{"total":75,"rows":[{"id":"2405.09673","title":"LoRA Learns Less and Forgets Less","created":"2024-05-15","cited_by_count":328,"area":null},{"id":"2410.02660","title":"How to Train Long-Context Language Models (Effectively)","created":"2024-10-03","cited_by_count":146,"area":null},{"id":"2405.04324","title":"Granite Code Models: A Family of Open Foundation Models for Code Intelligence","created":"2024-05-07","cited_by_count":117,"area":null},{"id":"2403.17919","title":"LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning","created":"2024-03-26","cited_by_count":89,"area":null},{"id":"2312.17120","title":"MathPile: A Billion-Token-Scale Pretraining Corpus for Math","created":"2023-12-28","cited_by_count":67,"area":null},{"id":"2404.09939","title":"A Survey on Deep Learning for Theorem Proving","created":"2024-04-15","cited_by_count":57,"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":"2409.16986","title":"Harnessing Diversity for Important Data Selection in Pretraining Large Language Models","created":"2024-09-25","cited_by_count":34,"area":null},{"id":"2402.07625","title":"Autonomous Data Selection with Zero-shot Generative Classifiers for Mathematical Texts","created":"2024-02-12","cited_by_count":27,"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":"2312.07622","title":"Mathematical Language Models: A Survey","created":"2023-12-12","cited_by_count":24,"area":null},{"id":"2403.03894","title":"IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generators","created":"2024-03-06","cited_by_count":23,"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":"2501.12766","title":"NExtLong: Toward Effective Long-Context Training without Long Documents","created":"2025-01-22","cited_by_count":20,"area":null},{"id":"2402.11111","title":"Language Models as Science Tutors","created":"2024-02-16","cited_by_count":17,"area":null},{"id":"2505.18091","title":"Data Mixing Can Induce Phase Transitions in Knowledge Acquisition","created":"2025-05-23","cited_by_count":16,"area":null},{"id":"2511.03108","title":"miniF2F-Lean Revisited: Reviewing Limitations and Charting a Path Forward","created":"2025-11-05","cited_by_count":14,"area":null},{"id":"2401.14624","title":"Unearthing Large Scale Domain-Specific Knowledge from Public Corpora","created":"2024-01-26","cited_by_count":12,"area":null},{"id":"2411.14318","title":"Velocitune: A Velocity-based Dynamic Domain Reweighting Method for Continual Pre-training","created":"2024-11-21","cited_by_count":12,"area":null},{"id":"2406.16746","title":"The Responsible Foundation Model Development Cheatsheet: A Review of Tools & Resources","created":"2024-06-24","cited_by_count":11,"area":null},{"id":"2311.15786","title":"YUAN 2.0: A Large Language Model with Localized Filtering-based Attention","created":"2023-11-27","cited_by_count":9,"area":null},{"id":"2502.04223","title":"\\'Eclair -- Extracting Content and Layout with Integrated Reading Order for Documents","created":"2025-02-06","cited_by_count":9,"area":null},{"id":"2506.12044","title":"Why Do Some Inputs Break Low-Bit LLM Quantization?","created":"2025-05-24","cited_by_count":9,"area":null},{"id":"2510.25771","title":"Gaperon: A Peppered English-French Generative Language Model Suite","created":"2025-10-29","cited_by_count":9,"area":null},{"id":"2404.10630","title":"HLAT: High-quality Large Language Model Pre-trained on AWS Trainium","created":"2024-04-16","cited_by_count":8,"area":null},{"id":"2504.06536","title":"Lugha-Llama: Adapting Large Language Models for African Languages","created":"2025-04-09","cited_by_count":8,"area":null},{"id":"2407.05134","title":"Solving for X and Beyond: Can Large Language Models Solve Complex Math Problems with More-Than-Two Unknowns?","created":"2024-07-06","cited_by_count":7,"area":null},{"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":"2602.20816","title":"Don't Ignore the Tail: Decoupling top-K Probabilities for Efficient Language Model Distillation","created":"2026-02-24","cited_by_count":7,"area":null},{"id":"2406.16694","title":"Task Oriented In-Domain Data Augmentation","created":"2024-06-24","cited_by_count":6,"area":null},{"id":"2411.18104","title":"Training and Evaluating Language Models with Template-based Data Generation","created":"2024-11-27","cited_by_count":6,"area":null},{"id":"2411.18872","title":"A Lean Dataset for International Math Olympiad: Small Steps towards Writing Math Proofs for Hard Problems","created":"2024-11-28","cited_by_count":6,"area":null},{"id":"2412.03398","title":"RedStone: Curating General, Code, Math, and QA Data for Large Language Models","created":"2024-12-04","cited_by_count":6,"area":null},{"id":"2502.00075","title":"BTS: Harmonizing Specialized Experts into a Generalist LLM","created":"2025-01-31","cited_by_count":6,"area":null},{"id":"2505.13406","title":"AutoMathKG: The automated mathematical knowledge graph based on LLM and vector database","created":"2025-05-19","cited_by_count":6,"area":null},{"id":"2508.00109","title":"FACTORY: A Challenging Human-Verified Prompt Set for Long-Form Factuality","created":"2025-07-31","cited_by_count":6,"area":null},{"id":"2512.08819","title":"Do Depth-Grown Models Overcome the Curse of Depth? An In-Depth Analysis","created":"2025-12-09","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":"2510.10071","title":"ADEPT: