SOMA: A Benchmark for Fine-Grained Egocentric Behavior and Body-Motion Understanding
SOMA benchmark tests 37 MLLMs on egocentric body-motion understanding with 1,632 questions across configuration, dynamics, and temporal reasoning
5 stories, newest first · one card per story
SOMA benchmark tests 37 MLLMs on egocentric body-motion understanding with 1,632 questions across configuration, dynamics, and temporal reasoning
LEGO turns one exocentric video into an egocentric view with a lifting-free synthesizer and diffusion model.
EgoLAP pretrains robot policies on human and robot data via language action reasoning, reaching 80.1% task progress.
Ego2Act tests whether video models can simulate multi-step egocentric manipulation from a scene image and goal.
Shanghai AI Laboratory introduces InternW0, a physical world model that jointly predicts visuals and continuous robot control.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views