{"total":18,"rows":[{"id":"2505.13738","title":"Power Lines: Scaling Laws for Weight Decay and Batch Size in LLM Pre-training","created":"2025-05-19","cited_by_count":43,"area":null},{"id":"2510.06213","title":"Training Dynamics Impact Post-Training Quantization Robustness","created":"2025-10-07","cited_by_count":15,"area":null},{"id":"2603.15958","title":"Deriving Hyperparameter Scaling Laws via Modern Optimization Theory","created":"2026-03-16","cited_by_count":10,"area":null},{"id":"2607.20548","title":"SOAP, Muon, and Beyond: Pushing LLM Pretraining Scales","created":"2026-07-13","cited_by_count":6,"area":null},{"id":"2510.08702","title":"Scaling Laws for Code: A More Data-Hungry Regime","created":"2025-10-09","cited_by_count":3,"area":null},{"id":"2608.07222","title":"Skaling: Chinchilla's Exponents Meet Kaplan's Coupling","created":"2026-08-07","cited_by_count":3,"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":"2608.11859","title":"Small-Scale Experiments: Are We There Yet?","created":"2026-08-12","cited_by_count":2,"area":null},{"id":"2510.04067","title":"What Scales in Cross-Entropy Scaling Law?","created":"2025-10-05","cited_by_count":1,"area":null},{"id":"2605.17000","title":"BoLT: A Benchmark to Democratize Black-box Optimization Research for Expensive LLM Tasks","created":"2026-05-16","cited_by_count":1,"area":null},{"id":"2606.13767","title":"Beyond LoRA: Is Sparsity-Induced Adaptation Better?","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2606.28057","title":"MultiHashFormer: Hash-based Generative Language Models","created":"2026-06-26","cited_by_count":1,"area":null},{"id":"2609.01431","title":"Efficiently Estimating Optimal Hyperparameter Scaling Laws through Power-Law Entropy Search","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2606.05610","title":"Predictable Scaling Laws of Optimal Hyperparameters for LLM Continued Pre-training","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2609.27581","title":"Does Step Law Transfer to Small-Scale Language Models? An Empirical Recalibration Below 59M Parameters","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2610.06784","title":"How to scale your HEP ML models: A recipe for robust architecture comparisons at scale","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.16837","title":"A Scaled-Up Empirical Study of Syntactic Language Models","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}