Author

Chuk Yoo

h-index 0 View on Semantic Scholar

We have 1 of 1 papers

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.

#artificial intelligence May 2026

Enabling KV Caching of Shared Prefix for Diffusion Language Models

Bidirectional prefix caching, BiCache, the first KV caching technique for shared prefixes in DLMs is proposed, which dynamically identifies a safe layer depth for reusing shared prefix KVs and eliminates redundant computation.

Younghun Go, Jaehoon Han, Changyong Shin et al. · arXiv.org · 0 citations