{"total":32,"rows":[{"id":"2511.16624","title":"SAM 3D: 3Dfy Anything in Images","created":"2025-11-20","cited_by_count":247,"area":null},{"id":"2510.24684","title":"SPICE: Self-Play In Corpus Environments Improves Reasoning","created":"2025-10-28","cited_by_count":83,"area":null},{"id":"2510.26788","title":"Defeating the Training-Inference Mismatch via FP16","created":"2025-10-30","cited_by_count":66,"area":null},{"id":"2510.18927","title":"BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping","created":"2025-10-21","cited_by_count":47,"area":null},{"id":"2509.15194","title":"Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation","created":"2025-09-18","cited_by_count":45,"area":null},{"id":"2509.07953","title":"RaC: Robot Learning for Long-Horizon Tasks by Scaling Recovery and Correction","created":"2025-09-09","cited_by_count":39,"area":null},{"id":"2509.16679","title":"Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle","created":"2025-09-20","cited_by_count":35,"area":null},{"id":"2601.09668","title":"STEP3-VL-10B Technical Report","created":"2026-01-14","cited_by_count":32,"area":null},{"id":"2510.23081","title":"A Survey on LLM Mid-Training","created":"2025-10-27","cited_by_count":21,"area":null},{"id":"2510.01152","title":"MASH: Modeling Abstention via Selective Help-Seeking","created":"2025-10-01","cited_by_count":6,"area":null},{"id":"2510.10681","title":"RePro: Training Language Models to Faithfully Recycle the Web for Pretraining","created":"2025-10-12","cited_by_count":6,"area":null},{"id":"2512.13874","title":"SAGE: Training Smart Any-Horizon Agents for Long Video Reasoning with Reinforcement Learning","created":"2025-12-15","cited_by_count":6,"area":null},{"id":"2601.12186","title":"Aletheia: What Makes RLVR For Code Verifiers Tick?","created":"2026-01-17","cited_by_count":5,"area":null},{"id":"2511.05933","title":"Reinforcement Learning Improves Traversal of Parametric Knowledge in LLMs","created":"2025-11-08","cited_by_count":4,"area":null},{"id":"2511.07464","title":"Motif 2 12.7B technical report","created":"2025-11-07","cited_by_count":4,"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":"2508.01326","title":"Large-Scale Diverse Synthesis for Mid-Training","created":"2025-08-02","cited_by_count":3,"area":null},{"id":"2605.30288","title":"MIRA: Mid-training Rubric Anchoring for Source-Aware Data Selection","created":"2026-05-28","cited_by_count":3,"area":null},{"id":"2508.01317","title":"LinkQA: Synthesizing Diverse QA from Multiple Seeds Strongly Linked by Knowledge Points","created":"2025-08-02","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":"2510.18383","title":"MENTOR: Reinforcement Learning via Flexible Teacher-Optimized Rewards for Tool-Use Distillation","created":"2025-10-21","cited_by_count":2,"area":null},{"id":"2602.00217","title":"Dispersion Loss Counteracts Embedding Condensation and Improves Generalization in Small Language Models","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2602.19458","title":"ComplLLM: Fine-tuning LLMs to Discover Complementary Signals for Decision-making","created":"2026-02-23","cited_by_count":2,"area":null},{"id":"2601.06911","title":"Distributional Clarity: The Hidden Driver of RL-Friendliness in Large Language Models","created":"2026-01-11","cited_by_count":1,"area":null},{"id":"2605.27564","title":"The Future of Facts: Tracing the Factual Generation-Verification Gap","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2606.32029","title":"When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2510.08741","title":"Coordinates from Context: Using LLMs to Ground Complex Location References","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2603.13761","title":"Level Up: Defining and Exploiting Transitional Problems for Curriculum Learning","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2606.27369","title":"Reinforcement Learning without Ground-Truth Solutions can Improve LLMs","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.20438","title":"Preference Tuning as Spectral Update Reorganization","created":"2026-05-12","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":"2609.18496","title":"MiST: Mid-Training LLMs for Cybersecurity","created":"2026-09-16","cited_by_count":0,"area":null}],"next_cursor":null}