Merging breaks MoE routing via softmax sensitivity; HARC uses Hessian curvature for closed-form router calibration that improves merged model performance without retraining.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
When Model Merging Breaks Routing: Training-Free Calibration for MoE
Merging breaks MoE routing via softmax sensitivity; HARC uses Hessian curvature for closed-form router calibration that improves merged model performance without retraining.