{"total":90,"rows":[{"id":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532,"area":null},{"id":"2403.16952","title":"Data Mixing Laws: Optimizing Data Mixtures by Predicting Language Modeling Performance","created":"2024-03-25","cited_by_count":184,"area":null},{"id":"2407.01492","title":"RegMix: Data Mixture as Regression for Language Model Pre-training","created":"2024-07-01","cited_by_count":177,"area":null},{"id":"2404.07965","title":"Rho-1: Not All Tokens Are What You Need","created":"2024-04-11","cited_by_count":133,"area":null},{"id":"2401.12926","title":"DsDm: Model-Aware Dataset Selection with Datamodels","created":"2024-01-23","cited_by_count":105,"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":"2310.17567","title":"Skill-Mix: a Flexible and Expandable Family of Evaluations for AI models","created":"2023-10-26","cited_by_count":64,"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":"2410.11820","title":"Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws","created":"2024-10-15","cited_by_count":47,"area":null},{"id":"2407.00211","title":"Detection and Measurement of Syntactic Templates in Generated Text","created":"2024-06-28","cited_by_count":44,"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":"2402.16705","title":"SelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-Reflection","created":"2024-02-26","cited_by_count":34,"area":null},{"id":"2411.05735","title":"Aioli: A Unified Optimization Framework for Language Model Data Mixing","created":"2024-11-08","cited_by_count":34,"area":null},{"id":"2311.11483","title":"A Multi-Center Study on the Adaptability of a Shared Foundation Model for Electronic Health Records","created":"2023-11-20","cited_by_count":31,"area":null},{"id":"2506.11300","title":"Beyond Random Sampling: Efficient Language Model Pretraining via Curriculum Learning","created":"2025-06-12","cited_by_count":26,"area":null},{"id":"2407.20177","title":"AutoScale: Scale-Aware Data Mixing for Pre-Training LLMs","created":"2024-07-29","cited_by_count":22,"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":"2502.06733","title":"Dynamic Loss-Based Sample Reweighting for Improved Large Language Model Pretraining","created":"2025-02-10","cited_by_count":16,"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":"2506.15872","title":"Hidden Breakthroughs in Language Model Training","created":"2025-06-18","cited_by_count":15,"area":null},{"id":"2409.07045","title":"Beyond IID: Optimizing Instruction Learning from the Perspective of Instruction Interaction and Dependency","created":"2024-09-11","cited_by_count":13,"area":null},{"id":"2409.11378","title":"Diversify and Conquer: Diversity-Centric Data Selection with Iterative Refinement","created":"2024-09-17","cited_by_count":13,"area":null},{"id":"2603.04964","title":"Replaying pre-training data improves fine-tuning","created":"2026-03-05","cited_by_count":13,"area":null},{"id":"2402.14270","title":"Take the Bull by the Horns: Hard Sample-Reweighted Continual Training Improves LLM Generalization","created":"2024-02-22","cited_by_count":12,"area":null},{"id":"2410.16208","title":"Compute-Constrained Data Selection","created":"2024-10-21","cited_by_count":12,"area":null},{"id":"2310.15777","title":"MindLLM: Pre-training Lightweight Large Language Model from Scratch, Evaluations and Domain Applications","created":"2023-10-24","cited_by_count":11,"area":null},{"id":"2604.08510","title":"What do Language Models Learn and When? The Implicit Curriculum Hypothesis","created":"2026-04-09","cited_by_count":10,"area":null},{"id":"2402.05164","title":"A Resource Model For Neural Scaling Law","created":"2024-02-07","cited_by_count":9,"area":null},{"id":"2502.21009","title":"Position: Solve Layerwise Linear Models First to Understand Neural Dynamical Phenomena (Neural Collapse, Emergence, Lazy/Rich Regime, and Grokking)","created":"2025-02-28","cited_by_count":9,"area":null},{"id":"2501.12391","title":"Physics of Skill Learning","created":"2025-01-21","cited_by_count":8,"area":null},{"id":"2502.06244","title":"PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts","created":"2025-02-10","cited_by_count":8,"area":null},{"id":"2402.17759","title":"Towards Optimal Learning of Language Models","created":"2024-02-27","cited_by_count":7,"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":"2310.16776","title":"DEFT: Data Efficient Fine-Tuning for Pre-Trained Language Models via Unsupervised Core-Set Selection","created":"2023-10-25","cited_by_count":6,"area":null},{"id":"2510.10023","title":"Skill-Targeted Adaptive Training","created":"2025-10-11","cited_by_count":6,"area":null},{"id":"2401.12246","title":"Orion-14B: Open-source Multilingual Large Language Models","created":"2024-01-20","cited_by_count":5,"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":"2504.04400","title":"Pre-training Generative Recommender with Multi-Identifier Item Tokenization","created":"2025-04-06","cited_by_count":4,"area":null},{"id":"2504.09844","title":"MegaScale-Data: Scaling Dataloader for Multisource Large Foundation Model Training","created":"2025-04-14","cited_by_count":4,"area":null},{"id":"2505.15811","title":"On the creation of narrow AI: hierarchy and nonlocality of neural network skills","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2505.20380","title":"GRAPE: Optimize Data Mixture for Group Robust Multi-target Adaptive Pretraining","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2605.10770","title":"DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures","created":"2026-05-11","cited_by_count":4,"area":null},{"id":"2410.05224","title":"Cookbook: A framework for improving LLM generative abilities via programmatic data generating templates","created":"2024-10-07","cited_by_count":3,"area":null},{"id":"2502.19790","title":"Mixtera: A Data Plane for Foundation Model Training","created":"2025-02-27","cited_by_count":3,"area":null},{"id":"2505.00358","title":"R&B: Domain Regrouping and Data Mixture Balancing for Efficient Foundation Model Training","created":"2025-05-01","cited_by_count":3,"area":null},{"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":"2510.18250","title":"ssToken: Self-modulated