area":null},{"id":"2509.19698","title":"A Unified Noise-Curvature View of Loss of Trainability","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2510.01878","title":"Geometrically Principled Randomized Optimization for Efficient LLM Training","created":"2025-10-02","cited_by_count":1,"area":null},{"id":"2602.00545","title":"Depth, Not Data: An Analysis of Hessian Spectral Bifurcation","created":"2026-01-31","cited_by_count":1,"area":null},{"id":"2606.30226","title":"Characterizing Optimizer-Dependent Training Dynamics Through Hessian Eigenvector Displacement and Localization","created":"2026-06-29","cited_by_count":1,"area":null},{"id":"2607.23012","title":"Mini-batch Noise Lowers Sharpness via Dominant-Subspace Fluctuations","created":"2026-07-25","cited_by_count":1,"area":null},{"id":"2412.13928","title":"Subspace Langevin Monte Carlo","created":"2024-12-18","cited_by_count":0,"area":null},{"id":"2511.03110","title":"Towards Scalable Backpropagation-Free Gradient Estimation","created":"2025-11-05","cited_by_count":0,"area":null},{"id":"2601.10251","title":"X-SAM: Boosting Sharpness-Aware Minimization with Dominant-Eigenvector Gradient Correction","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2602.02899","title":"Decentralized SGD with Controlled Disagreement Finds Flatter Minima","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2605.27739","title":"Worker Disagreement Reveals Sharp Directions in Local SGD","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2606.00542","title":"Rethinking Bregman Divergences in Kronecker-Factored Optimizers","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2606.30384","title":"Scalar Representations of Neural Network Training Dynamics","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2608.28442","title":"Curvature-Conditioned Multiscale Momentum with Sphere Constraints for LLM Pretraining","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.01034","title":"The Multiple Timescales of Gradient Descent on the Edge of Stability: A Perturbative Derivation of the Central Flow","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.31983","title":"Understanding the Subspace Stabilization of the Hessian and Gradient Covariance Matrix","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}