{"total":15,"rows":[{"id":"2503.04715","title":"Predictable Scale: Part I, Step Law -- Optimal Hyperparameter Scaling Law in Large Language Model Pretraining","created":"2025-03-06","cited_by_count":34,"area":null},{"id":"2509.14026","title":"Quantum Variational Activation Functions Empower Kolmogorov-Arnold Networks","created":"2025-09-17","cited_by_count":10,"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":"2603.15958","title":"Deriving Hyperparameter Scaling Laws via Modern Optimization Theory","created":"2026-03-16","cited_by_count":10,"area":null},{"id":"2506.10911","title":"NoLoCo: No-all-reduce Low Communication Training Method for Large Models","created":"2025-06-12","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":"2510.08702","title":"Scaling Laws for Code: A More Data-Hungry Regime","created":"2025-10-09","cited_by_count":3,"area":null},{"id":"2508.10894","title":"MAESTRO: Masked AutoEncoders for Multimodal, Multitemporal, and Multispectral Earth Observation Data","created":"2025-08-14","cited_by_count":2,"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":"2605.24316","title":"Scaling Laws for Dynamic Mini-Batch SGD in Sketched Linear Regression","created":"2026-05-23","cited_by_count":2,"area":null},{"id":"2607.27731","title":"Towards joint scaling laws with optimal batch size schedules","created":"2026-07-30","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":"2605.24326","title":"ScaleAcross Explorer: Exploring Communication Optimization for Scale-Across AI Model Training","created":"2026-05-23","cited_by_count":0,"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":"2610.15965","title":"Scaling Repeated-Data Pretraining: Batch Size, Regularization, and GPU-Time Tradeoffs","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}