{"total":16,"rows":[{"id":"2409.15790","title":"Small Language Models: Survey, Measurements, and Insights","created":"2024-09-24","cited_by_count":112,"area":null},{"id":"2503.09543","title":"PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs","created":"2025-03-12","cited_by_count":35,"area":null},{"id":"2406.04327","title":"Causal Estimation of Memorisation Profiles","created":"2024-06-06","cited_by_count":20,"area":null},{"id":"2510.24966","title":"Sequences of Logits Reveal the Low Rank Structure of Language Models","created":"2025-10-28","cited_by_count":9,"area":null},{"id":"2603.10145","title":"Lost in Backpropagation: The LM Head is a Gradient Bottleneck","created":"2026-03-10","cited_by_count":9,"area":null},{"id":"2410.11451","title":"Tending Towards Stability: Convergence Challenges in Small Language Models","created":"2024-10-15","cited_by_count":7,"area":null},{"id":"2601.21698","title":"Curriculum Learning for LLM Pretraining: An Analysis of Learning Dynamics","created":"2026-01-29","cited_by_count":6,"area":null},{"id":"2509.24012","title":"Pretraining Scaling Laws for Generative Evaluations of Language Models","created":"2025-09-28","cited_by_count":5,"area":null},{"id":"2508.02189","title":"Learning Dynamics of Meta-Learning in Small Model Pretraining","created":"2025-08-04","cited_by_count":3,"area":null},{"id":"2602.20433","title":"Disentangling Geometry, Performance, and Training in Language Models","created":"2026-02-24","cited_by_count":3,"area":null},{"id":"2409.11253","title":"Norm of Mean Contextualized Embeddings Determines their Variance","created":"2024-09-17","cited_by_count":1,"area":null},{"id":"2410.07880","title":"Unsupervised Data Validation Methods for Efficient Model Training","created":"2024-10-10","cited_by_count":1,"area":null},{"id":"2509.12960","title":"Investigating ReLoRA: Effects on the Learning Dynamics of Small Language Models","created":"2025-09-16","cited_by_count":1,"area":null},{"id":"2507.22250","title":"Using Scaling Laws for Data Source Utility Estimation in Domain-Specific Pre-Training","created":"2025-07-29","cited_by_count":0,"area":null},{"id":"2608.23358","title":"The Geometry of Low-Resource Language Representations","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2610.19247","title":"Copy-Paste Language Models","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}