{"total":63,"rows":[{"id":"2412.02595","title":"Nemotron-CC: Transforming Common Crawl into a Refined Long-Horizon Pretraining Dataset","created":"2024-12-03","cited_by_count":160,"area":null},{"id":"2503.03983","title":"Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities","created":"2025-03-06","cited_by_count":133,"area":"lr"},{"id":"2503.01875","title":"Time-MQA: Time Series Multi-Task Question Answering with Context Enhancement","created":"2025-02-26","cited_by_count":82,"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":"2409.17115","title":"Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale","created":"2024-09-25","cited_by_count":37,"area":null},{"id":"2408.02085","title":"Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Models","created":"2024-08-04","cited_by_count":29,"area":"alignment"},{"id":"2408.15545","title":"SciLitLLM: How to Adapt LLMs for Scientific Literature Understanding","created":"2024-08-28","cited_by_count":29,"area":null},{"id":"2410.17215","title":"MiniPLM: Knowledge Distillation for Pre-Training Language Models","created":"2024-10-22","cited_by_count":29,"area":"distill"},{"id":"2410.17952","title":"SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domains","created":"2024-10-23","cited_by_count":28,"area":"rag"},{"id":"2510.01631","title":"Demystifying Synthetic Data in LLM Pre-training: A Systematic Study of Scaling Laws, Benefits, and Pitfalls","created":"2025-10-02","cited_by_count":26,"area":"synth"},{"id":"2409.12452","title":"Unlocking Reasoning Potential in Large Langauge Models by Scaling Code-form Planning","created":"2024-09-19","cited_by_count":25,"area":"lr"},{"id":"2412.14689","title":"How to Synthesize Text Data without Model Collapse?","created":"2024-12-19","cited_by_count":25,"area":"synth"},{"id":"2510.23081","title":"A Survey on LLM Mid-Training","created":"2025-10-27","cited_by_count":21,"area":null},{"id":"2410.10626","title":"Efficiently Democratizing Medical LLMs for 50 Languages via a Mixture of Language Family Experts","created":"2024-10-14","cited_by_count":17,"area":"moe"},{"id":"2504.16511","title":"QuaDMix: Quality-Diversity Balanced Data Selection for Efficient LLM Pretraining","created":"2025-04-23","cited_by_count":16,"area":null},{"id":"2604.17148","title":"Graph-of-Agents: A Graph-based Framework for Multi-Agent LLM Collaboration","created":"2026-04-18","cited_by_count":16,"area":"agents"},{"id":"2410.01109","title":"Mixing It Up: The Cocktail Effect of Multi-Task Fine-Tuning on LLM Performance -- A Case Study in Finance","created":"2024-10-01","cited_by_count":15,"area":null},{"id":"2411.19930","title":"On Domain-Adaptive Post-Training for Multimodal Large Language Models","created":"2024-11-29","cited_by_count":13,"area":"mllm"},{"id":"2510.14865","title":"Midtraining Bridges Pretraining and Posttraining Distributions","created":"2025-10-16","cited_by_count":12,"area":null},{"id":"2501.14431","title":"Domaino1s: Guiding LLM Reasoning for Explainable Answers in High-Stakes Domains","created":"2025-01-24","cited_by_count":11,"area":"lr"},{"id":"2601.16206","title":"Computer Environments Elicit General Agentic Intelligence in LLMs","created":"2026-01-22","cited_by_count":11,"area":"agents"},{"id":"2507.11405","title":"DCR: Quantifying Data Contamination in LLMs Evaluation","created":"2025-07-15","cited_by_count":10,"area":null},{"id":"2502.13233","title":"SearchRAG: Can Search Engines Be Helpful for LLM-based Medical Question Answering?","created":"2025-02-18","cited_by_count":9,"area":null},{"id":"2410.14745","title":"Semi-supervised Fine-tuning for Large Language Models","created":"2024-10-17","cited_by_count":8,"area":null},{"id":"2507.04391","title":"Does Learning Mathematical Problem-Solving Generalize to Broader Reasoning?","created":"2025-07-06","cited_by_count":7,"area":"lr"},{"id":"2608.17528","title":"Agent Lightning v1.0: Towards Harnessed Agentic RL","created":"2026-08-18","cited_by_count":7,"area":"agents"},{"id":"2411.06824","title":"Combining Domain and Alignment Vectors to Achieve Better Knowledge-Safety Trade-offs in LLMs","created":"2024-11-11","cited_by_count":6,"area":null},{"id":"2502.00329","title":"CoddLLM: Empowering Large Language Models for Data Analytics","created":"2025-02-01","cited_by_count":6,"area":null},{"id":"2603.12658","title":"Beyond Static Models: An Evolving Framework for Continual Learning in Large Language Models across Training Stages","created":"2026-03-13","cited_by_count":6,"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":"2505.18458","title":"A Survey of LLM $\\times$ DATA","created":"2025-05-24","cited_by_count":4,"area":"rag"},{"id":"2601.03448","title":"Enhancing Linguistic Competence of Language Models through Pre-training with Language Learning Tasks","created":"2026-01-06","cited_by_count":4,"area":null},{"id":"2411.00005","title":"Mastering the Craft of Data Synthesis