Loading activity…
@junyaoshi
research @sundayrobotics | PhD @Penn @GRASPlab previously @SkildAI @Columbia
AI
According to thoma_gu, OmniGuide steers a frozen robot model using vision-language models, geometry and human guidance.
AI
Figure says its robots began useful work in 30 rented Bay Area homes without additional training. A team member reports 56% zero-shot success with Index pretraining, versus 8% without it.
