{"total":32,"rows":[{"id":"2407.01492","title":"RegMix: Data Mixture as Regression for Language Model Pre-training","created":"2024-07-01","cited_by_count":177,"area":null},{"id":"2411.04905","title":"OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models","created":"2024-11-07","cited_by_count":130,"area":null},{"id":"2410.08527","title":"Scaling Laws for Predicting Downstream Performance in LLMs","created":"2024-10-11","cited_by_count":48,"area":null},{"id":"2406.12907","title":"Reconciling Kaplan and Chinchilla Scaling Laws","created":"2024-06-12","cited_by_count":39,"area":null},{"id":"2408.15545","title":"SciLitLLM: How to Adapt LLMs for Scientific Literature Understanding","created":"2024-08-28","cited_by_count":29,"area":null},{"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":"2406.14026","title":"Demystifying Language Model Forgetting with Low-rank Example Associations","created":"2024-06-20","cited_by_count":8,"area":null},{"id":"2412.15270","title":"Baichuan4-Finance Technical Report","created":"2024-12-17","cited_by_count":8,"area":null},{"id":"2407.10804","title":"Mix-CPT: A Domain Adaptation Framework via Decoupling Knowledge Learning and Format Alignment","created":"2024-07-15","cited_by_count":7,"area":null},{"id":"2605.12715","title":"Scaling Laws for Mixture Pretraining Under Data Constraints","created":"2026-05-12","cited_by_count":6,"area":null},{"id":"2502.12051","title":"How to Upscale Neural Networks with Scaling Law? A Survey and Practical Guidelines","created":"2025-02-17","cited_by_count":5,"area":null},{"id":"2505.00985","title":"Position: Enough of Scaling LLMs! Lets Focus on Downscaling","created":"2025-05-02","cited_by_count":5,"area":null},{"id":"2505.07796","title":"Learning Dynamics in Continual Pre-Training for Large Language Models","created":"2025-05-12","cited_by_count":5,"area":null},{"id":"2506.10952","title":"Domain2Vec: Vectorizing Datasets to Find the Optimal Data Mixture without Training","created":"2025-06-12","cited_by_count":5,"area":null},{"id":"2510.10071","title":"ADEPT: Continual Pretraining via Adaptive Expansion and Dynamic Decoupled Tuning","created":"2025-10-11","cited_by_count":5,"area":null},{"id":"2604.22753","title":"Spend Less, Fit Better: Budget-Efficient Scaling Law Fitting via Active Experiment Selection","created":"2026-04-24","cited_by_count":3,"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":"2510.06548","title":"Reusing Overtrained Language Models Saturates Scaling","created":"2025-10-08","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":"2603.19149","title":"Optimal Splitting of Language Models from Mixtures to Specialized Domains","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2608.10850","title":"Diffract: Spectral View of LLM Domain Adaptation","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2409.06624","title":"A Practice of Post-Training on Llama-3 70B with Optimal Selection of Additional Language Mixture Ratio","created":"2024-09-10","cited_by_count":0,"area":null},{"id":"2506.14146","title":"Collaborative Editable Model","created":"2025-06-17","cited_by_count":0,"area":null},{"id":"2510.23198","title":"PTPP-Aware Adaptation Scaling Laws: Predicting Domain-Adaptation Performance at Unseen Pre-Training Budgets","created":"2025-10-27","cited_by_count":0,"area":null},{"id":"2603.19268","title":"Full-Stack Domain Enhancement for Combustion LLMs: Construction and Optimization","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2604.14815","title":"Continued Pretraining of FinBERT on Finnish Histopathological Reports: Train-Time Signals and Proxy Downstream Correlations","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2604.25297","title":"LegalMidm: Use-Case-Driven Legal Domain Specialization for Korean Large Language Model","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2609.14571","title":"Domain-specific Pretraining Profile and Transformer Performance: Evidence from Modeling Digital Pragmatics in Arabic-English Code-switching","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2609.36263","title":"Paired Multimodal Scaling Laws","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.40089","title":"Replay on Demand: An Emergent Curriculum for Balancing Adaptation and Forgetting in Continued Pretraining","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.02593","title":"Fisher-Guided Submodular Data Selection for Continual Pre-Training of Large Language Models","created":"2026-10-01","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}