Can Linguistic Reasoning Vectors Enhance Multimodal Reasoning Ability?
Most Vision-Language Models (VLMs) are built by extending pretrained Large Language Models (LLMs) with visual modules and multimodal alignment. However, this multimodal scaling often degrades the language-side reasoning ability originally encoded in the base LLM. While the base LLM retains usable reasoning after scalin...
Zi-Yi Wang, Li Li, Ao-Lin Zhou et al.
· 0 citations