Distributed Subliminal Learning: Replacing Model Updates with Random-Carrier Outputs

Excerpt

arXiv:2610.05378v1 Announce Type: cross Abstract: Collaborative learning typically exchanges model parameters: federated clients communicate updates, while independently adapted foundation models are combined by exchanging adapters or checkpoints. This makes communication scale with model size and requires local specializations to be reconciled in weight space, where interference is common. We ask whether knowledge can instead be shared through model behavior on task-unrelated inputs. We introdu