2 papers
cs.AI2026
Trajectory-Refined Distillation
Li Jiang, Haoran Xu, Yichuan Ding +1
On-policy distillation (OPD) has become a central post-training tool for large language models (LLMs), providing dense per-token teacher supervision along the student's own rollout…
cs.CL2026
Which Heads Matter for Reasoning? RL-Guided KV Cache Compression
Wenjie Du, Li Jiang, Keda Tao +2
Reasoning large language models exhibit complex reasoning behaviors via extended chain-of-thought generation that are highly fragile to information loss during decoding, creating c…