An ensemble of expert diffusion models trained in isolation on disjoint data clusters, combined by a learned router, matches the global flow-matching objective and outperforms a monolithic model at equal FLOPs.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Decentralized Diffusion Models
An ensemble of expert diffusion models trained in isolation on disjoint data clusters, combined by a learned router, matches the global flow-matching objective and outperforms a monolithic model at equal FLOPs.