Tag
Introduces VIABench, a comprehensive video benchmark for evaluating multimodal large language models in real-world visual assistance for blind and visually impaired individuals, covering 761 videos and 14,526 annotations across three tasks.
VGenST-Bench is a benchmark that uses generative models to actively synthesize controlled spatio-temporal reasoning scenarios, with a multi-agent pipeline and human quality control, to evaluate multimodal large language models.