{"total":22,"rows":[{"id":"2509.20758","title":"SFT Doesn't Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMs","created":"2025-09-25","cited_by_count":24,"area":null},{"id":"2509.21016","title":"RL Grokking Recipe: How Does RL Unlock and Transfer New Algorithms in LLMs?","created":"2025-09-25","cited_by_count":23,"area":null},{"id":"2507.05195","title":"Train-before-Test Harmonizes Language Model Rankings","created":"2025-07-07","cited_by_count":12,"area":null},{"id":"2508.20697","title":"Token Buncher: Shielding LLMs from Harmful Reinforcement Learning Fine-Tuning","created":"2025-08-28","cited_by_count":8,"area":null},{"id":"2509.26313","title":"One-Token Rollout: Guiding Supervised Fine-Tuning of LLMs with Policy Gradient","created":"2025-09-30","cited_by_count":8,"area":null},{"id":"2606.25178","title":"Transferability for General Reasoning: An Automated Curriculum for Multi-Domain RLVR","created":"2026-06-23","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":"2603.08371","title":"Leaderboard Incentives: Model Rankings under Strategic Post-Training","created":"2026-03-09","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":"2509.20321","title":"Conversational Speech Reveals Structural Robustness Failures in SpeechLLM Backbones","created":"2025-09-24","cited_by_count":2,"area":null},{"id":"2606.07812","title":"Scaling Participation in Modular AI Systems","created":"2026-06-05","cited_by_count":2,"area":null},{"id":"2508.10409","title":"Dataset Construction for Training LLM to Learn Analog Circuit Knowledge","created":"2025-08-14","cited_by_count":1,"area":null},{"id":"2604.14258","title":"GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification","created":"2026-04-15","cited_by_count":1,"area":null},{"id":"2511.06776","title":"Data Trajectory Alignment for LLM Domain Adaptation: A Two-Phase Synthesis Framework for Telecommunications Mathematics","created":"2025-11-10","cited_by_count":0,"area":null},{"id":"2605.25381","title":"Not only where, But when: Temporal Scheduling for RLVR","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.25450","title":"The Generalization Spectrum: A Chromatographic Approach to Evaluating Learning Algorithms","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2608.07786","title":"Who Built This Model? Tracing LLM Lineage via Spectral Fingerprints in Weight Space","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2609.22146","title":"GRRR: The Geometry of Reshaping, Rotation, and Routing in Decoder LLM post-training","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.29230","title":"EAGER: Enhancing Generative Event Extraction via Reinforcement Learning with Verifiable Rewards","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.36952","title":"ER-JEPA: Experience Replay Improves Joint-Embedding Predictive Learning in Language Models","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39702","title":"A helps B while B hurts A: directed transfer in instruction-tuning mixture","created":"2026-09-30","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}