{"total":72,"rows":[{"id":"2310.06694","title":"Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning","created":"2023-10-10","cited_by_count":415,"area":null},{"id":"2411.12372","title":"RedPajama: an Open Dataset for Training Large Language Models","created":"2024-11-19","cited_by_count":182,"area":null},{"id":"2401.16380","title":"Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling","created":"2024-01-29","cited_by_count":161,"area":null},{"id":"2403.03883","title":"SaulLM-7B: A pioneering Large Language Model for Law","created":"2024-03-06","cited_by_count":142,"area":null},{"id":"2311.14648","title":"Calibrated Language Models Must Hallucinate","created":"2023-11-24","cited_by_count":115,"area":null},{"id":"2411.10915","title":"Bias in Large Language Models: Origin, Evaluation, and Mitigation","created":"2024-11-16","cited_by_count":77,"area":null},{"id":"2406.07545","title":"Open-LLM-Leaderboard: From Multi-choice to Open-style Questions for LLMs Evaluation, Benchmark, and Arena","created":"2024-06-11","cited_by_count":76,"area":null},{"id":"2402.19379","title":"Wisdom of the Silicon Crowd: LLM Ensemble Prediction Capabilities Rival Human Crowd Accuracy","created":"2024-02-29","cited_by_count":67,"area":null},{"id":"2504.13161","title":"Nemotron-CLIMB: CLustering-based Iterative Data Mixture Bootstrapping for Language Model Pre-training","created":"2025-04-17","cited_by_count":66,"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":"2404.10237","title":"Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models","created":"2024-04-16","cited_by_count":46,"area":"mllm"},{"id":"2407.19584","title":"SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domain","created":"2024-07-28","cited_by_count":39,"area":null},{"id":"2407.08699","title":"Mitigating Catastrophic Forgetting in Language Transfer via Model Merging","created":"2024-07-11","cited_by_count":36,"area":null},{"id":"2407.17465","title":"u-$\\mu$P: The Unit-Scaled Maximal Update Parametrization","created":"2024-07-24","cited_by_count":29,"area":null},{"id":"2412.15285","title":"Maximize Your Data's Potential: Enhancing LLM Accuracy with Two-Phase Pretraining","created":"2024-12-18","cited_by_count":26,"area":null},{"id":"2406.14833","title":"Efficient Continual Pre-training by Mitigating the Stability Gap","created":"2024-06-21","cited_by_count":25,"area":null},{"id":"2402.14526","title":"Balanced Data Sampling for Language Model Training with Clustering","created":"2024-02-22","cited_by_count":23,"area":null},{"id":"2402.07862","title":"AI-Augmented Predictions: LLM Assistants Improve Human Forecasting Accuracy","created":"2024-02-12","cited_by_count":21,"area":null},{"id":"2510.06826","title":"Mid-Training of Large Language Models: A Survey","created":"2025-10-08","cited_by_count":21,"area":null},{"id":"2411.11072","title":"Multilingual Large Language Models: A Systematic Survey","created":"2024-11-17","cited_by_count":18,"area":null},{"id":"2312.01700","title":"Data Management For Training Large Language Models: A Survey","created":"2023-12-04","cited_by_count":17,"area":null},{"id":"2411.12892","title":"Selective Attention: Enhancing Transformer through Principled Context Control","created":"2024-11-19","cited_by_count":16,"area":null},{"id":"2509.23184","title":"PonderLM-2: Pretraining LLM with Latent Thoughts in Continuous Space","created":"2025-09-27","cited_by_count":16,"area":"lr"},{"id":"2410.13859","title":"$\\gamma-$MoD: Exploring Mixture-of-Depth Adaptation for Multimodal Large Language Models","created":"2024-10-17","cited_by_count":14,"area":"mllm"},{"id":"2505.24844","title":"Chameleon: A Flexible Data-mixing Framework for Language Model Pretraining and Finetuning","created":"2025-05-30","cited_by_count":14,"area":null},{"id":"2502.03009","title":"Scaling Laws for Upcycling Mixture-of-Experts Language Models","created":"2025-02-05","cited_by_count":13,"area":"moe"},{"id":"2412.13702","title":"Typhoon 2: A Family of Open Text and Multimodal Thai Large Language Models","created":"2024-12-18","cited_by_count":12,"area":"mllm"},{"id":"2601.10825","title":"Reasoning Models Generate Societies of Thought","created":"2026-01-15","cited_by_count":12,"area":"lr"},{"id":"2409.17416","title":"From Deception to Detection: The Dual Roles of Large Language Models in Fake News","created":"2024-09-25","cited_by_count":11,"area":null},{"id":"2410.01485","title":"A Little Goes a Long Way: Efficient Long Context Training and Inference with Partial Contexts","created":"2024-10-02","cited_by_count":9,"area":"inference"},{"id":"2410.01866","title":"House of Cards: Massive Weights in LLMs","created":"2024-10-02","cited_by_count":9,"area":null},{"id":"2410.12455","title":"Loss Landscape Characterization of Neural Networks without Over-Parametrization","created":"2024-10-16","cited_by_count":8,"area":null},{"id":"2505.12942","title":"A3 : an Analytical Low-Rank Approximation Framework for Attention","created":"2025-05-19","cited_by_count":8,"area":"inference"},{"id":"2507.14240","title":"HuggingGraph: Understanding the Supply Chain of LLM Ecosystem","created":"2025-07-17","cited_by_count":8,"area":null},{"id":"2509.17196","title":"Evolution of Concepts in Language Model Pre-Training","created":"2025-09-21","cited_by_count":8,"area":null},{"id":"2505.16066","title":"Merge to Mix: Mixing Datasets via Model Merging","created":"2025-05-21","cited_by_count":7,"area":null},{"id":"2312.14862","title":"YAYI 2: Multilingual