for CodeLLMs","created":"2024-10-16","cited_by_count":3,"area":"synth"},{"id":"2505.24539","title":"Localizing Persona Representations in LLMs","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2508.01326","title":"Large-Scale Diverse Synthesis for Mid-Training","created":"2025-08-02","cited_by_count":3,"area":null},{"id":"2508.15213","title":"Select to Know: An Internal-External Knowledge Self-Selection Framework for Domain-Specific Question Answering","created":"2025-08-21","cited_by_count":3,"area":null},{"id":"2509.07177","title":"Towards EnergyGPT: A Large Language Model Specialized for the Energy Sector","created":"2025-09-08","cited_by_count":3,"area":null},{"id":"2409.00286","title":"OnlySportsLM: Optimizing Sports-Domain Language Models with SOTA Performance under Billion Parameters","created":"2024-08-30","cited_by_count":2,"area":null},{"id":"2507.05750","title":"DocTalk: Scalable Graph-based Dialogue Synthesis for Enhancing LLM Conversational Capabilities","created":"2025-07-08","cited_by_count":2,"area":null},{"id":"2508.01317","title":"LinkQA: Synthesizing Diverse QA from Multiple Seeds Strongly Linked by Knowledge Points","created":"2025-08-02","cited_by_count":2,"area":null},{"id":"2508.06178","title":"Comparing Knowledge Injection Methods for LLMs in a Low-Resource Regime","created":"2025-08-08","cited_by_count":2,"area":null},{"id":"2510.26336","title":"From Amateur to Master: Infusing Knowledge into LLMs via Automated Curriculum Learning","created":"2025-10-30","cited_by_count":2,"area":null},{"id":"2511.02451","title":"Merging Continual Pretraining Models for Domain-Specialized LLMs: A Case Study in Finance","created":"2025-11-04","cited_by_count":2,"area":"lr"},{"id":"2603.02588","title":"ExpGuard: LLM Content Moderation in Specialized Domains","created":"2026-03-03","cited_by_count":2,"area":"safety"},{"id":"2505.16178","title":"Understanding Fact Recall in Language Models: Why Two-Stage Training Encourages Memorization but Mixed Training Teaches Knowledge","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2510.08152","title":"DACIP-RC: Domain Adaptive Continual Instruction Pre-Training via Reading Comprehension on Business Conversations","created":"2025-10-09","cited_by_count":1,"area":null},{"id":"2511.22312","title":"Token-Level Marginalization for Multi-Label LLM Classifiers","created":"2025-11-27","cited_by_count":1,"area":null},{"id":"2603.02041","title":"EstLLM: Enhancing Estonian Capabilities in Multilingual LLMs via Continued Pretraining and Post-Training","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2605.25188","title":"DarkForest: Less Talk, Higher Accuracy for Multi-Agent LLMs","created":"2026-05-24","cited_by_count":1,"area":"lr"},{"id":"2606.28057","title":"MultiHashFormer: Hash-based Generative Language Models","created":"2026-06-26","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":"2510.12115","title":"Tracing Multilingual Knowledge Acquisition Dynamics in Domain Adaptation: A Case Study of English-Japanese Biomedical Adaptation","created":"2025-10-14","cited_by_count":0,"area":null},{"id":"2601.16398","title":"White-Box Sensitivity Auditing with Steering Vectors","created":"2026-01-23","cited_by_count":0,"area":"mechinterp"},{"id":"2601.21280","title":"Token Entropy Regularization for Multi-modal Antenna Affiliation Identification","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2601.22146","title":"FineInstructions: Scaling Synthetic Instructions to Pre-Training Scale","created":"2026-01-29","cited_by_count":0,"area":"synth"},{"id":"2602.04466","title":"Is Micro Domain-Adaptive Pre-Training Effective for Real-World Operations? Multi-Step Evaluation Reveals Potential and Bottlenecks","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2604.17020","title":"Beyond Static Benchmarks: Synthesizing Harmful Content via Persona-based Simulation for Robust Evaluation","created":"2026-04-18","cited_by_count":0,"area":"safety"},{"id":"2606.01849","title":"ContinuousBench: Can Differentially Private Synthetic Text Improve Capabilities?","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2608.11788","title":"TELLME: Test-Enhanced Learning for Language Model Enrichment","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.30609","title":"Reading the News: Adapting Large Language Models to Swedish Journalism Through Continued Pre-Training","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.09116","title":"When Does Scale-Invariant Optimization Become Unstable? An Exact Schedule Law with Weight Decay","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.39702","title":"A helps B while B hurts A: directed transfer in instruction-tuning mixture","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.39827","title":"Synthetic Pre-pretraining Survives Scale, but Not as a Grammatical Prior","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}