Physical Intelligence to present π0.7 at CoRL oral with emergent robot capabilities
lucy_x_shi · x · 2026-11-09
Physical Intelligence will present its latest robot foundation model π0.7 at CoRL (oral talk Monday 10:50am, poster 63 at 5pm).
The company highlights several emergent capabilities:
- Zero-data generalization: controls a new robot to fold shirts with no shirt-folding training data
- Language-based coaching: figures out how to use a new appliance guided purely by language
- One model, many skills: performs a wide range of dexterous manipulation tasks in a single model
π0.7 marks a notable step for generalist robot foundation models in cross-task generalization.
More from Embodied
- CoRL 2026 workshop on uncertainty in robotic world models, Sept 30 deadline — Majumdar_Ani · 2026-11-09
- EgoMo3R: Stanford's NeurIPS paper jointly reconstructs 3D motion and scenes from egocentric video — jcniebles · 2026-11-09
- Agent Buddy: an ESP32 animated companion that shows your AI coding agents' live status — DanWahlin · 2026-11-09
- Origami Robotics to Unveil New Direct-Drive Robot Hands and Data Glove at CoRL Party — ybisk · 2026-11-09
- OmniGuide steers diffusion VLAs at test time with differentiable 3D guidance, no retraining — thoma_gu · 2026-11-09
- Fully open MolmoAct2 action reasoning model wins Best Paper at CoRL TAG — jmin__cho · 2026-11-09