Open-Source Large Language Models","created":"2023-12-22","cited_by_count":6,"area":null},{"id":"2405.17234","title":"Benchmarking General-Purpose In-Context Learning","created":"2024-05-27","cited_by_count":6,"area":null},{"id":"2408.15565","title":"SIaM: Self-Improving Code-Assisted Mathematical Reasoning of Large Language Models","created":"2024-08-28","cited_by_count":6,"area":"lr"},{"id":"2507.23632","title":"On the Expressiveness of Softmax Attention: A Recurrent Neural Network Perspective","created":"2025-07-31","cited_by_count":6,"area":null},{"id":"2411.14055","title":"DRPruning: Efficient Large Language Model Pruning through Distributionally Robust Optimization","created":"2024-11-21","cited_by_count":5,"area":null},{"id":"2412.02857","title":"Measuring Fingerprints of Web-filtered Text Datasets and Fingerprint Propagation Through Training","created":"2024-12-03","cited_by_count":5,"area":null},{"id":"2412.06845","title":"7B Fully Open Source Moxin-LLM/VLM -- From Pretraining to GRPO-based Reinforcement Learning Enhancement","created":"2024-12-08","cited_by_count":5,"area":"lr"},{"id":"2507.01785","title":"MuRating: A High Quality Data Selecting Approach to Multilingual Large Language Model Pretraining","created":"2025-07-02","cited_by_count":5,"area":null},{"id":"2507.15640","title":"Data Mixing Agent: Learning to Re-weight Domains for Continual Pre-training","created":"2025-07-21","cited_by_count":5,"area":"agents"},{"id":"2505.18458","title":"A Survey of LLM $\\times$ DATA","created":"2025-05-24","cited_by_count":4,"area":"rag"},{"id":"2602.09003","title":"Data Science and Technology Towards AGI Part I: Tiered Data Management","created":"2026-02-09","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":"2502.19790","title":"Mixtera: A Data Plane for Foundation Model Training","created":"2025-02-27","cited_by_count":3,"area":null},{"id":"2410.05938","title":"EMMA: Empowering Multi-modal Mamba with Structural and Hierarchical Alignment","created":"2024-10-08","cited_by_count":2,"area":"ssm"},{"id":"2505.21598","title":"Rethinking Data Mixture for Large Language Models: A Comprehensive Survey and New Perspectives","created":"2025-05-27","cited_by_count":2,"area":"lr"},{"id":"2510.06548","title":"Reusing Overtrained Language Models Saturates Scaling","created":"2025-10-08","cited_by_count":2,"area":null},{"id":"2510.22926","title":"Simple Denoising Diffusion Language Models","created":"2025-10-27","cited_by_count":2,"area":"diffusion"},{"id":"2602.00747","title":"Decouple Searching from Training: Scaling Data Mixing via Model Merging for Large Language Model Pre-training","created":"2026-01-31","cited_by_count":2,"area":null},{"id":"2602.03784","title":"Fix the Structural Bottleneck: Context Compression via Explicit Information Transmission","created":"2026-02-03","cited_by_count":2,"area":"agents"},{"id":"2410.04454","title":"Inner-Probe: Discovering Copyright-related Data Generation in LLM Architecture","created":"2024-10-06","cited_by_count":1,"area":null},{"id":"2410.11647","title":"Measuring Spiritual Values and Bias of Large Language Models","created":"2024-10-15","cited_by_count":1,"area":null},{"id":"2411.11289","title":"LP Data Pipeline: Lightweight, Purpose-driven Data Pipeline for Large Language Models","created":"2024-11-18","cited_by_count":1,"area":null},{"id":"2502.05765","title":"Privacy-Preserving Dataset Combination","created":"2025-02-09","cited_by_count":1,"area":null},{"id":"2506.23025","title":"Spectra 1.1: Scaling Laws and Efficient Inference for Ternary Language Models","created":"2025-06-28","cited_by_count":1,"area":null},{"id":"2602.10657","title":"Benchmarks Are Not That Out of Distribution: Word Overlap Predicts Performance","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2602.17363","title":"2Mamba2Furious: Linear in Complexity, Competitive in Accuracy","created":"2026-02-19","cited_by_count":1,"area":"ssm"},{"id":"2604.12397","title":"KoCo: Conditioning Language Model Pre-training on Knowledge Coordinates","created":"2026-04-14","cited_by_count":1,"area":null},{"id":"2605.30348","title":"LLMSurgeon: Diagnosing Data Mixture of Large Language Models","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.02559","title":"From Layers to Submodules: Rethinking Granularity in Replacement-Based LLM Compression","created":"2026-06-01","cited_by_count":1,"area":"lr"},{"id":"2405.13386","title":"360Zhinao Technical Report","created":"2024-05-22","cited_by_count":0,"area":null},{"id":"2509.12649","title":"A Systematic Evaluation of Parameter-Efficient Fine-Tuning Methods for the Security of Code LLMs","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2605.15913","title":"Towards Generalization of Block Attention via Automatic Segmentation and Block Distillation","created":"2026-05-15","cited_by_count":0,"area":"rag"},{"id":"2607.22662","title":"CuraWeb: Joint Optimization of Quality, Redundancy, and Diversity for Web-Scale Pretraining Data","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2608.29715","title":"Higher-Dimensional Rotary Position Embedding","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.09081","title":"Everything in Moderation: Per-Domain Coverage Optima and Alignment-Resistant Domain Gaps in Multi-Domain Mid-Training","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.19213","title":"Layer-wise Curriculum Learning for Efficient LLM Compression","created":"2026-09-16","cited_by_count":0,"area":null}],"next_cursor":null}