{"total":32,"rows":[{"id":"2404.07965","title":"Rho-1: Not All Tokens Are What You Need","created":"2024-04-11","cited_by_count":133,"area":null},{"id":"2403.08540","title":"Language models scale reliably with over-training and on downstream tasks","created":"2024-03-13","cited_by_count":113,"area":null},{"id":"2411.04330","title":"Scaling Laws for Precision","created":"2024-11-07","cited_by_count":95,"area":null},{"id":"2412.13337","title":"Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMs","created":"2024-12-17","cited_by_count":40,"area":null},{"id":"2412.04403","title":"Establishing Task Scaling Laws via Compute-Efficient Model Ladders","created":"2024-12-05","cited_by_count":35,"area":null},{"id":"2410.12360","title":"Towards Neural Scaling Laws for Time Series Foundation Models","created":"2024-10-16","cited_by_count":33,"area":null},{"id":"2507.11783","title":"EEG Foundation Models: A Critical Review of Current Progress and Future Directions","created":"2025-07-15","cited_by_count":32,"area":null},{"id":"2410.11840","title":"A Hitchhiker's Guide to Scaling Law Estimation","created":"2024-10-15","cited_by_count":27,"area":null},{"id":"2403.02419","title":"Are More LLM Calls All You Need? Towards Scaling Laws of Compound Inference Systems","created":"2024-03-04","cited_by_count":25,"area":null},{"id":"2403.06563","title":"Unraveling the Mystery of Scaling Laws: Part I","created":"2024-03-11","cited_by_count":24,"area":null},{"id":"2410.01769","title":"Quantifying Generalization Complexity for Large Language Models","created":"2024-10-02","cited_by_count":18,"area":null},{"id":"2410.01671","title":"Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understanding","created":"2024-10-02","cited_by_count":16,"area":null},{"id":"2411.12925","title":"Loss-to-Loss Prediction: Scaling Laws for All Datasets","created":"2024-11-19","cited_by_count":15,"area":null},{"id":"2505.03793","title":"LENSLLM: Unveiling Fine-Tuning Dynamics for LLM Selection","created":"2025-05-01","cited_by_count":14,"area":null},{"id":"2411.05712","title":"Scaling Laws for Task-Optimized Models of the Primate Visual Ventral Stream","created":"2024-11-08","cited_by_count":13,"area":null},{"id":"2410.16208","title":"Compute-Constrained Data Selection","created":"2024-10-21","cited_by_count":12,"area":null},{"id":"2406.14508","title":"Evidence of a log scaling law for political persuasion with large language models","created":"2024-06-20","cited_by_count":11,"area":null},{"id":"2411.16035","title":"Predicting Emergent Capabilities by Finetuning","created":"2024-11-25","cited_by_count":10,"area":null},{"id":"2604.08510","title":"What do Language Models Learn and When? The Implicit Curriculum Hypothesis","created":"2026-04-09","cited_by_count":10,"area":null},{"id":"2506.10972","title":"Predictable Scale: Part II, Farseer: A Refined Scaling Law in Large Language Models","created":"2025-06-12","cited_by_count":6,"area":null},{"id":"2407.12869","title":"Bilingual Adaptation of Monolingual Foundation Models","created":"2024-07-13","cited_by_count":5,"area":null},{"id":"2411.13322","title":"Scaling Laws for Online Advertisement Retrieval","created":"2024-11-20","cited_by_count":3,"area":null},{"id":"2508.04755","title":"Are Large Language Models Dynamic Treatment Planners? An In Silico Study from a Prior Knowledge Injection Angle","created":"2025-08-06","cited_by_count":1,"area":null},{"id":"2509.12679","title":"Large Language Model Scaling Laws for Neural Quantum States in Quantum Chemistry","created":"2025-09-16","cited_by_count":1,"area":null},{"id":"2605.17340","title":"Olivia: Harmonizing Time Series Foundation Models with Power Spectral Density","created":"2026-05-17","cited_by_count":1,"area":null},{"id":"2605.28179","title":"SuperValid: Capability-Aligned OOD Validation for Generalizable Downstream Scaling","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2501.09631","title":"Empowering Large Language Models in Wireless Communication: A Novel Dataset and Fine-Tuning Framework","created":"2025-01-16","cited_by_count":0,"area":null},{"id":"2510.10948","title":"Unify Variables in Neural Scaling Laws for General Audio Representations via Embedding Effective Rank","created":"2025-10-13","cited_by_count":0,"area":null},{"id":"2602.15253","title":"Scaling Laws for Masked-Reconstruction Transformers on Single-Cell Transcriptomics","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2606.12117","title":"Soft-Prompt Tuning for Fair and Efficient LLM Benchmark Evaluation","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2606.17649","title":"A Risk Decomposition Framework for Pre-Hoc Fine-Tuning Prediction","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2609.16262","title":"Compute-Optimal Pretrain--Fine-tune in Ridge Gradient Descent","created":"2026-09-14","cited_by_count":0,"area":null}],"next_cursor":null}