{"total":25,"rows":[{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137,"area":"synth"},{"id":"2305.10142","title":"Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedback","created":"2023-05-17","cited_by_count":207,"area":"synth"},{"id":"2402.13064","title":"Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models","created":"2024-02-20","cited_by_count":99,"area":"synth"},{"id":"2402.07712","title":"Model Collapse Demystified: The Case of Regression","created":"2024-02-12","cited_by_count":82,"area":"synth"},{"id":"2503.19551","title":"Scaling Laws of Synthetic Data for Language Models","created":"2025-03-25","cited_by_count":46,"area":"synth"},{"id":"2412.02980","title":"Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models","created":"2024-12-04","cited_by_count":35,"area":"synth"},{"id":"2502.14948","title":"Learning to Solve and Verify: A Self-Play Framework for Code and Test Generation","created":"2025-02-20","cited_by_count":35,"area":"synth"},{"id":"2607.15524","title":"Recursive Harness Self-Improvement","created":"2026-07-17","cited_by_count":32,"area":"synth"},{"id":"2510.01631","title":"Demystifying Synthetic Data in LLM Pre-training: A Systematic Study of Scaling Laws, Benefits, and Pitfalls","created":"2025-10-02","cited_by_count":26,"area":"synth"},{"id":"2510.12784","title":"SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models","created":"2025-10-14","cited_by_count":22,"area":"synth"},{"id":"2602.04029","title":"PluRel: Synthetic Data unlocks Scaling Laws for Relational Foundation Models","created":"2026-02-03","cited_by_count":19,"area":"synth"},{"id":"2405.19846","title":"Quest: Query-centric Data Synthesis Approach for Long-context Scaling of Large Language Model","created":"2024-05-30","cited_by_count":16,"area":"synth"},{"id":"2409.19759","title":"Balancing Cost and Effectiveness of Synthetic Data Generation Strategies for LLMs","created":"2024-09-29","cited_by_count":15,"area":"synth"},{"id":"2605.26097","title":"Forgetting in Language Models: Capacity, Optimization, and Self-Generated Replay","created":"2026-05-25","cited_by_count":7,"area":"synth"},{"id":"2601.06086","title":"AzeroS: Extending LLM to Speech with Self-Generated Instruction-Free Tuning","created":"2025-12-31","cited_by_count":3,"area":"synth"},{"id":"2608.27287","title":"Astar: Learning to Propose Evolution Directions for Self-Evolving Industrial AI Systems","created":"2026-08-27","cited_by_count":2,"area":"synth"},{"id":"2511.13640","title":"Data Value in the Age of Scaling: Understanding LLM Scaling Dynamics Under Real-Synthetic Data Mixtures","created":"2025-11-17","cited_by_count":1,"area":"synth"},{"id":"2607.11883","title":"Requential Coding: Pushing the Limits of Model Compression with Self-Generated Training Data","created":"2026-07-13","cited_by_count":1,"area":"synth"},{"id":"2307.10633","title":"Multi-Method Self-Training: Improving Code Generation With Text, And Vice Versa","created":"2023-07-20","cited_by_count":0,"area":"synth"},{"id":"2506.12161","title":"Meta-Learning and Synthetic Data for Automated Pretraining and Finetuning","created":"2025-06-11","cited_by_count":0,"area":"synth"},{"id":"2602.07298","title":"Principled Synthetic Data Enables the First Scaling Laws for LLMs in Recommendation","created":"2026-02-07","cited_by_count":0,"area":"synth"},{"id":"2603.18073","title":"Continually self-improving AI","created":"2026-03-18","cited_by_count":0,"area":"synth"},{"id":"2605.20279","title":"The Economics of Model Collapse: Equilibrium, Welfare, and Optimal Provenance Subsidies in Synthetic Data Markets","created":"2026-05-19","cited_by_count":0,"area":"synth"},{"id":"2609.09572","title":"Learning with Synthetic Data via SGD in High-Dimensional Linear Regression","created":"2026-09-09","cited_by_count":0,"area":"synth"},{"id":"2609.18878","title":"Preventing Model Collapse: A Fisher-Rao Perspective on the Dynamics of Training with Synthetic Data","created":"2026-09-16","cited_by_count":0,"area":"synth"}],"next_cursor":null}