{"total":84,"rows":[{"id":"2504.11468","title":"SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models","created":"2025-04-10","cited_by_count":212,"area":"lr"},{"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":"2410.15226","title":"On the Diversity of Synthetic Data and its Impact on Training Large Language Models","created":"2024-10-19","cited_by_count":59,"area":"synth"},{"id":"2502.04194","title":"The Best Instruction-Tuning Data are Those That Fit","created":"2025-02-06","cited_by_count":52,"area":null},{"id":"2502.13260","title":"Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models","created":"2025-02-18","cited_by_count":51,"area":"lr"},{"id":"2511.03276","title":"Diffusion Language Models are Super Data Learners","created":"2025-11-05","cited_by_count":48,"area":"diffusion"},{"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":"2502.09650","title":"Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples","created":"2025-02-11","cited_by_count":37,"area":"alignment"},{"id":"2502.10361","title":"Enhancing Multilingual LLM Pretraining with Model-Based Data Selection","created":"2025-02-14","cited_by_count":35,"area":null},{"id":"2503.01807","title":"Large-Scale Data Selection for Instruction Tuning","created":"2025-03-03","cited_by_count":35,"area":null},{"id":"2408.08781","title":"Evaluating the Evaluator: Measuring LLMs' Adherence to Task Evaluation Instructions","created":"2024-08-16","cited_by_count":34,"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":"2412.14689","title":"How to Synthesize Text Data without Model Collapse?","created":"2024-12-19","cited_by_count":25,"area":"synth"},{"id":"2502.00883","title":"SimPER: A Minimalist Approach to Preference Alignment without Hyperparameters","created":"2025-02-02","cited_by_count":25,"area":"alignment"},{"id":"2501.12147","title":"Improving Influence-based Instruction Tuning Data Selection for Balanced Learning of Diverse Capabilities","created":"2025-01-21","cited_by_count":23,"area":null},{"id":"2412.03881","title":"Weak-to-Strong Generalization Through the Data-Centric Lens","created":"2024-12-05","cited_by_count":21,"area":"alignment"},{"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":"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":"2504.14194","title":"Meta-rater: A Multi-dimensional Data Selection Method for Pre-training Language Models","created":"2025-04-19","cited_by_count":19,"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":"2509.01321","title":"Towards High Data Efficiency in Reinforcement Learning with Verifiable Reward","created":"2025-09-01","cited_by_count":19,"area":"lr"},{"id":"2410.18779","title":"A Little Help Goes a Long Way: Efficient LLM Training by Leveraging Small LMs","created":"2024-10-24","cited_by_count":15,"area":null},{"id":"2505.19051","title":"Efficient Data Selection at Scale via Influence Distillation","created":"2025-05-25","cited_by_count":15,"area":null},{"id":"2510.01218","title":"Control the Temperature: Selective Sampling for Diverse and High-Quality LLM Outputs","created":"2025-09-20","cited_by_count":15,"area":null},{"id":"2501.14315","title":"Mitigating Forgetting in LLM Fine-Tuning via Low-Perplexity Token Learning","created":"2025-01-24","cited_by_count":14,"area":"synth"},{"id":"2411.06068","title":"Zyda-2: a 5 Trillion Token High-Quality Dataset","created":"2024-11-09","cited_by_count":13,"area":null},{"id":"2505.17895","title":"DataRater: Meta-Learned Dataset Curation","created":"2025-05-23","cited_by_count":13,"area":null},{"id":"2410.16208","title":"Compute-Constrained Data Selection","created":"2024-10-21","cited_by_count":12,"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":"2412.06293","title":"Mastering Collaborative Multi-modal Data Selection: A Focus on Informativeness, Uniqueness, and Representativeness","created":"2024-12-09","cited_by_count":10,"area":"mllm"},{"id":"2505.21344","title":"The Multilingual Divide and Its Impact on Global AI Safety","created":"2025-05-27","cited_by_count":10,"area":null},{"id":"2510.06108","title":"Influence Functions for Efficient Data Selection in Reasoning","created":"2025-10-07","cited_by_count":10,"area":"lr"},{"id":"2506.11480","title":"LearnAlign: