project
QuantiPhy - A quantitative evaluation benchmark for VLM physics inference developed by Fei-Fei Li's team.
QuantiPhy is the first benchmark developed by Fei-Fei Li's team at Stanford University to quantitatively evaluate the physical reasoning capabilities of visual-language models (VLMs). QuantiPhy uses over 3300 video-text instances to require models to perform physical reasoning based on visual...
QuantiPhy is the first benchmark developed by Fei-Fei Li's team at Stanford University to quantitatively evaluate the physical reasoning capabilities of visual-language models (VLMs). QuantiPhy uses over 3300 video-text instances to require models to perform physical reasoning based on visual...