MoR–Swin: Efficient Vision Transformer Using Mixture of Recursions
Yongbao Ai, Tianxiang Gao, Zhipeng Lin, Longqi Yang, Qingyu Chang · 2026
Read MoR–Swin: Efficient Vision Transformer Using Mixture of Recursions by Yongbao Ai, Tianxiang Gao, Zhipeng Lin, Longqi Yang, Qingyu Chang (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13514322.txt.
Description
Vision Transformers, especially Swin Transformer, have become default backbones for various vision tasks but suffer from high memory consumption and training costs. This letter proposes MoR–Swin, a novel architecture that integrates Mixture of Recursions (MoR) into Swin Transformer. An adaptive token-level recursion mechanism dynamically allocates computational depth based on semantic complexity.
Catalog record
| CREATOR | Yongbao Ai, Tianxiang Gao, Zhipeng Lin, Longqi Yang, Qingyu Chang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 49 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |