Author

Jihun Park

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Jul 2026

Soft Mixture-of-Recursions: Going Deeper with Recursive Vision Transformers

Soft Mixture-of-Recursions (SoftMoR) is proposed, which learns token-wise weights to combine representations across recursion steps, and instantiate it as the Soft Recursive Vision Transformer (SR-ViT), which can benefit from deeper recursion while adding few parameters.

Sang-In Lee, Jihun Park · arXiv.org · 2 citations