{"total":288,"rows":[{"id":"2411.12372","title":"RedPajama: an Open Dataset for Training Large Language Models","created":"2024-11-19","cited_by_count":182,"area":null},{"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":"2502.20321","title":"UniTok: A Unified Tokenizer for Visual Generation and Understanding","created":"2025-02-27","cited_by_count":153,"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":"2407.13623","title":"Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies","created":"2024-07-18","cited_by_count":118,"area":null},{"id":"2409.15790","title":"Small Language Models: Survey, Measurements, and Insights","created":"2024-09-24","cited_by_count":112,"area":null},{"id":"2409.00088","title":"On-Device Language Models: A Comprehensive Review","created":"2024-08-26","cited_by_count":104,"area":null},{"id":"2411.04330","title":"Scaling Laws for Precision","created":"2024-11-07","cited_by_count":95,"area":null},{"id":"2510.24684","title":"SPICE: Self-Play In Corpus Environments Improves Reasoning","created":"2025-10-28","cited_by_count":83,"area":null},{"id":"2505.02222","title":"Practical Efficiency of Muon for Pretraining","created":"2025-05-04","cited_by_count":80,"area":null},{"id":"2505.01618","title":"Don't be lazy: CompleteP enables compute-efficient deep transformers","created":"2025-05-02","cited_by_count":78,"area":null},{"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":"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":"2412.04332","title":"Liquid: Language Models are Scalable and Unified Multi-modal Generators","created":"2024-12-05","cited_by_count":63,"area":null},{"id":"2503.13423","title":"SuperBPE: Space Travel for Language Models","created":"2025-03-17","cited_by_count":63,"area":null},{"id":"2512.23675","title":"End-to-End Test-Time Training for Long Context","created":"2025-12-29","cited_by_count":62,"area":null},{"id":"2501.17116","title":"Optimizing Large Language Model Training Using FP4 Quantization","created":"2025-01-28","cited_by_count":56,"area":null},{"id":"2410.16713","title":"Collapse or Thrive? Perils and Promises of Synthetic Data in a Self-Generating World","created":"2024-10-22","cited_by_count":52,"area":null},{"id":"2506.07900","title":"MiniCPM4: Ultra-Efficient LLMs on End Devices","created":"2025-06-09","cited_by_count":52,"area":null},{"id":"2507.09404","title":"Scaling Laws for Optimal Data Mixtures","created":"2025-07-12","cited_by_count":52,"area":null},{"id":"2504.07951","title":"Scaling Laws for Native Multimodal Models","created":"2025-04-10","cited_by_count":50,"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":"2409.05816","title":"Improving Pretraining Data Using Perplexity Correlations","created":"2024-09-09","cited_by_count":46,"area":null},{"id":"2509.06888","title":"mmBERT: A Modern Multilingual Encoder with Annealed Language Learning","created":"2025-09-08","cited_by_count":45,"area":null},{"id":"2410.07064","title":"Data Selection via Optimal Control for Language Models","created":"2024-10-09","cited_by_count":38,"area":null},{"id":"2505.05427","title":"Ultra-FineWeb: Efficient Data Filtering and Verification for High-Quality LLM Training Data","created":"2025-05-08","cited_by_count":38,"area":null},{"id":"2507.11412","title":"Seq vs Seq: An Open Suite of Paired Encoders and Decoders","created":"2025-07-15","cited_by_count":38,"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":"2412.04403","title":"Establishing Task Scaling Laws via Compute-Efficient Model Ladders","created":"2024-12-05","cited_by_count":35,"area":null},{"id":"2502.10361","title":"Enhancing Multilingual LLM Pretraining with Model-Based Data Selection","created":"2025-02-14","cited_by_count":35,"area":null},{"id":"2407.07890","title":"Training on the Test Task Confounds Evaluation and Emergence","created":"2024-07-10","cited_by_count":34,"area":null},{"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":"2507.06187","title":"The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains","created":"2025-07-08","cited_by_count":28,"area":null},{"id":"2603.05498","title":"The Spike, the Sparse and the Sink: Anatomy of Massive Activations and Attention