MEPT routes each input through one of several per-layer prompt experts plus a shared expert, reporting modest accuracy gains and a 79% cut in activated prompt parameters on SuperGLUE.
These phenomena motivate our method
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MEPT: Mixture of Expert Prompt Tuning as a Manifold Mapper
MEPT routes each input through one of several per-layer prompt experts plus a shared expert, reporting modest accuracy gains and a 79% cut in activated prompt parameters on SuperGLUE.