arXiv cs.LG
One Block, Multiple Depths: Recurrent Vision Transformers with Depth-Programmed Experts
하나의 블록, 다양한 깊이: 깊이 프로그래밍된 전문가를 활용한 순환 비전 트랜스포머
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.