Data Selection for LLM Reinforcement Learning with Improved Gradient Alignment","created":"2025-06-13","cited_by_count":9,"area":"lr"},{"id":"2504.10724","title":"HELIOS: Adaptive Model And Early-Exit Selection for Efficient LLM Inference Serving","created":"2025-04-14","cited_by_count":8,"area":"inference"},{"id":"2602.18584","title":"GIST: Targeted Data Selection for Instruction Tuning via Coupled Optimization Geometry","created":"2026-02-20","cited_by_count":8,"area":null},{"id":"2507.16178","title":"LLM Data Selection and Utilization via Dynamic Bi-level Optimization","created":"2025-07-22","cited_by_count":7,"area":null},{"id":"2510.13890","title":"A Survey on Collaborating Small and Large Language Models for Performance, Cost-effectiveness, Cloud-edge Privacy, and Trustworthiness","created":"2025-10-14","cited_by_count":7,"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":"2410.21526","title":"Not All LLM-Generated Data Are Equal: Rethinking Data Weighting in Text Classification","created":"2024-10-28","cited_by_count":6,"area":"lr"},{"id":"2508.17677","title":"TiKMiX: Take Data Influence into Dynamic Mixture for Language Model Pre-training","created":"2025-08-25","cited_by_count":6,"area":null},{"id":"2505.07293","title":"AttentionInfluence: Adopting Attention Head Influence for Weak-to-Strong Pretraining Data Selection","created":"2025-05-12","cited_by_count":5,"area":"lr"},{"id":"2506.10952","title":"Domain2Vec: Vectorizing Datasets to Find the Optimal Data Mixture without Training","created":"2025-06-12","cited_by_count":5,"area":null},{"id":"2508.11551","title":"ADMIRE-BayesOpt: Accelerated Data MIxture RE-weighting for Language Models with Bayesian Optimization","created":"2025-08-15","cited_by_count":5,"area":null},{"id":"2505.16340","title":"Improving Chemical Understanding of LLMs via SMILES Parsing","created":"2025-05-22","cited_by_count":4,"area":null},{"id":"2505.18458","title":"A Survey of LLM $\\times$ DATA","created":"2025-05-24","cited_by_count":4,"area":"rag"},{"id":"2506.11389","title":"Curriculum-Guided Layer Scaling for Language Model Pretraining","created":"2025-06-13","cited_by_count":4,"area":null},{"id":"2510.05148","title":"Every Step Counts: Decoding Trajectories as Authorship Fingerprints of dLLMs","created":"2025-10-02","cited_by_count":4,"area":"diffusion"},{"id":"2602.03075","title":"ReMiT: RL-Guided Mid-Training for Iterative LLM Evolution","created":"2026-02-03","cited_by_count":4,"area":null},{"id":"2602.14696","title":"A Critical Look at Targeted Instruction Selection: Disentangling What Matters (and What Doesn't)","created":"2026-02-16","cited_by_count":4,"area":null},{"id":"2503.00034","title":"MergeIT: From Selection to Merging for Efficient Instruction Tuning","created":"2025-02-25","cited_by_count":3,"area":null},{"id":"2510.08413","title":"Prompts Generalize with Low Data: Non-vacuous Generalization Bounds for Optimizing Prompts with More Informative Priors","created":"2025-10-09","cited_by_count":3,"area":null},{"id":"2512.13279","title":"AIR: Post-training Data Selection for Reasoning via Attention Head Influence","created":"2025-12-15","cited_by_count":3,"area":"lr"},{"id":"2605.05227","title":"Rethinking Data Curation in LLM Training: Online Reweighting Offers Better Generalization than Offline Methods","created":"2026-04-19","cited_by_count":3,"area":"lr"},{"id":"2605.10129","title":"Synthetic Pre-Pre-Training Improves Language Model Robustness to Noisy Pre-Training Data","created":"2026-05-11","cited_by_count":3,"area":null},{"id":"2506.04981","title":"Better Semi-supervised Learning for Multi-domain ASR Through Incremental Retraining and Data Filtering","created":"2025-06-05","cited_by_count":2,"area":null},{"id":"2606.28551","title":"DataComp-VLM: Improved Open Datasets for Vision-Language Models","created":"2026-06-26","cited_by_count":2,"area":"mllm"},{"id":"2410.07880","title":"Unsupervised Data Validation Methods for Efficient Model Training","created":"2024-10-10","cited_by_count":1,"area":null},{"id":"2505.06699","title":"Model Steering: Learning with a Reference Model Improves Generalization Bounds and Scaling