{"total":161,"rows":[{"id":"2507.20534","title":"Kimi K2: Open Agentic Intelligence","created":"2025-07-28","cited_by_count":567,"area":"agents"},{"id":"2406.20094","title":"Scaling Synthetic Data Creation with 1,000,000,000 Personas","created":"2024-06-28","cited_by_count":417,"area":"synth"},{"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":"2405.16712","title":"Zamba: A Compact 7B SSM Hybrid Model","created":"2024-05-26","cited_by_count":124,"area":null},{"id":"2412.11664","title":"C3oT: Generating Shorter Chain-of-Thought without Compromising Effectiveness","created":"2024-12-16","cited_by_count":119,"area":"lr"},{"id":"2405.08813","title":"CinePile: A Long Video Question Answering Dataset and Benchmark","created":"2024-05-14","cited_by_count":114,"area":null},{"id":"2404.07503","title":"Best Practices and Lessons Learned on Synthetic Data","created":"2024-04-11","cited_by_count":106,"area":"synth"},{"id":"2406.06046","title":"MATES: Model-Aware Data Selection for Efficient Pretraining with Data Influence Models","created":"2024-06-10","cited_by_count":100,"area":null},{"id":"2402.09668","title":"How to Train Data-Efficient LLMs","created":"2024-02-15","cited_by_count":93,"area":null},{"id":"2506.10943","title":"Self-Adapting Language Models","created":"2025-06-12","cited_by_count":84,"area":null},{"id":"2404.07177","title":"Scaling Laws for Data Filtering -- Data Curation cannot be Compute Agnostic","created":"2024-04-10","cited_by_count":77,"area":"mllm"},{"id":"2502.10341","title":"Organize the Web: Constructing Domains Enhances Pre-Training Data Curation","created":"2025-02-14","cited_by_count":76,"area":null},{"id":"2406.14491","title":"Instruction Pre-Training: Language Models are Supervised Multitask Learners","created":"2024-06-20","cited_by_count":63,"area":null},{"id":"2507.15857","title":"Diffusion Beats Autoregressive in Data-Constrained Settings","created":"2025-07-21","cited_by_count":63,"area":"diffusion"},{"id":"2409.07431","title":"Synthetic continued pretraining","created":"2024-09-11","cited_by_count":60,"area":null},{"id":"2504.02807","title":"MegaMath: Pushing the Limits of Open Math Corpora","created":"2025-04-03","cited_by_count":51,"area":"lr"},{"id":"2403.13799","title":"Reverse Training to Nurse the Reversal Curse","created":"2024-03-20","cited_by_count":49,"area":null},{"id":"2511.03276","title":"Diffusion Language Models are Super Data Learners","created":"2025-11-05","cited_by_count":48,"area":"diffusion"},{"id":"2503.19551","title":"Scaling Laws of Synthetic Data for Language Models","created":"2025-03-25","cited_by_count":46,"area":"synth"},{"id":"2502.12671","title":"Baichuan-M1: Pushing the Medical Capability of Large Language Models","created":"2025-02-18","cited_by_count":43,"area":null},{"id":"2504.16980","title":"Safety Pretraining: Toward the Next Generation of Safe AI","created":"2025-04-23","cited_by_count":43,"area":null},{"id":"2410.12896","title":"A Survey on Data Synthesis and Augmentation for Large Language Models","created":"2024-10-16","cited_by_count":41,"area":"synth"},{"id":"2505.00661","title":"On the generalization of language models from in-context learning and finetuning: a controlled study","created":"2025-05-01","cited_by_count":40,"area":"lr"},{"id":"2505.20161","title":"Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning","created":"2025-05-26","cited_by_count":40,"area":"lr"},{"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":"2412.02980","title":"Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models","created":"2024-12-04","cited_by_count":35,"area":"synth"},{"id":"2507.23751","title":"CoT-Self-Instruct: Building high-quality synthetic prompts for reasoning and non-reasoning