Large-Small Model Synergy with Multimodal Fine-Grained Heuristics for Knowledge-Based Visual Question Answering

Open Webpage

Zhongfan Sun, Kan Guo, Yongli Hu, Daxin Tian, Qingqing Gao, Jiapu Wang, Junbin Gao, Yanfeng Sun, Baocai Yin

Published: 27 Oct 2025, Last Modified: 21 Jan 2026CrossrefEveryoneRevisionsCC BY-SA 4.0