VIMA 1.5

Software / AppMentioned in 1 video

A Vision Language Action model that achieved the best overall performance on the Humanoid Everyday dataset benchmarks.

Videos Mentioning VIMA 1.5

Stanford Robotics Seminar ENGR319 | Winter 2026 | 𝚿0: An Open Foundation Model

Stanford Robotics Seminar ENGR319 | Winter 2026 | 𝚿0: An Open Foundation Model

Stanford Online

A Vision Language Action model that achieved the best overall performance on the Humanoid Everyday dataset benchmarks.