arXiv cs.AI
Beyond Teacher Likelihood: Group-Calibrated On-Policy Distillation for Long-Context Reasoning
교사 가능성의 한계를 넘어: 장문 추론을 위한 그룹 보정된 온정책계 정제
No write-up yet — this entry is still just the auto-fetched hook. Aaron's own summary (200–500 words) will replace this note once he's written it.