and Semantic-aware Token Selection for LLM Fine-tuning","created":"2025-10-21","cited_by_count":3,"area":null},{"id":"2511.16602","title":"Bridging VLMs and Embodied Intelligence with Deliberate Practice Policy Optimization","created":"2025-11-20","cited_by_count":3,"area":null},{"id":"2606.04401","title":"TANDEM: Bi-Level Data Mixture Optimization with Twin Networks","created":"2026-06-03","cited_by_count":3,"area":null},{"id":"2406.00894","title":"Pretrained Hybrids with MAD Skills","created":"2024-06-02","cited_by_count":2,"area":null},{"id":"2506.10288","title":"ClusterUCB: Efficient Gradient-Based Data Selection for Targeted Fine-Tuning of LLMs","created":"2025-06-12","cited_by_count":2,"area":null},{"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":"2606.11499","title":"Hubs or Fringes: Pretraining Data Selection via Web Graph Centrality","created":"2026-06-09","cited_by_count":2,"area":null},{"id":"2609.06107","title":"DataFlex-RL: An Evaluation Platform for RLVR Data Policies","created":"2026-09-05","cited_by_count":2,"area":null},{"id":"2505.12754","title":"ProDS: Preference-oriented Data Selection for Instruction Tuning","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2505.16260","title":"Small-to-Large Generalization: Data Influences Models Consistently Across Scale","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2510.13008","title":"CurLL: A Developmental Framework to Evaluate Continual Learning in Language Models","created":"2025-10-14","cited_by_count":1,"area":null},{"id":"2602.05393","title":"Late-to-Early Training: LET LLMs Learn Earlier, So Faster and Better","created":"2026-02-05","cited_by_count":1,"area":null},{"id":"2603.13201","title":"Neuron-Aware Data Selection In Instruction Tuning For Large Language Models","created":"2026-03-13","cited_by_count":1,"area":null},{"id":"2604.01025","title":"Fast and Accurate Probing of In-Training LLMs' Downstream Performances","created":"2026-04-01","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":"2606.08167","title":"Explaining Data Mixing Scaling Laws","created":"2026-06-06","cited_by_count":1,"area":null},{"id":"2606.29858","title":"Smooth Scaling Laws Hide Stepwise Token Learning","created":"2026-06-29","cited_by_count":1,"area":null},{"id":"2606.29999","title":"AlgoSkill: Learning to Design Algorithms by Scheduling Human-Like Skills","created":"2026-06-29","cited_by_count":1,"area":null},{"id":"2609.10518","title":"BrainTaskonomy: Learning How to Pretrain and What to Transfer in fMRI Foundation Models","created":"2026-09-09","cited_by_count":1,"area":null},{"id":"2402.13866","title":"Kuaiji: the First Chinese Accounting Large Language Model","created":"2024-02-21","cited_by_count":0,"area":null},{"id":"2405.13386","title":"360Zhinao Technical Report","created":"2024-05-22","cited_by_count":0,"area":null},{"id":"2508.18192","title":"Unraveling the cognitive patterns of Large Language Models through module communities","created":"2025-08-25","cited_by_count":0,"area":null},{"id":"2509.23461","title":"Data-Efficient Training by Evolved Sampling","created":"2025-09-27","cited_by_count":0,"area":null},{"id":"2509.24422","title":"CDT: A Comprehensive Capability Framework for Large Language Models Across Cognition, Domain, and Task","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2602.03772","title":"UniGeM: Unifying Data Mixing and Selection via Geometric Exploration and Mining","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2604.22951","title":"The Power of Power Law: Asymmetry Enables Compositional Reasoning","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2605.15220","title":"Always Learning, Always Mixing: Efficient and Simple Data Mixing All The Time","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.19101","title":"Heterogeneity-Aware Dataset Scheduling for Efficient Audio Large Language Model Training","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2607.03522","title":"Co-Adaptive Multi-Task LoRA: Transfer-Aware, Label-Free Control of Domain Participation","created":"2026-07-03","cited_by_count":0,"area":null},{"id":"2607.04846","title":"Pretraining Curricula Enable Selective Fine-tuning","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.16122","title":"CRAFT: Clustering Rubrics to Diagnose Weak LLM Capabilities and Generate Targeted Fine-Tuning Data","created":"2026-07-17","cited_by_count":0,"area":null},{"id":"2608.05156","title":"Scaffold-Mediated Post-Training: Co-Evolving Model Parameters and Procedural Scaffold Graphs","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2608.11746","title":"Epiplexity Guided Data Selection and Generation for Out-of-Distribution Generalization","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.13545","title":"LittleLearner: Language Models Under Pedagogically Controlled Knowledge Exposure","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.14936","title":"Small Models Scout Bottleneck Order for Large-Model Data Control","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2609.32487","title":"Neural Dynamics as the Composition of Quantized Units","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.32991","title":"What Should Data Teach? Moving Bottlenecks Across Circuit, Store, and Use","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.33845","title":"How code helps different tasks? A decompositional lens on LLM post-training","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.37712","title":"PolyOCR-Venus: Unified OCR Foundation Models for Text-Centric Visual Intelligence","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39702","title":"A helps B while B hurts A: directed transfer in instruction-tuning mixture","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.11548","title":"Conditional Transfer from Controlled Pretraining Mixtures to Code","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.12345","title":"Overcoming Prior Barriers: Supervised Fine-Tuning under Long-Tail Distribution","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.14437","title":"From Transfer Probes to Expert Grouping: Evidence from LoRA Post-Training","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}