DistMoE composes independently trained per-client Mixture-of-Experts specialists for vision-language models using a shared public anchor and isotropic residual calibration, without rehearsal of other clients' private data.
Moe-llava: Mixture of experts for large vision-language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
DistMoE: Private-data Rehearsal-free Routing in Mixture-of-Experts for Distributed Instruction Tuning
DistMoE composes independently trained per-client Mixture-of-Experts specialists for vision-language models using a shared public anchor and isotropic residual calibration, without rehearsal of other clients' private data.