Sinks","created":"2026-03-05","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":"2508.13144","title":"Signal and Noise: A Framework for Reducing Uncertainty in Language Model Evaluation","created":"2025-08-18","cited_by_count":26,"area":null},{"id":"2407.21075","title":"Apple Intelligence Foundation Language Models","created":"2024-07-29","cited_by_count":24,"area":null},{"id":"2604.21106","title":"How Much Is One Recurrence Worth? Iso-Depth Scaling Laws for Looped Language Models","created":"2026-04-22","cited_by_count":24,"area":null},{"id":"2408.15045","title":"DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understanding","created":"2024-08-27","cited_by_count":23,"area":null},{"id":"2509.04185","title":"Set Block Decoding is a Language Model Inference Accelerator","created":"2025-09-04","cited_by_count":23,"area":null},{"id":"2512.16676","title":"DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI","created":"2025-12-18","cited_by_count":23,"area":null},{"id":"2501.01956","title":"Metadata Conditioning Accelerates Language Model Pre-training","created":"2025-01-03","cited_by_count":22,"area":null},{"id":"2411.15242","title":"The Zamba2 Suite: Technical Report","created":"2024-11-22","cited_by_count":21,"area":null},{"id":"2503.00808","title":"Predictive Data Selection: The Data That Predicts Is the Data That Teaches","created":"2025-03-02","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":"2602.05400","title":"OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration","created":"2026-02-05","cited_by_count":21,"area":null},{"id":"2410.07461","title":"Is C4 Dataset Optimal for Pruning? An Investigation of Calibration Data for LLM Pruning","created":"2024-10-09","cited_by_count":20,"area":null},{"id":"2412.08467","title":"Bootstrapping Language-Guided Navigation Learning with Self-Refining Data Flywheel","created":"2024-12-11","cited_by_count":20,"area":null},{"id":"2502.06857","title":"Gemstones: A Model Suite for Multi-Faceted Scaling Laws","created":"2025-02-07","cited_by_count":20,"area":null},{"id":"2510.15103","title":"Continual Learning via Sparse Memory Finetuning","created":"2025-10-16","cited_by_count":20,"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":"2411.02780","title":"How much is a noisy image worth? Data Scaling Laws for Ambient Diffusion","created":"2024-11-05","cited_by_count":18,"area":null},{"id":"2502.12982","title":"Sailor2: Sailing in South-East Asia with Inclusive Multilingual LLMs","created":"2025-02-18","cited_by_count":18,"area":null},{"id":"2503.13427","title":"xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference","created":"2025-03-17","cited_by_count":18,"area":null},{"id":"2410.23825","title":"GlotCC: An Open Broad-Coverage CommonCrawl Corpus and Pipeline for Minority Languages","created":"2024-10-31","cited_by_count":16,"area":null},{"id":"2503.21193","title":"UGen: Unified Autoregressive Multimodal Model with Progressive Vocabulary Learning","created":"2025-03-27","cited_by_count":16,"area":null},{"id":"2504.12427","title":"Position: The Most Expensive Part of an LLM should be its Training Data","created":"2025-04-16","cited_by_count":16,"area":null},{"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":"2505.18091","title":"Data Mixing Can Induce Phase Transitions in Knowledge Acquisition","created":"2025-05-23","cited_by_count":16,"area":null},{"id":"2606.16899","title":"Fantastic Pretraining Optimizers and Where to Find Them II: Hyperball Optimization","created":"2026-06-15","cited_by_count":16,"area":null},{"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":"2504.02107","title":"TiC-LM: A Web-Scale Benchmark for Time-Continual LLM Pretraining","created":"2025-04-02","cited_by_count":15,"area":null},{"id":"2506.14761","title":"From Bytes to Ideas: Language Modeling with Autoregressive U-Nets","created":"2025-06-17","cited_by_count":15,"area":null},{"id":"2510.14751","title":"Beyond Multi-Token Prediction: Pretraining LLMs with Future Summaries","created":"2025-10-16","cited_by_count":15,"area":null},{"id":"2510.21450","title":"ParaRNN: Unlocking Parallel Training of Nonlinear RNNs for Large Language