tasks","created":"2025-07-31","cited_by_count":32,"area":"lr"},{"id":"2506.04689","title":"Recycling the Web: A Method to Enhance Pre-training Data Quality and Quantity for Language Models","created":"2025-06-05","cited_by_count":31,"area":null},{"id":"2501.00654","title":"ICONS: Influence Consensus for Vision-Language Data Selection","created":"2024-12-31","cited_by_count":29,"area":"mllm"},{"id":"2509.14786","title":"Pre-training under infinite compute","created":"2025-09-18","cited_by_count":29,"area":null},{"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":"2412.14689","title":"How to Synthesize Text Data without Model Collapse?","created":"2024-12-19","cited_by_count":25,"area":"synth"},{"id":"2503.11751","title":"reWordBench: Benchmarking and Improving the Robustness of Reward Models with Transformed Inputs","created":"2025-03-14","cited_by_count":25,"area":"alignment"},{"id":"2410.23933","title":"Language Models can Self-Lengthen to Generate Long Texts","created":"2024-10-31","cited_by_count":24,"area":null},{"id":"2505.02881","title":"Rewriting Pre-Training Data Boosts LLM Performance in Math and Code","created":"2025-05-05","cited_by_count":21,"area":"lr"},{"id":"2508.10975","title":"BeyondWeb: Lessons from Scaling Synthetic Data for Trillion-scale Pretraining","created":"2025-08-14","cited_by_count":21,"area":"synth"},{"id":"2510.23081","title":"A Survey on LLM Mid-Training","created":"2025-10-27","cited_by_count":21,"area":null},{"id":"2507.12466","title":"Language Models Improve When Pretraining Data Matches Target Tasks","created":"2025-07-16","cited_by_count":19,"area":null},{"id":"2410.03735","title":"Task-Adaptive Pretrained Language Models via Clustered-Importance Sampling","created":"2024-09-30","cited_by_count":18,"area":null},{"id":"2502.13252","title":"Multilingual Language Model Pretraining using Machine-translated Data","created":"2025-02-18","cited_by_count":17,"area":null},{"id":"2408.04614","title":"Better Alignment with Instruction Back-and-Forth Translation","created":"2024-08-08","cited_by_count":16,"area":"alignment"},{"id":"2407.18743","title":"Towards Effective and Efficient Continual Pre-training of Large Language Models","created":"2024-07-26","cited_by_count":15,"area":null},{"id":"2409.02098","title":"CRAFT Your Dataset: Task-Specific Synthetic Dataset Generation Through Corpus Retrieval and Augmentation","created":"2024-09-03","cited_by_count":14,"area":"synth"},{"id":"2410.12881","title":"MIND: Math Informed syNthetic Dialogues for Pretraining LLMs","created":"2024-10-15","cited_by_count":14,"area":"lr"},{"id":"2602.11164","title":"Automated Optimization Modeling via a Localizable Error-Driven Perspective","created":"2026-01-17","cited_by_count":14,"area":null},{"id":"2406.12397","title":"Unveiling the Flaws: Exploring Imperfections in Synthetic Data and Mitigation Strategies for Large Language Models","created":"2024-06-18","cited_by_count":13,"area":"synth"},{"id":"2410.17170","title":"Self-calibration for Language Model Quantization and Pruning","created":"2024-10-22","cited_by_count":13,"area":null},{"id":"2411.06068","title":"Zyda-2: a 5 Trillion Token High-Quality Dataset","created":"2024-11-09","cited_by_count":13,"area":null},{"id":"2502.14709","title":"Group-Level Data Selection for Efficient Pretraining","created":"2025-02-20","cited_by_count":13,"area":null},{"id":"2508.09494","title":"Learning Facts at Scale with Active Reading","created":"2025-08-13","cited_by_count":13,"area":null},{"id":"2510.12225","title":"HoneyBee: Data Recipes for Vision-Language Reasoners","created":"2025-10-14","cited_by_count":13,"area":"lr"},{"id":"2410.03083","title":"Scaling Parameter-Constrained Language Models with Quality Data","created":"2024-10-04","cited_by_count":12,"area":null},{"id":"2504.05571","title":"Knowledge-Instruct: