{"total":29,"rows":[{"id":"2512.22382","title":"Completed Hyperparameter Transfer across Modules, Width, Depth, Batch and Duration","created":"2025-12-26","cited_by_count":27,"area":null},{"id":"2505.02809","title":"Towards Quantifying the Hessian Structure of Neural Networks","created":"2025-05-05","cited_by_count":13,"area":null},{"id":"2601.23000","title":"Mano: Restriking Manifold Optimization for LLM Training","created":"2026-01-30","cited_by_count":12,"area":null},{"id":"2603.10067","title":"HTMuon: Improving Muon via Heavy-Tailed Spectral Correction","created":"2026-03-10","cited_by_count":12,"area":null},{"id":"2602.04998","title":"Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning","created":"2026-02-04","cited_by_count":10,"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":"2602.14208","title":"Fast Catch-Up, Late Switching: Optimal Batch Size Scheduling via Functional Scaling Laws","created":"2026-02-15","cited_by_count":6,"area":null},{"id":"2606.04662","title":"Why Muon Outperforms Adam: A Curvature Perspective","created":"2026-06-03","cited_by_count":6,"area":null},{"id":"2602.11137","title":"Weight Decay Improves Language Model Plasticity","created":"2026-02-11","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":"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":"2510.14009","title":"Noise-Adaptive Layerwise Learning Rates: Accelerating Geometry-Aware Optimization for Deep Neural Network Training","created":"2025-10-15","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":"2511.21377","title":"Controlling changes to attention logits","created":"2025-11-26","cited_by_count":3,"area":null},{"id":"2605.22297","title":"One LR Doesn't Fit All: Heavy-Tail Guided Layerwise Learning Rates for LLMs","created":"2026-05-21","cited_by_count":3,"area":null},{"id":"2608.24814","title":"Effective Learning Rate Governs Loss Dynamics in Language Model Pretraining","created":"2026-08-25","cited_by_count":3,"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":"2606.29158","title":"On the Nonlinearity of Learning Rate Scaling for LLM Training","created":"2026-06-28","cited_by_count":2,"area":null},{"id":"2512.07112","title":"FOAM: Blocked State Folding for Memory-Efficient LLM Training","created":"2025-12-08","cited_by_count":1,"area":null},{"id":"2606.00340","title":"Balancing Learning Rates Across Layers: Exact Two-Step Dynamics and Optimal Scaling in Linear Neural Networks","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2605.05794","title":"Revealing Modular Gradient Noise Imbalance in LLMs: Calibrating Adam via Signal-to-Noise Ratio","created":"2026-05-07","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":"2608.28442","title":"Curvature-Conditioned Multiscale Momentum with Sphere Constraints for LLM Pretraining","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.02728","title":"Momentum in large-batch training: Polyak enlarges the critical batch size, Nesterov improves data efficiency","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.34681","title":"SOLAR: A State-Driven Online Learning Rate Scheduler for LLM Pretraining","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36692","title":"Normalize-Then-Precondition: A Hierarchical Approach to Marginal Scale and Interaction Geometry for LLM Training","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39767","title":"How Does Local Landscape Geometry Evolve in Language Model Pre-Training?","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.17285","title":"Which Geometry on Which Layer? Measured Sign-Spectral Assignment in Mixed-Optimizer Training","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}