{"total":141,"rows":[{"id":"2404.06395","title":"MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies","created":"2024-04-09","cited_by_count":723,"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":"2502.10341","title":"Organize the Web: Constructing Domains Enhances Pre-Training Data Curation","created":"2025-02-14","cited_by_count":76,"area":null},{"id":"2409.15254","title":"Archon: An Architecture Search Framework for Inference-Time Techniques","created":"2024-09-23","cited_by_count":60,"area":null},{"id":"2507.09404","title":"Scaling Laws for Optimal Data Mixtures","created":"2025-07-12","cited_by_count":52,"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":"2410.11820","title":"Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws","created":"2024-10-15","cited_by_count":47,"area":null},{"id":"2406.01375","title":"D-CPT Law: Domain-specific Continual Pre-Training Scaling Law for Large Language Models","created":"2024-06-03","cited_by_count":41,"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":"2410.12360","title":"Towards Neural Scaling Laws for Time Series Foundation Models","created":"2024-10-16","cited_by_count":33,"area":null},{"id":"2407.17467","title":"CMR Scaling Law: Predicting Critical Mixture Ratios for Continual Pre-training of Language Models","created":"2024-07-24","cited_by_count":23,"area":null},{"id":"2509.26625","title":"Learning to See Before Seeing: Demystifying LLM Visual Priors from Language Pre-training","created":"2025-09-30","cited_by_count":23,"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":"2503.12811","title":"A Multi-Power Law for Loss Curve Prediction Across Learning Rate Schedules","created":"2025-03-17","cited_by_count":22,"area":null},{"id":"2510.22037","title":"ATLAS: Adaptive Transfer Scaling Laws for Multilingual Pretraining, Finetuning, and Decoding the Curse of Multilinguality","created":"2025-10-24","cited_by_count":22,"area":null},{"id":"2512.10950","title":"E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training","created":"2025-12-11","cited_by_count":22,"area":null},{"id":"2604.19341","title":"Structured Scaling of AI Discovery Across Diverse Scientific Domains","created":"2026-04-21","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":"2504.14588","title":"Phoenix: A Motion-based Self-Reflection Framework for Fine-grained Robotic Action Correction","created":"2025-04-20","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":"2411.12925","title":"Loss-to-Loss Prediction: Scaling Laws for All Datasets","created":"2024-11-19","cited_by_count":15,"area":null},{"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":"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":"2502.04380","title":"Diversity as a Reward: Fine-Tuning LLMs on a Mixture of Domain-Undetermined Data","created":"2025-02-05","cited_by_count":13,"area":null},{"id":"2503.09197","title":"Q-SiT: Teaching LMMs for Image Quality Scoring and Interpreting","created":"2025-03-12","cited_by_count":13,"area":null},{"id":"2507.21184","title":"Can Language Models Discover Scaling Laws?","created":"2025-07-27","cited_by_count":13,"area":null},{"id":"2503.03862","title":"Not-Just-Scaling Laws: Towards a Better Understanding of the Downstream Impact of Language Model Design Decisions","created":"2025-03-05","cited_by_count":12,"area":null},{"id":"2508.11953","title":"Data Mixing Optimization for Supervised Fine-Tuning of Large Language Models","created":"2025-08-16","cited_by_count":12,"area":null},{"id":"2601.06395","title":"AfriqueLLM: How Data Mixing and Model Architecture Impact Continued Pre-training for African Languages","created":"2026-01-10","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":"2404.17785","title":"Temporal Scaling Law for Large Language Models","created":"2024-04-27","cited_by_count":11,"area":null},{"id":"2410.15661","title":"Scalable Data Ablation Approximations for Language Models through Modular Training and Merging","created":"2024-10-21","cited_by_count":11,"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":"2503.01506","title":"SampleMix: A Sample-wise Pre-training Data Mixing Strategey by Coordinating Data Quality and Diversity","created":"2025-03-03","cited_by_count":10,"area":null},{"id":"2503.21023","title":"Data Mixture Optimization: A Multi-fidelity Multi-scale Bayesian Framework","created":"2025-03-26","cited_by_count":9,"area":null},{"id":"2505.12534","title":"ChemPile: A 250GB Diverse and Curated Dataset for Chemical Foundation Models","created":"2025-05-18","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":"2407.08642","title":"Towards Building Specialized Generalist AI with System 1 and System 2 Fusion","created":"2024-07-11","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":"2505.16066","title":"Merge to Mix: Mixing Datasets via Model Merging","created":"2025-05-21","cited_by_count":7,"area":null},{"id":"2505.17293","title":"Graph Data Selection for Domain Adaptation: A Model-Free Approach","created":"2025-05-22","cited_by_count":7,"area":null},{"id":"2601.17858","title":"MergeMix: Optimizing Mid-Training Data Mixtures via Learnable Model Merging","created":"2026-01-25","cited_by_count":7,"area":null},{"id":"2410.04579","title":"Upsample or Upweight? Balanced Training on Heavily Imbalanced Datasets","created":"2024-10-06","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":"2510.24626","title":"Relative Scaling Laws for LLMs","created":"2025-10-28","cited_by_count":6,"area":null},{"id":"2601.21698","title":"Curriculum Learning for LLM Pretraining: An Analysis of Learning Dynamics","created":"2026-01-29","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":"2501.04661","title":"Beyond Memorization: Assessing Semantic Generalization in Large Language Models Using Phrasal Constructions","created":"2025-01-08","cited_by_count":5,"area":null},{"id":"2502.12051","title":"How