Latent Cache Flow uses a small joint-translation-and-compression adapter to let LLMs with different contexts exchange KV cache summaries, outperforming both larger C2C adapters and text in early experiments.
International Conference on Machine Learning , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Latent Cache Flow: Model-to-Model Communication Without Text
Latent Cache Flow uses a small joint-translation-and-compression adapter to let LLMs with different contexts exchange KV cache summaries, outperforming both larger C2C adapters and text in early experiments.