cs.AIJun 5, 2026

Improving Multimodal Reasoning via Worst Dimension Optimization

Authors: Haocheng LvHuaping ZhangQiuchi LiLei LiChunxiao Gao

Organizations: Beijing Institute of Technology

Abstract

Multimodal reasoning requires a path that retains integrity over a wide range of constraints, from visual grounding to logic consistency. However, the current Process Reward Models focus on heuristically defined rewards that equally weigh these factors, which may lead to the concealment of individual dimension failures by the dominating factors, without guaranteeing the validity of the reasoning process in general.

Explore similar work

CardsList