AI RESEARCH
KG-ViP: Bridging Knowledge Grounding and Visual Perception in Multi-modal LLMs for Visual Question Answering
arXiv CS.CV
•
ArXi:2601.11632v2 Announce Type: replace Multi-modal Large Language Models (MLLMs) for Visual Question Answering (VQA) often suffer from dual limitations: knowledge hallucination and insufficient fine-grained visual perception. Crucially, we identify that commonsense graphs and scene graphs provide precisely complementary solutions to these respective deficiencies by providing rich external knowledge and capturing fine-grained visual details. However, prior works typically treat them in isolation, overlooking their synergistic potential.