Plug-and-Play Grounding of Reasoning in Multimodal Large Language Models
Abstract: The rise of Multimodal Large Language Models (MLLMs), renowned for their advanced instruction-following and reasoning capabilities, has significantly propelled the field of visual reasoning. However, due to limitations in their image tokenization processes, most MLLMs struggle to capture fine details of text and objects in images, especially in high-resolution samples. To overcome this, we introduce P2G, a novel framework for plug-and-play grounding in MLLMs. P2G utilizes the tool-usage potential of MLLMs to employ expert agents for on-the-fly grounding of critical visual and textual elements in images, thereby enabling deliberate reasoning through multimodal prompting. Additionally, we develop P2GB, a benchmark designed to evaluate MLLMs' proficiency in understanding inter-object relationships and textual content in challenging high-resolution images. Extensive experiments on visual reasoning tasks demonstrate the superiority of P2G, achieving performance comparable to GPT-4V on P2GB with a 7B backbone. Our work underscores the potential of plug-and-play grounding in reasoning, presenting a promising alternative to mere model scaling.
Paper Type: Long
Research Area: Multimodality and Language Grounding to Vision, Robotics and Beyond
Research Area Keywords: vision question answering, multimodality, reasoning
Contribution Types: NLP engineering experiment, Data resources
Languages Studied: English
Submission Number: 1118
Loading