GitHubRepoVKnowUVKnowU: Evaluating Visual Knowledge Understanding in Multimodal LLMscommonsense-reasoninghuman-centricintuitive-physics21Python10 mo agoOpenGVLabShare or keepTake it
GitHubRepoRIVER[ICLR 2026] RIVER: A Real-Time Interaction Benchmark for Video LLMslong-video-understandingmemory-benchmarkmultimodal-benchmark19Python7 mo agoOpenGVLabShare or keepTake it