Effective Continual Pre-training from Limited Data using Instructions","created":"2025-04-08","cited_by_count":12,"area":null},{"id":"2407.06380","title":"Data, Data Everywhere: A Guide for Pretraining Dataset Construction","created":"2024-07-08","cited_by_count":11,"area":null},{"id":"2502.04235","title":"Reformulation for Pretraining Data Augmentation","created":"2025-02-06","cited_by_count":10,"area":null},{"id":"2508.02853","title":"Modeling Annotator Disagreement with Demographic-Aware Experts and Synthetic Perspectives","created":"2025-08-04","cited_by_count":10,"area":"moe"},{"id":"2410.20796","title":"Rephrasing natural text data with different languages and quality levels for Large Language Model pre-training","created":"2024-10-28","cited_by_count":8,"area":null},{"id":"2410.22211","title":"ProMQA: Question Answering Dataset for Multimodal Procedural Activity Understanding","created":"2024-10-29","cited_by_count":8,"area":null},{"id":"2505.20416","title":"GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation","created":"2025-05-26","cited_by_count":8,"area":"synth"},{"id":"2602.12413","title":"Soft Contamination Means Benchmarks Test Shallow Generalization","created":"2026-02-12","cited_by_count":8,"area":null},{"id":"2412.03253","title":"Alignment at Pre-training! Towards Native Alignment for Arabic LLMs","created":"2024-12-04","cited_by_count":7,"area":"alignment"},{"id":"2412.07030","title":"FM2DS: Few-Shot Multimodal Multihop Data Synthesis with Knowledge Distillation for Question Answering","created":"2024-12-09","cited_by_count":7,"area":"synth"},{"id":"2503.17195","title":"TreeSynth: Synthesizing Diverse Data from Scratch via Tree-Guided Subspace Partitioning","created":"2025-03-21","cited_by_count":7,"area":null},{"id":"2601.07087","title":"When Should We Introduce Safety Interventions During Pretraining?","created":"2026-01-11","cited_by_count":7,"area":"safety"},{"id":"2602.07824","title":"Data Darwinism Part I: Unlocking the Value of Scientific Data for Pre-training","created":"2026-02-08","cited_by_count":7,"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":"2408.15079","title":"BaichuanSEED: Sharing the Potential of ExtensivE Data Collection and Deduplication by Introducing a Competitive Large Language Model Baseline","created":"2024-08-27","cited_by_count":6,"area":null},{"id":"2410.04275","title":"Language Model-Driven Data Pruning Enables Efficient Active Learning","created":"2024-10-05","cited_by_count":6,"area":null},{"id":"2410.05639","title":"DecorateLM: Data Engineering through Corpus Rating, Tagging, and Editing with Language Models","created":"2024-10-08","cited_by_count":6,"area":null},{"id":"2411.12986","title":"Training Bilingual LMs with Data Constraints in the Targeted Language","created":"2024-11-20","cited_by_count":6,"area":null},{"id":"2501.07314","title":"FinerWeb-10BT: Refining Web Data with LLM-Based Line-Level Filtering","created":"2025-01-13","cited_by_count":6,"area":null},{"id":"2502.14644","title":"LIFT: A Novel Framework for Enhancing Long-Context Understanding of LLMs via Long Input Fine-Tuning","created":"2025-02-20","cited_by_count":6,"area":null},{"id":"2505.00022","title":"Aleph-Alpha-GermanWeb: Improving German-language LLM pre-training with model-based data curation and synthetic data generation","created":"2025-04-24","cited_by_count":6,"area":"synth"},{"id":"2509.08653","title":"Generative Data Refinement: Just Ask for Better Data","created":"2025-09-10","cited_by_count":6,"area":null},{"id":"2510.10681","title":"RePro: Training Language Models to Faithfully Recycle the Web for Pretraining","created":"2025-10-12","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":"2605.12715","title":"Scaling