Models","created":"2025-10-24","cited_by_count":15,"area":null},{"id":"2510.02375","title":"Pretraining with hierarchical memories: separating long-tail and common knowledge","created":"2025-09-29","cited_by_count":14,"area":null},{"id":"2511.18903","title":"How Learning Rate Decay Wastes Your Best Data in Curriculum-Based LLM Pretraining","created":"2025-11-24","cited_by_count":14,"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":"2503.14376","title":"Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernels","created":"2025-03-18","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":"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":"2508.15706","title":"Overcoming the Communication-Performance Tradeoff in LLM Pretraining","created":"2025-08-21","cited_by_count":12,"area":null},{"id":"2510.14865","title":"Midtraining Bridges Pretraining and Posttraining Distributions","created":"2025-10-16","cited_by_count":12,"area":null},{"id":"2602.21492","title":"GradAlign: Gradient-Aligned Data Selection for LLM Reinforcement Learning","created":"2026-02-25","cited_by_count":12,"area":null},{"id":"2502.10510","title":"MixMin: Finding Data Mixtures via Convex Minimization","created":"2025-02-14","cited_by_count":11,"area":null},{"id":"2511.21016","title":"Gated KalmaNet: A Fading Memory Layer Through Test-Time Ridge Regression","created":"2025-11-26","cited_by_count":11,"area":null},{"id":"2601.21579","title":"KromHC: Manifold-Constrained Hyper-Connections with Kronecker-Product Residual Matrices","created":"2026-01-29","cited_by_count":11,"area":null},{"id":"2407.19474","title":"Visual Riddles: a Commonsense and World Knowledge Challenge for Large Vision and Language Models","created":"2024-07-28","cited_by_count":10,"area":null},{"id":"2410.08102","title":"Efficient Pretraining Data Selection for Language Models via Multi-Actor Collaboration","created":"2024-10-10","cited_by_count":10,"area":null},{"id":"2605.02105","title":"Sharpness-Aware Pretraining Mitigates Catastrophic Forgetting","created":"2026-05-04","cited_by_count":10,"area":null},{"id":"2605.05724","title":"Auto Research with Specialist Agents Develops Effective and Non-Trivial Training Recipes","created":"2026-05-07","cited_by_count":10,"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":"2406.14026","title":"Demystifying Language Model Forgetting with Low-rank Example Associations","created":"2024-06-20","cited_by_count":8,"area":null},{"id":"2503.07879","title":"Datasets, Documents, and Repetitions: The Practicalities of Unequal Data Quality","created":"2025-03-10","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":"2505.18513","title":"Enhancing Training Data Attribution with Representational Optimization","created":"2025-05-24","cited_by_count":8,"area":null},{"id":"2410.13456","title":"Unlocking Legal Knowledge: A Multilingual Dataset for Judicial Summarization in Switzerland","created":"2024-10-17","cited_by_count":7,"area":null},{"id":"2412.17743","title":"YuLan-Mini: An Open Data-efficient Language Model","created":"2024-12-23","cited_by_count":7,"area":null},{"id":"2509.22367","title":"What Is The Political Content in LLMs' Pre- and Post-Training Data?","created":"2025-09-26","cited_by_count":7,"area":null},{"id":"2510.00379","title":"Composer: A Search Framework for Hybrid Neural Architecture Design","created":"2025-10-01","cited_by_count":7,"area":null},{"id":"2510.17802","title":"Unbiased Gradient Low-Rank Projection","created":"2025-10-20","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":"2603.11021","title":"Leech Lattice Vector Quantization for Efficient LLM Compression","created":"2026-03-11","cited_by_count":7,"area":null},{"id":"2605.10468","title":"Can Muon Fine-tune Adam-Pretrained Models?","created":"2026-05-11","cited_by_count":7,"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":"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":"2502.13347","title":"Craw4LLM: Efficient Web Crawling for LLM Pretraining","created":"2025-02-19","cited_by_count":6,"area":null},{"id":"2502.17259","title":"Detecting Benchmark Contamination Through Watermarking","created":"2025-02-24","cited_by_count":6,"area":null}],"next_cursor":"100"}