Robot learning is moving beyond policies built for one robot, one scene, one task.
At MIT, we’re exploring a different path: turning video world models into embodiment-agnostic robot policies.
Introducing VERA: a 14B video-to-action system that controls robots across embodiments, skills, and environments.
From zero-shot pick-and-place on a real Panda arm to contact-rich cube reorientation with a 16-DoF robotic hand.
Different robots. Different environments. Different tasks.
Same video planner. Same weights.
We’re open-sourcing everything so you can fine-tune VERA for your own robot setup too. Deep dive in the thread:
🔗
🧵 (1/7)
China has stepped up systematic efforts to protect its national treasure, the giant panda, with notable results:
- The wild giant panda population in the country has grown from about 1,100 in the 1980s to nearly 1,900, according to the 2025 data from the National Forestry and Grassland Administration.
- The Giant Panda National Park was established in October 2021, covering a total area of over 22,000 square kilometers and providing around 72% of wild giant pandas with significant protection.
- The protected habitat areas for giant pandas have expanded from 1.39 million hectares to 2.58 million hectares since 2012.