{"total":32,"rows":[{"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":"2402.11505","title":"Federated Fine-tuning of Large Language Models under Heterogeneous Tasks and Client Resources","created":"2024-02-18","cited_by_count":93,"area":null},{"id":"2312.06353","title":"Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytes","created":"2023-12-11","cited_by_count":55,"area":null},{"id":"2404.10830","title":"Fewer Truncations Improve Language Modeling","created":"2024-04-16","cited_by_count":35,"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":"2505.17826","title":"Trinity-RFT: A General-Purpose and Unified Framework for Reinforcement Fine-Tuning of Large Language Models","created":"2025-05-23","cited_by_count":19,"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":"2501.14755","title":"Data-Juicer 2.0: Cloud-Scale Adaptive Data Processing for and with Foundation Models","created":"2024-12-23","cited_by_count":12,"area":null},{"id":"2505.18658","title":"Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metrics","created":"2025-05-24","cited_by_count":12,"area":null},{"id":"2407.11784","title":"Data-Juicer Sandbox: A Feedback-Driven Suite for Multimodal Data-Model Co-development","created":"2024-07-16","cited_by_count":10,"area":null},{"id":"2506.12213","title":"Fed-HeLLo: Efficient Federated Foundation Model Fine-Tuning with Heterogeneous LoRA Allocation","created":"2025-06-13","cited_by_count":7,"area":null},{"id":"2409.06277","title":"Ferret: Federated Full-Parameter Tuning at Scale for Large Language Models","created":"2024-09-10","cited_by_count":6,"area":null},{"id":"2505.16915","title":"DetailMaster: Can Your Text-to-Image Model Handle Long Prompts?","created":"2025-05-22","cited_by_count":6,"area":null},{"id":"2509.07287","title":"Paladin: Defending LLM-enabled Phishing Emails with a New Trigger-Tag Paradigm","created":"2025-09-08","cited_by_count":5,"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":"2410.15524","title":"MIRA: A Method of Federated MultI-Task Learning for LaRge LAnguage Models","created":"2024-10-20","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":"2603.14712","title":"Towards Next-Generation LLM Training: From the Data-Centric Perspective","created":"2026-03-16","cited_by_count":3,"area":null},{"id":"2510.20279","title":"ResearchGPT: Benchmarking and Training LLMs for End-to-End Computer Science Research Workflows","created":"2025-10-23","cited_by_count":2,"area":null},{"id":"2602.00597","title":"Hermes the Polyglot: A Unified Framework to Enhance Expressiveness for Multimodal Interlingual Subtitling","created":"2026-01-31","cited_by_count":2,"area":null},{"id":"2605.06733","title":"Beyond Factor Aggregation: Gauge-Aware Low-Rank Server Representations for Federated LoRA","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2404.16886","title":"Review of Data-centric Time Series Analysis from Sample, Feature, and Period","created":"2024-04-24","cited_by_count":1,"area":null},{"id":"2406.19271","title":"AutoPureData: Automated Filtering of Undesirable Web Data to Update LLM Knowledge","created":"2024-06-27","cited_by_count":1,"area":null},{"id":"2412.14436","title":"ORBIT: Cost-Effective Dataset Curation for Large Language Model Domain Adaptation with an Astronomy Case Study","created":"2024-12-19","cited_by_count":1,"area":null},{"id":"2505.13766","title":"A Blueprint for AI-Driven Software Quality: Integrating LLMs with Established Standards","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2605.12944","title":"From Instance Selection to Fixed-Pool Data Recipe Search for Supervised Fine-Tuning","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2607.20465","title":"DataPrep-Bench: Benchmarking LLMs as Training Data Preparators","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2405.13386","title":"360Zhinao Technical Report","created":"2024-05-22","cited_by_count":0,"area":null},{"id":"2509.03503","title":"Warming Up for Zeroth-Order Federated Pre-Training with Low Resource Clients","created":"2025-09-03","cited_by_count":0,"area":null},{"id":"2601.14263","title":"Call2Instruct: Automated Pipeline for Generating Q&A Datasets from Call Center Recordings for LLM Fine-Tuning","created":"2025-12-01","cited_by_count":0,"area":null},{"id":"2603.29211","title":"Xuanwu: Evolving General Multimodal Models into an Industrial-Grade Foundation for Content Ecosystems","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2607.27928","title":"Harnessing the Potential of Optimizing Data Mixtures via Bayesian Domain Reweighting","created":"2026-07-30","cited_by_count":0,"area":null}],"next_cursor":null}