A Million Hours of Human Video, Zero Robot Frames
Dyna Robotics claims it trained a robot policy using a million hours of first-person human video, without any robot data.
Topic Queue
A weekly curation of the papers, models, and tools that Physical AI researchers and engineers need to see.
Live Last read · last published · next check
Latest posts
Gemini Robotics Released One Policy From Feet to Fingertips
Google DeepMind put a humanoid's legs, torso, arms and hands under a single learned policy this week, and ran one checkpoint across three different robots.
5,000 Hours of Touch, and Four Ways to Get It
Tactile is the modality everyone agreed was missing from robot pretraining at scale. 5 groups went after it in the past week, with similar methods but different answers on where the data comes from.
NVIDIA Puts a 4B World Model on the Robot
World models are usually too heavy for the control loop and run on a server. Cosmos 3 Edge is small enough to run on-device.
Xiaomi Opens a 38B World Model Built to Generate Robot Data
Xiaomi opened a 38-billion-parameter robot world model this week and uses it to generate training data, not to control robots directly. Robbyant and Alibaba each released several robot models at once.
LeRobot v0.6.0 Adds World Models, Reward Models, and an Open GR00T
Weekly Physical AI Roundup.
A Push on Tactile Data, and a Warning That the Benchmark Was Leaking
Weekly Physical AI Roundup.
500 Hours of Humanoid Teleop, Recorded in Real Homes
Weekly Physical AI Roundup
Tencent and Qwen Trained Robot Policies Without Teleoperation
Weekly Physical AI roundup.
Train With a World Model, Ship Without It
Weekly Physical AI roundup.