Preprint
Aug 2026
SciMIF: Understanding Multimodal Instruction Following in Scientific Domains
This work introduces SciMIF, a novel benchmark designed to evaluate the capability of MLLMs in following complex scientific instructions, and proposes a comprehensive taxonomy comprising 10 constraint groups that captures both general functional requirements and discipline-specific characteristics.
Ye Shen, Yu-Ting Zheng, Dun Pei et al.
· 0 citations