{"total":17,"rows":[{"id":"2510.18874","title":"Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting","created":"2025-10-21","cited_by_count":94,"area":null},{"id":"2510.15103","title":"Continual Learning via Sparse Memory Finetuning","created":"2025-10-16","cited_by_count":20,"area":null},{"id":"2512.14273","title":"Zoom-Zero: Reinforced Coarse-to-Fine Video Understanding via Temporal Zoom-in","created":"2025-12-16","cited_by_count":8,"area":null},{"id":"2605.14967","title":"InfoSFT: Learn More and Forget Less with Information-Aware Token Weighting","created":"2026-05-14","cited_by_count":4,"area":null},{"id":"2509.17866","title":"Understanding Post-Training Structural Changes in Large Language Models","created":"2025-09-22","cited_by_count":3,"area":null},{"id":"2511.23151","title":"Learning to Refuse: Refusal-Aware Reinforcement Fine-Tuning for Hard-Irrelevant Queries in Video Temporal Grounding","created":"2025-11-28","cited_by_count":3,"area":null},{"id":"2603.02951","title":"CGL: Advancing Continual GUI Learning via Reinforcement Fine-Tuning","created":"2026-03-03","cited_by_count":3,"area":null},{"id":"2605.10973","title":"Rotation-Preserving Supervised Fine-Tuning","created":"2026-05-08","cited_by_count":3,"area":null},{"id":"2605.30148","title":"Overcoming Forgetting in LLM Fine-Tuning with Evolution Strategies","created":"2026-05-28","cited_by_count":3,"area":null},{"id":"2605.09640","title":"Overcoming Catastrophic Forgetting in Visual Continual Learning with Reinforcement Fine-Tuning","created":"2026-05-10","cited_by_count":2,"area":null},{"id":"2607.22676","title":"How LLM Task-Adaptation Reshapes Alignment: A Multi-dimensional Study of Behavioral and Representational Drift","created":"2026-07-10","cited_by_count":1,"area":null},{"id":"2608.00220","title":"Verifier-Induced Support Reshaping in On-Policy Optimization","created":"2026-07-31","cited_by_count":1,"area":null},{"id":"2605.05732","title":"CRAFT: Forgetting-Aware Intervention-Based Adaptation for Continual Learning","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2606.24901","title":"LLM Evolution as an Industry-Scale Ecosystem: A Lifecycle Perspective on Continual Learning","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2608.03660","title":"Taming the Implicit: Dual-Channel Risk-Aware Reinforcement Fine-Tuning for Continual Multimodal Post-Training","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2610.02437","title":"Learning Style, Forgetting Semantics: A Case Study of SFT and RFT on Classification Tasks","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.18634","title":"Geometric Calibration of Supervised Fine-Tuning","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}