{"total":19,"rows":[{"id":"2407.01492","title":"RegMix: Data Mixture as Regression for Language Model Pre-training","created":"2024-07-01","cited_by_count":177,"area":null},{"id":"2507.09404","title":"Scaling Laws for Optimal Data Mixtures","created":"2025-07-12","cited_by_count":52,"area":null},{"id":"2407.17467","title":"CMR Scaling Law: Predicting Critical Mixture Ratios for Continual Pre-training of Language Models","created":"2024-07-24","cited_by_count":23,"area":null},{"id":"2407.20177","title":"AutoScale: Scale-Aware Data Mixing for Pre-Training LLMs","created":"2024-07-29","cited_by_count":22,"area":null},{"id":"2503.12811","title":"A Multi-Power Law for Loss Curve Prediction Across Learning Rate Schedules","created":"2025-03-17","cited_by_count":22,"area":null},{"id":"2510.22037","title":"ATLAS: Adaptive Transfer Scaling Laws for Multilingual Pretraining, Finetuning, and Decoding the Curse of Multilinguality","created":"2025-10-24","cited_by_count":22,"area":null},{"id":"2503.21023","title":"Data Mixture Optimization: A Multi-fidelity Multi-scale Bayesian Framework","created":"2025-03-26","cited_by_count":9,"area":null},{"id":"2601.17858","title":"MergeMix: Optimizing Mid-Training Data Mixtures via Learnable Model Merging","created":"2026-01-25","cited_by_count":7,"area":null},{"id":"2502.00270","title":"DUET: Optimizing Training Data Mixtures via Feedback from Unseen Evaluation Tasks","created":"2025-02-01","cited_by_count":6,"area":null},{"id":"2412.02857","title":"Measuring Fingerprints of Web-filtered Text Datasets and Fingerprint Propagation Through Training","created":"2024-12-03","cited_by_count":5,"area":null},{"id":"2505.00358","title":"R&B: Domain Regrouping and Data Mixture Balancing for Efficient Foundation Model Training","created":"2025-05-01","cited_by_count":3,"area":null},{"id":"2605.30334","title":"Demystifying Data Organization for Enhanced LLM Training","created":"2026-05-28","cited_by_count":3,"area":null},{"id":"2606.07597","title":"Repetition Mismatch: Why Data Mixture Experiments Don't Scale and How to Fix Them","created":"2026-05-29","cited_by_count":2,"area":null},{"id":"2603.08022","title":"Capacity-Aware Mixture Law Enables Efficient LLM Data Optimization","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2608.23922","title":"Data Mixing as Mixture Experiment: Response Surface Methodology and Optimal Design for Large Language Model Pretraining","created":"2026-08-24","cited_by_count":1,"area":null},{"id":"2605.06859","title":"Knowledge Transfer Scaling Laws for 3D Medical Imaging","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2607.27928","title":"Harnessing the Potential of Optimizing Data Mixtures via Bayesian Domain Reweighting","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2609.38011","title":"When do data mixtures improve scaling laws? Insights from high-dimensional regression","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.05126","title":"Selecting Repetition Counts Across Model Scales in Data-Constrained Pretraining","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}