NVIDIA Announces Cosmos 3: Omnimodal World Models for Physical AI
NVIDIA Cosmos 3 is a unified world model capable of understanding and generating language, images, video, audio, and actions for robotics.
Sources x.com
🤖 DAIMON open-sources massive 10,000-hour tactile dataset for physical AI
Startup DAIMON Robotics has announced Daimon-Infinity, the world's largest multimodal tactile dataset, aiming to bring a sensitive sense of touch to robots.
Sources spectrum.ieee.org
Wetour Robotics Launches Spatial Intent Fusion — Turning the Human Body Into a Robot Control Interface
Wetour Robotics introduces Spatial Intent Fusion, a solution combining spatial, visual, and gesture data to control physical devices with under-100ms latency.
Sources spectrum.ieee.org
Panda Master — A Robot Combining GPT and a Robotic Arm for Real-Time Calligraphy
At the Physical AI Hackathon, the 'Panda Master' project made an impression by combining the ReachyMini robot, a GPT model, and an Agilex robotic arm to converse with users and draw 'fortunes' for them.
Sources x.com