Laws for Mixture Pretraining Under Data Constraints","created":"2026-05-12","cited_by_count":6,"area":null},{"id":"2405.13010","title":"UCCIX: Irish-eXcellence Large Language Model","created":"2024-05-13","cited_by_count":5,"area":null},{"id":"2406.04638","title":"Large Language Model-guided Document Selection","created":"2024-06-07","cited_by_count":5,"area":null},{"id":"2410.23956","title":"Multilingual Pretraining Using a Large Corpus Machine-Translated from a Single Source Language","created":"2024-10-31","cited_by_count":5,"area":null},{"id":"2503.15815","title":"Attention Pruning: Automated Fairness Repair of Language Models via Surrogate Simulated Annealing","created":"2025-03-20","cited_by_count":5,"area":null},{"id":"2510.00962","title":"Analyzing Dialectical Biases in LLMs for Knowledge and Reasoning Benchmarks","created":"2025-10-01","cited_by_count":5,"area":"lr"},{"id":"2606.04261","title":"Can Generalist Agents Automate Data Curation?","created":"2026-06-02","cited_by_count":5,"area":null},{"id":"2503.19123","title":"Overcoming Vocabulary Mismatch: Vocabulary-agnostic Teacher Guided Language Modeling","created":"2025-03-24","cited_by_count":4,"area":null},{"id":"2504.00019","title":"ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation Grounding","created":"2025-03-27","cited_by_count":4,"area":null},{"id":"2505.00979","title":"Synthesize-on-Graph: Knowledgeable Synthetic Data Generation for Continue Pre-training of Large Language Models","created":"2025-05-02","cited_by_count":4,"area":"synth"},{"id":"2505.18458","title":"A Survey of LLM $\\times$ DATA","created":"2025-05-24","cited_by_count":4,"area":"rag"},{"id":"2506.00469","title":"Massively Multilingual Adaptation of Large Language Models Using Bilingual Translation Data","created":"2025-05-31","cited_by_count":4,"area":null},{"id":"2511.11966","title":"On the Entropy Calibration of Language Models","created":"2025-11-15","cited_by_count":4,"area":null},{"id":"2606.24998","title":"Internal Data Repetition Destroys Language Models","created":"2026-06-23","cited_by_count":4,"area":null},{"id":"2404.10555","title":"Construction of Domain-specified Japanese Large Language Model for Finance through Continual Pre-training","created":"2024-04-16","cited_by_count":3,"area":null},{"id":"2406.01981","title":"Zyda: A 1.3T Dataset for Open Language Modeling","created":"2024-06-04","cited_by_count":3,"area":null},{"id":"2409.19854","title":"The Construction of Instruction-tuned LLMs for Finance without Instruction Data Using Continual Pretraining and Model Merging","created":"2024-09-30","cited_by_count":3,"area":null},{"id":"2411.00686","title":"Latent Paraphrasing: Perturbation on Layers Improves Knowledge Injection in Language Models","created":"2024-11-01","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":"2509.25531","title":"MixtureVitae: Open Web-Scale Pretraining Dataset With High Quality Instruction and Reasoning Data Built from Permissive-First Text Sources","created":"2025-09-29","cited_by_count":3,"area":"lr"},{"id":"2510.06048","title":"BLISS: A Lightweight Bilevel Influence Scoring Method for Data Selection in Language Model Pretraining","created":"2025-10-07","cited_by_count":3,"area":null},{"id":"2510.18908","title":"Improving Topic Modeling of Social Media Short Texts with Rephrasing: A Case Study of COVID-19 Related Tweets","created":"2025-10-21","cited_by_count":3,"area":null},{"id":"2510.20860","title":"Data-Centric Lessons To Improve Speech-Language Pretraining","created":"2025-10-22","cited_by_count":3,"area":null},{"id":"2601.09966","title":"A Sustainable AI Economy Needs Data Deals That Work for Generators","created":"2026-01-15","cited_by_count":3,"area":null}],"next_cursor":"100"}