to Upscale Neural Networks with Scaling Law? A Survey and Practical Guidelines","created":"2025-02-17","cited_by_count":5,"area":null},{"id":"2502.15950","title":"Optimizing Pre-Training Data Mixtures with Mixtures of Data Expert Models","created":"2025-02-21","cited_by_count":5,"area":null},{"id":"2505.07796","title":"Learning Dynamics in Continual Pre-Training for Large Language Models","created":"2025-05-12","cited_by_count":5,"area":null},{"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":"2510.25108","title":"Shift is Good: Mismatched Data Mixing Improves Test Performance","created":"2025-10-29","cited_by_count":5,"area":null},{"id":"2603.29791","title":"Reasoning-Driven Synthetic Data Generation and Evaluation","created":"2026-03-31","cited_by_count":5,"area":null},{"id":"2606.04261","title":"Can Generalist Agents Automate Data Curation?","created":"2026-06-02","cited_by_count":5,"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":"2504.13227","title":"DIDS: Domain Impact-aware Data Sampling for Large Language Model Training","created":"2025-04-17","cited_by_count":4,"area":null},{"id":"2506.21910","title":"AutoMixer: Checkpoint Artifacts as Automatic Data Mixers","created":"2025-06-27","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":"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":"2504.00695","title":"ToReMi: Topic-Aware Data Reweighting for Dynamic Pre-Training Data Selection","created":"2025-04-01","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":"2510.20860","title":"Data-Centric Lessons To Improve Speech-Language Pretraining","created":"2025-10-22","cited_by_count":3,"area":null},{"id":"2601.09966","title":"A Sustainable AI Economy Needs Data Deals That Work for Generators","created":"2026-01-15","cited_by_count":3,"area":null},{"id":"2603.17945","title":"ShapleyLaw: A Game-Theoretic Approach to Multilingual Scaling Laws","created":"2026-03-18","cited_by_count":3,"area":null},{"id":"2604.22753","title":"Spend Less, Fit Better: Budget-Efficient Scaling Law Fitting via Active Experiment Selection","created":"2026-04-24","cited_by_count":3,"area":null},{"id":"2605.02364","title":"InfoLaw: Information Scaling Laws for Large Language Models with Quality-Weighted Mixture Data and Repetition","created":"2026-05-04","cited_by_count":3,"area":null},{"id":"2605.30334","title":"Demystifying Data Organization for Enhanced LLM Training","created":"2026-05-28","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":"2608.07222","title":"Skaling: Chinchilla's Exponents Meet Kaplan's Coupling","created":"2026-08-07","cited_by_count":3,"area":null},{"id":"2504.05563","title":"Do Data Valuations Make Good Data Prices?","created":"2025-04-07","cited_by_count":2,"area":null},{"id":"2508.11144","title":"CTRL Your Shift: Clustered Transfer Residual Learning for Many Small Datasets","created":"2025-08-15","cited_by_count":2,"area":null},{"id":"2509.25380","title":"Predicting Training Re-evaluation Curves Enables Effective Data Curriculums for LLMs","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2510.08095","title":"Beyond Real Data: Synthetic Data through the Lens of Regularization","created":"2025-10-09","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":"2606.07597","title":"Repetition Mismatch: Why Data Mixture Experiments Don't Scale and How to Fix Them","created":"2026-05-29","cited_by_count":2,"area":null},{"id":"2607.11052","title":"Domain-Aware Scaling Laws Uncover Data Synergy","created":"2026-07-13","cited_by_count":2,"area":null},{"id":"2607.25271","title":"Bridging Compute- and Data-Optimal Pretraining","created":"2026-07-28","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":"2409.17527","title":"Data Proportion Detection for Optimized Data Management for Large Language Models","created":"2024-09-26","cited_by_count":1,"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":"2501.02068","title":"The interplay between domain specialization and model size","created":"2025-01-03","cited_by_count":1,"area":null},{"id":"2501.02842","title":"Foundations of GenIR","created":"2025-01-06","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":"2503.05491","title":"Statistical Deficiency for Task Inclusion Estimation","created":"2025-03-07","cited_by_count":1,"area":null},{"id":"2504.01386","title":"DALIP: Distribution Alignment-based Language-Image Pre-Training for Domain-Specific Data","created":"2025-04-02","cited_by_count":1,"area":null},{"id":"2505.21438","title":"Measuring Fine-Grained Relatedness in Multitask Learning via Data Attribution","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2510.25753","title":"How Data Mixing Shapes In-Context Learning: Asymptotic Equivalence for Transformers with MLPs","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2603.08022","title":"Capacity-Aware Mixture Law Enables Efficient LLM Data Optimization","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2603.19149","title":"Optimal Splitting of Language Models from Mixtures to Specialized Domains","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2605.26121","title":"GEM: Geometric Entropy Mixing for Optimal LLM Data Curation","created":"2026-04-27","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":"2606.14971","title":"FastMix: Fast Data Mixture Optimization via Gradient Descent","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2606.18307","title":"DRIFT: Data Selection for LLM Instruction Tuning via On-Policy Attribution","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2607.18789","title":"Moving Alphabet: A Controlled Study of Training Data for Text-to-Video Generation","created":"2026-07-21","cited_by_count":1,"area":null},{"id":"2607.28351","title":"Teffic-Audio: Tell Fact from Fiction","created":"2026-07-30","cited_by_count":1,"area":null}],"next_cursor":"100"}