Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging
机构 * City University of Hong Kong(香港城市大学) ; Hong Kong University of Science(香港科学大学) ; National University of Singapore(新加坡国立大学) ; Northwestern University(西北大学)
Comments ICML 2025. Camera-ready version updated. Our code is publicly available at https://github.com/shiqichen17/VLM_Merging