arXiv cs.LG
Where Rounding Happens Matters: Rounding-Location Alignment Stabilizes LLM Reinforcement Learning
반올림이 일어나는 위치가 중요하다: 반올림 위치 정렬이 LLM 강화학습을 안정화한다
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.