EgoExo-Next:Benchmarking Vision-Language Models on Visual-Option Next-State and Cross-View Reasoning
EgoExo-Next, a visual-option benchmark for dynamic visual-state reasoning, where models must identify how an observed action trajectory subsequently appears rather than predict only an action label or textual description, suggests that current VLMs remain substantially limited in dynamic visual-state reasoning.
Yu-Tong Li, Mo Wang, Xiao-Tong Li et al.
· 0 citations