Continual Pretraining via Adaptive Expansion and Dynamic Decoupled Tuning","created":"2025-10-11","cited_by_count":5,"area":null},{"id":"2503.09032","title":"Teaching LLMs How to Learn with Contextual Fine-Tuning","created":"2025-03-12","cited_by_count":4,"area":null},{"id":"2503.14917","title":"MASS: Mathematical Data Selection via Skill Graphs for Pretraining Large Language Models","created":"2025-03-19","cited_by_count":4,"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":"2510.16713","title":"so much depends / upon / a whitespace: Why Whitespace Matters for Poets and LLMs","created":"2025-10-19","cited_by_count":4,"area":null},{"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":"2605.10544","title":"Where Does Long-Context Supervision Actually Go? Effective-Context Exposure Balancing","created":"2026-05-11","cited_by_count":4,"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":"2411.05281","title":"Fox-1: Open Small Language Model for Cloud and Edge","created":"2024-11-08","cited_by_count":3,"area":null},{"id":"2504.16760","title":"Lightweight Latent Verifiers for Efficient Meta-Generation Strategies","created":"2025-04-23","cited_by_count":3,"area":null},{"id":"2602.20433","title":"Disentangling Geometry, Performance, and Training in Language Models","created":"2026-02-24","cited_by_count":3,"area":null},{"id":"2607.09657","title":"Scalable Visual Pretraining for Language Intelligence","created":"2026-07-10","cited_by_count":3,"area":null},{"id":"2411.00863","title":"Next-Token Prediction Task Assumes Optimal Data Ordering for LLM Training in Proof Generation","created":"2024-10-30","cited_by_count":2,"area":null},{"id":"2510.06548","title":"Reusing Overtrained Language Models Saturates Scaling","created":"2025-10-08","cited_by_count":2,"area":null},{"id":"2512.07612","title":"PCMind-2.1-Kaiyuan-2B Technical Report","created":"2025-12-08","cited_by_count":2,"area":null},{"id":"2606.18650","title":"BLADE: Scalable Bi-level Adaptive Data Selection for LLM Training","created":"2026-06-17","cited_by_count":2,"area":null},{"id":"2608.14071","title":"Scaling Domain Data Repetition in LLM Pretraining","created":"2026-08-14","cited_by_count":2,"area":null},{"id":"2410.07825","title":"Extracting and Combining Abilities For Building Multi-lingual Ability-enhanced Large Language Models","created":"2024-10-10","cited_by_count":1,"area":null},{"id":"2502.00340","title":"Unlocking Full Efficiency of Token Filtering in Large Language Model Training","created":"2025-02-01","cited_by_count":1,"area":null},{"id":"2508.01245","title":"WarriorMath: Enhancing the Mathematical Ability of Large Language Models with a Defect-aware Framework","created":"2025-08-02","cited_by_count":1,"area":null},{"id":"2508.03542","title":"Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations and Sentences","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2607.24717","title":"DataOrchestra: Learning to Orchestrate Per-Example Curation of Pretraining Data","created":"2026-07-27","cited_by_count":1,"area":null},{"id":"2608.27370","title":"Puro-2B: Poor Lab's Qwen2-1.5B Trained on RTX 5090 within $5090","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2609.17380","title":"OPEN-1B: A Fully Auditable Training Run","created":"2026-09-15","cited_by_count":1,"area":null},{"id":"2609.31291","title":"Softmax Reparameterization for Output-Head Quantization","created":"2026-09-25","cited_by_count":1,"area":null},{"id":"2406.11410","title":"HARE: HumAn pRiors, a key to small language model Efficiency","created":"2024-06-17","cited_by_count":0,"area":null},{"id":"2502.12928","title":"Finedeep: Mitigating Sparse Activation in Dense LLMs via Multi-Layer Fine-Grained Experts","created":"2025-02-18","cited_by_count":0,"area":null},{"id":"2504.17449","title":"HMI: Hierarchical Knowledge Management for Efficient Multi-Tenant Inference in Pretrained Language Models","created":"2025-04-24","cited_by_count":0,"area":null},{"id":"2505.17919","title":"KITINet: KInetic Theory Inspired Inter-Channel Information Exchange for Residual Networks","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2603.02873","title":".tmu: A Low-Entropy Tree-Structured Representation for LLM-Assisted Scientific Writing","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2605.15053","title":"TFGN: Task-Free, Replay-Free Continual Pre-Training Without Catastrophic Forgetting at LLM Scale","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2606.05610","title":"Predictable Scaling Laws of Optimal Hyperparameters for LLM Continued Pre-training","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2607.25063","title":"Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2609.05766","title":"Data Scout: Targeted Web Crawling for Domain-Specific Pretraining Corpora","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.38446","title":"What Pretraining and Midtraining Make Learnable from Rewards?","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.06636","title":"Differentially Private Mixing of Public Datasets Improves Private Learning","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.11790","title":"Easy to anticipate, hard to compute: boundary dependence finds the computed outputs that entropy patching misses","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}