{"total":20,"rows":[{"id":"2601.10684","title":"On the origin of neural scaling laws: from random graphs to natural language","created":"2026-01-15","cited_by_count":14,"area":null},{"id":"2603.18534","title":"Data-efficient pre-training by scaling synthetic megadocs","created":"2026-03-19","cited_by_count":7,"area":null},{"id":"2604.13977","title":"How Can We Synthesize High-Quality Pretraining Data? A Systematic Study of Prompt Design, Generator Model, and Source Data","created":"2026-04-15","cited_by_count":6,"area":null},{"id":"2603.06603","title":"Scale Dependent Data Duplication","created":"2026-02-18","cited_by_count":4,"area":null},{"id":"2604.13076","title":"Alignment midtraining for animals","created":"2026-03-21","cited_by_count":4,"area":null},{"id":"2607.25271","title":"Bridging Compute- and Data-Optimal Pretraining","created":"2026-07-28","cited_by_count":2,"area":null},{"id":"2602.11217","title":"The Magic Correlations: Understanding Knowledge Transfer from Pretraining to Supervised Fine-Tuning","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2609.17699","title":"NeMo Data Designer: An Extensible Framework for Multimodal Synthetic Data Generation","created":"2026-09-15","cited_by_count":1,"area":null},{"id":"2602.11064","title":"Motion Capture is Not the Target Domain: Scaling Synthetic Data for Learning Motion Representations","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2604.12097","title":"Temporal Flattening in LLM-Generated Text: Comparing Human and LLM Writing Trajectories","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2604.28075","title":"Repetition over Diversity: High-Signal Data Filtering for Sample-Efficient German Language Modeling","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.17775","title":"Systematic Evaluation of the Quality of Synthetic Clinical Notes Rephrased by LLMs at Million-Note Scale","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.27399","title":"Short-Term Gain, Long-Term Fragility: AI Labor Substitution and the Erosion of Sustainable Capability","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2607.25681","title":"Cognivia: A Cognitive Behavioral Therapy Copilot for Evidence-Based Mental Healthcare","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.25826","title":"Unfolding Scientific Papers into Multi-Turn Generation Trajectories for Continued Pre-Training","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.33016","title":"Relative Generalization Invariance of LLM Pretraining","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.37891","title":"It's All Training: A Fully Synthetic Single-Stage Recipe for LLMs","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.40295","title":"How Much Is an AI Token Worth? Scaling Laws for Wild AI-Generated Web Text","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.16264","title":"Spectral Considerations on Unsupervised Time-domain EEG Representation Learning with Deep Networks","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.19294","title":"Qwenfant: Train Big Character-level BabyLMs on Concise Parallel Text","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}