{"total":24,"rows":[{"id":"2602.07488","title":"Deriving Neural Scaling Laws from the statistics of natural language","created":"2026-02-07","cited_by_count":23,"area":null},{"id":"2510.14751","title":"Beyond Multi-Token Prediction: Pretraining LLMs with Future Summaries","created":"2025-10-16","cited_by_count":15,"area":null},{"id":"2601.21571","title":"Shaping capabilities with token-level data filtering","created":"2026-01-29","cited_by_count":13,"area":null},{"id":"2605.01640","title":"Prescriptive Scaling Laws for Data Constrained Training","created":"2026-05-02","cited_by_count":12,"area":null},{"id":"2605.19407","title":"A Bitter Lesson for Data Filtering","created":"2026-05-19","cited_by_count":8,"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":"2602.01642","title":"The Effect of Mini-Batch Noise on the Implicit Bias of Adam","created":"2026-02-02","cited_by_count":4,"area":null},{"id":"2602.11137","title":"Weight Decay Improves Language Model Plasticity","created":"2026-02-11","cited_by_count":4,"area":null},{"id":"2604.09258","title":"Nexus: Same Pretraining Loss, Better Downstream Generalization via Common Minima","created":"2026-04-10","cited_by_count":4,"area":null},{"id":"2606.16246","title":"Demystifying Training-Time Augmentation for Data-Constrained Language Model Pretraining","created":"2026-06-15","cited_by_count":4,"area":null},{"id":"2607.27372","title":"Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation","created":"2026-07-29","cited_by_count":4,"area":null},{"id":"2512.23340","title":"The Law of Multi-Model Collaboration: Scaling Limits of Model Ensembling for Large Language Models","created":"2025-12-29","cited_by_count":3,"area":null},{"id":"2603.24562","title":"Scaling Recurrence-aware Foundation Models for Clinical Records via Next-Visit Prediction","created":"2026-03-25","cited_by_count":3,"area":null},{"id":"2606.06888","title":"Data-Constrained Language Model Pretraining: Improved Regularization and Scaling Laws","created":"2026-06-05","cited_by_count":3,"area":null},{"id":"2609.19107","title":"How Model Growth, Recursion, and Boundary Operators Influence Scaling Exponents","created":"2026-09-16","cited_by_count":2,"area":null},{"id":"2603.23562","title":"Synthetic Mixed Training: Scaling Parametric Knowledge Acquisition Beyond RAG","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2606.14150","title":"Small LLMs: Pruning vs. Training from Scratch","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2605.08541","title":"Tokens-per-Parameter Coverage Is Critical for Robust LLM Scaling Law Extrapolation","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.13225","title":"Mix, Don't Tune: Bilingual Pre-Training Outperforms Hyperparameter Search in Data-Constrained Settings","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2606.05029","title":"Validity Threats for Foundation Model Research","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2607.05025","title":"Uncertainty-aware damage identification in short-span bridges via physics-informed variational autoencoder","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2610.05591","title":"What Is a Repeated Token Worth? The Scaling Geometry of Multi-Epoch Pretraining","created":"2026-10-04","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},{"id":"2610.20533","title":"Generative Representation Learning for Scalable Latent Tokenization","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}