Physical Intelligence (@physical

Physical Intelligence

122 posts

Physical Intelligence

@physical_int

Physical Intelligence (Pi), bringing AI into the physical world.

San Francisco, CA

physicalintelligence.company

Joined March 2024

Physical Intelligence
@physical_int
Jun 18
New work with @nvidia: evaluating robot policies entirely inside a world model. The policy acts, the model imagines the consequences, and the imagined evals predict real-world results. 🧵 real vs world-model rollout side by side📷
GIF
167K
Physical Intelligence
@physical_int
Jun 18
Replying to @physical_int
The model also knows when not to trust itself: its uncertainty estimates track how far generations deviate from reality. The uncertainty accurately predicts when model generation degrades
GIF
7.5K
Physical Intelligence
@physical_int
Jun 18
Joint work with the NVIDIA Cosmos team. Paper: arxiv.org/abs/2606.18610 Website: weichengtseng.github.io/sc3-eval/
arxiv.org
SC3-Eval: Evaluating Robot Foundation Models via Self-Consistent...
Evaluating generalist robot manipulation policies in the real world is expensive, slow, and difficult to scale. Action-conditioned video world models offer a scalable alternative by simulating...
6.4K
Physical Intelligence
@physical_int
Jun 3
π0.5 driving autonomous anastomosis!
Ryan McGuire
@r_mcguire
Apr 23
Replying to @r_mcguire
alephsurgical.com/blogs/research…
76K
Physical Intelligence
@physical_int
Apr 16
Our newest model, π0.7, has some interesting emergent capabilities: it can control a new robot to fold shirts for which we had no shirt folding data, figure out how to use an appliance with language-based coaching, and perform a wide range of dexterous tasks all in one model!
00:00
460K
Physical Intelligence
@physical_int
Apr 16
Replying to @physical_int
We are still discovering what π0.7 can do. It's fun to play with and the results so far have been quite surprising!
00:00
19K
Physical Intelligence
@physical_int
Apr 16
To find out more, check out our blog post, videos, and full-length research paper: pi.website/pi07
13K
Physical Intelligence reposted
Stanford MSL
@StanfordMSL
Mar 28
π, But Make It Fly ✈️ We fine-tuned π0, a VLA model pretrained entirely on manipulators, to fly a drone that picks up objects, navigates through gates, and composes both skills from language commands.
00:00
103K
Physical Intelligence
@physical_int
Mar 19
We developed an RL method for fine-tuning our models for precise tasks in just a few hours or even minutes. Instead of training the whole model, we add an “RL token” output to π-0.6, our latest model, which is used by a tiny actor and critic to learn quickly with RL.
00:00
434K
Physical Intelligence
@physical_int
Mar 19
Replying to @physical_int
With RL, the robot can learn very precise tasks, like fastening a zip tie, and can actually do it more consistently and more quickly than even human teleoperation.
00:00
18K
Physical Intelligence
@physical_int
Mar 19
To learn more about RLT, check out our blog post:
Precise Manipulation with Efficient Online RL
From pi.website
24K