Preprint
Oct 2026
FastJEV: Understanding Redundancy for Compact JEV Inference
JEV models make multimodal decisions by directly scoring candidates. Although the common context is encoded once, candidate evaluation can still repeat matching token histories, duplicate inference states, and execute the full backbone. In this paper, we study these sources of redundancy and present FastJEV for compact...
Jie Ma, Jie Gao, Yi-Hang Liu et al.
· 0 citations