Laws","created":"2025-05-10","cited_by_count":1,"area":null},{"id":"2507.02378","title":"Efficient Code LLM Training via Distribution-Consistent and Diversity-Aware Data Selection","created":"2025-07-03","cited_by_count":1,"area":null},{"id":"2510.03880","title":"Exploring Instruction Data Quality for Explainable Image Quality Assessment","created":"2025-10-04","cited_by_count":1,"area":"mllm"},{"id":"2510.18909","title":"Learning from the Best, Differently: A Diversity-Driven Rethinking on Data Selection","created":"2025-10-21","cited_by_count":1,"area":"lr"},{"id":"2602.11871","title":"DMAP: A Distribution Map for Text","created":"2026-02-12","cited_by_count":1,"area":null},{"id":"2602.14536","title":"Explainable Token-level Noise Filtering for LLM Fine-tuning Datasets","created":"2026-02-16","cited_by_count":1,"area":null},{"id":"2603.18361","title":"Synthetic Data Generation for Training Diversified Commonsense Reasoning Models","created":"2026-03-18","cited_by_count":1,"area":"lr"},{"id":"2604.11810","title":"GRACE: A Dynamic Coreset Selection Framework for Large Language Model Optimization","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2605.28247","title":"IRDS: Interpretable RLVR Data Selection via Verifier-Coupled Sparse Autoencoder Coverage","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2609.19754","title":"AutoData: Agentic Search for Pre-training Data Selection","created":"2026-09-17","cited_by_count":1,"area":"agents"},{"id":"2406.14124","title":"Measuring Sample Importance in Data Pruning for Language Models based on Information Entropy","created":"2024-06-20","cited_by_count":0,"area":null},{"id":"2410.01789","title":"Investigating on RLHF methodology","created":"2024-10-02","cited_by_count":0,"area":"alignment"},{"id":"2506.09329","title":"Towards Efficient and Effective Alignment of Large Language Models","created":"2025-06-11","cited_by_count":0,"area":"alignment"},{"id":"2508.01540","title":"MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning","created":"2025-08-03","cited_by_count":0,"area":"mllm"},{"id":"2509.18577","title":"Prior-based Noisy Text Data Filtering: Fast and Strong Alternative For Perplexity","created":"2025-09-23","cited_by_count":0,"area":null},{"id":"2512.00134","title":"Asm2SrcEval: Evaluating Large Language Models for Assembly-to-Source Code Translation","created":"2025-11-28","cited_by_count":0,"area":null},{"id":"2512.21515","title":"Perplexity-Aware Data Scaling Law: Perplexity Landscapes Predict Performance for Continual Pre-training","created":"2025-12-25","cited_by_count":0,"area":null},{"id":"2601.14091","title":"Zero-shot adaptable task planning for autonomous construction robots: a comparative study of lightweight single and multi-AI agent systems","created":"2026-01-20","cited_by_count":0,"area":"agents"},{"id":"2605.17806","title":"AMO: Operator-level Adaptive Muon Orthogonalization","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2607.18199","title":"PPL-Factory: Task-Aware and Budget-Aware Data Selection from Language Modeling to Reasoning","created":"2026-07-20","cited_by_count":0,"area":"lr"},{"id":"2608.22858","title":"Mapping the Concept Landscape: Structural Perception of Global Distributions for Transparent Data Pruning","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.25826","title":"Unfolding Scientific Papers into Multi-Turn Generation Trajectories for Continued Pre-Training","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.05513","title":"When and What to Teach: Budget-Aware Online Adaptation for Web Agents","created":"2026-08-31","cited_by_count":0,"area":"agents"},{"id":"2609.33405","title":"Decoupling Token Roles in Autoregressive Pretraining","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.34287","title":"ReScraper: Unified Scraping and Cleaning of Web Data for Effective LLM Pretraining","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36535","title":"When Updating Stops Being Learning: Rethinking LLM Self-Evolution via learnable information gain","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.05831","title":"Selecting Long-Horizon Trajectories for Reliable and Efficient Terminal-Agent Training","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}