cross-model-communication

Tag

Cards List
#cross-model-communication

Latent Cache Flow: Model-to-Model Communication Without Text

arXiv cs.LG · 2026-05-25 Cached

The paper introduces Latent Cache Flow (LCF), a method for efficient model-to-model communication by exchanging compressed KV caches instead of text, reducing adapter size and enabling cross-context communication.

0 favorites 0 likes
← Back to home

Submit Feedback