VLsI: Verbalized Layers-to-Interactions from Large to Small Vision Language Models

Lee, Byung-KwanByung-KwanLeeHachiuma, RyoRyoHachiumaYU-CHIANG WANGRo, Yong ManYong ManRoWu, Yueh-HuaYueh-HuaWu2025-10-272025-10-272025-06-10https://scholars.lib.ntu.edu.tw/handle/123456789/733077[SDGs]SDG4VLsI: Verbalized Layers-to-Interactions from Large to Small Vision Language Modelsconference paper10.1109/cvpr52734.2025.02751