{"total":21,"rows":[{"id":"2507.09404","title":"Scaling Laws for Optimal Data Mixtures","created":"2025-07-12","cited_by_count":52,"area":null},{"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":"2507.02119","title":"Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks","created":"2025-07-02","cited_by_count":22,"area":null},{"id":"2511.18903","title":"How Learning Rate Decay Wastes Your Best Data in Curriculum-Based LLM Pretraining","created":"2025-11-24","cited_by_count":14,"area":null},{"id":"2602.03702","title":"Anytime Pretraining: Horizon-Free Learning-Rate Schedules with Weight Averaging","created":"2026-02-03","cited_by_count":10,"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":"2509.25087","title":"Scaling with Collapse: Efficient and Predictable Training of LLM Families","created":"2025-09-29","cited_by_count":9,"area":null},{"id":"2602.06797","title":"Optimal Learning Rate Schedules under Functional Scaling Laws: Power Decay and Warmup-Stable-Decay","created":"2026-02-06","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":"2505.07796","title":"Learning Dynamics in Continual Pre-Training for Large Language Models","created":"2025-05-12","cited_by_count":5,"area":null},{"id":"2505.12242","title":"ZenFlow: Enabling Stall-Free Offloading for LLM Training","created":"2025-05-18","cited_by_count":5,"area":null},{"id":"2509.25049","title":"Efficient Hyperparameter Tuning via Trajectory Invariance Principle","created":"2025-09-29","cited_by_count":4,"area":null},{"id":"2602.10300","title":"Configuration-to-Performance Scaling Law with Neural Ansatz","created":"2026-02-10","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":"2505.24452","title":"Stepsize anything: A unified learning rate schedule for budgeted-iteration training","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2602.02593","title":"Effective Frontiers: A Unification of Neural Scaling Laws","created":"2026-02-01","cited_by_count":1,"area":null},{"id":"2606.17660","title":"TuneAhead: Predicting Fine-tuning Performance Before Full Training Begins","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2606.29858","title":"Smooth Scaling Laws Hide Stepwise Token Learning","created":"2026-06-29","cited_by_count":1,"area":null},{"id":"2601.05034","title":"How to Set the Batch Size for Large-Scale Pre-training?","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2605.09154","title":"Predicting Large Model Test Losses with a Noisy Quadratic System","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2609.33041","title":"Balancing Early Performance Sacrifices with Long-Term Gains: Scaling Learning-Rate Warmup Duration Across Training Horizons","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}