Receiver-conditioned latent communication between AI agents. Paper and demos.
Max Rossi
maxr0ssi
AI & ML interests
MS Data Science & Research at Columbia, with the Advanced Master’s Research extension.
I study how language models communicate through hidden states, drawing on information theory.
CacheBack / RCLC: agent communication in latent space, guided by what the receiver needs.
Latent Cache Flow: model-to-model communication without text. Co-first-author paper at the ICML 2026 Adapt-FM workshop.
Recent Activity
upvoted a paper about 17 hours ago
Receiver-Conditioned Latent Communication gives 94% CacheBack updated a collection about 21 hours ago
CacheBack updated a collection about 21 hours ago
CacheBack