{"total":15,"rows":[{"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":"2606.04261","title":"Can Generalist Agents Automate Data Curation?","created":"2026-06-02","cited_by_count":5,"area":null},{"id":"2605.02364","title":"InfoLaw: Information Scaling Laws for Large Language Models with Quality-Weighted Mixture Data and Repetition","created":"2026-05-04","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":"2607.11052","title":"Domain-Aware Scaling Laws Uncover Data Synergy","created":"2026-07-13","cited_by_count":2,"area":null},{"id":"2608.14071","title":"Scaling Domain Data Repetition in LLM Pretraining","created":"2026-08-14","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":"2606.08167","title":"Explaining Data Mixing Scaling Laws","created":"2026-06-06","cited_by_count":1,"area":null},{"id":"2606.14971","title":"FastMix: Fast Data Mixture Optimization via Gradient Descent","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2509.15556","title":"Exploring Polyglot Harmony: On Multilingual Data Allocation for Large Language Models Pretraining","created":"2025-09-19","cited_by_count":0,"area":null},{"id":"2604.17614","title":"Characterizing Model-Native Skills","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2605.29448","title":"How Much Is a Dataset Worth? Scaling Laws, the Vendi Score, and Matrix Spectral Functions","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.24133","title":"Holistic Data Scheduler for LLM Pre-training via Multi-Objective Reinforcement Learning","created":"2026-06-23","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":"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}