arXiv cs.AI
How to Loop MoE: Flatten the Experts, Untie the Attention
MoE 루프링 방법: 전문가를 평탄화하고 주의를 분산시키기
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.