Matching the Training-Time Weight Rule in Inference-Time Expert Deactivation
Expert deactivation at inference time changes both token routing and expert weights, and its effect on performance depends on how these changes are implemented.
By Hao Cheng (Zhejiang Gongshang University), Zhiyu Yang (Chang'an University), Bo Ma (Zhejiang Gongshang University), Hanzhang Jia (University of Sussex)arXiv - cs.CL (NLP)
Read the full story
Originally published by arXiv - cs.CL (NLP) on Nov 5, 2026.
Comments
Sign in to join the discussion.