{"total":17,"rows":[{"id":"2504.14757","title":"SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs","created":"2025-04-20","cited_by_count":22,"area":null},{"id":"2510.23081","title":"A Survey on LLM Mid-Training","created":"2025-10-27","cited_by_count":21,"area":null},{"id":"2504.02953","title":"Cultural Learning-Based Culture Adaptation of Language Models","created":"2025-04-03","cited_by_count":16,"area":null},{"id":"2602.12036","title":"Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models","created":"2026-02-12","cited_by_count":6,"area":null},{"id":"2503.13992","title":"The KoLMogorov Test: Compression by Code Generation","created":"2025-03-18","cited_by_count":5,"area":null},{"id":"2503.21332","title":"ReFeed: Multi-dimensional Summarization Refinement with Reflective Reasoning on Feedback","created":"2025-03-27","cited_by_count":4,"area":null},{"id":"2502.11466","title":"GiFT: Gibbs Fine-Tuning for Code Generation","created":"2025-02-17","cited_by_count":3,"area":null},{"id":"2502.20855","title":"MAMUT: A Novel Framework for Modifying Mathematical Formulas for the Generation of Specialized Datasets for Language Model Training","created":"2025-02-28","cited_by_count":1,"area":null},{"id":"2604.16804","title":"AutoOR: Scalably Post-training LLMs to Autoformulate Operations Research Problems","created":"2026-04-18","cited_by_count":1,"area":null},{"id":"2609.36903","title":"MultiTalk: Scaling Full-Duplex Speech Models to Long, Multi-Party, Bilingual Conversation","created":"2026-09-29","cited_by_count":1,"area":null},{"id":"2502.08904","title":"MIH-TCCT: Mitigating Inconsistent Hallucinations in LLMs via Event-Driven Text-Code Cyclic Training","created":"2025-02-13","cited_by_count":0,"area":null},{"id":"2512.02791","title":"Making Dialogue Grounding Data Rich: A Three-Tier Data Synthesis Framework for Generalized Referring Expression Comprehension","created":"2025-12-02","cited_by_count":0,"area":null},{"id":"2602.20296","title":"Learning to Solve Complex Problems via Dataset Decomposition","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2605.21160","title":"Learning First Integrals via Backward-Generated Data and Guided Reinforcement Learning","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2605.23933","title":"KT4EQG: Personalized Exercise Question Generation via Knowledge Tracing","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2607.22883","title":"Evaluating and Mitigating the Misguidance Effect of Buggy Code in LLM-Generated Unit Tests","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2609.01386","title":"When Tokenization is Secretly Output Supervision","created":"2026-09-01","cited_by_count":0,"area":null}],"next_cursor":null}