MBZUAI's PAN 2 is an open world model that simulates actions as video, under Apache 2.0
PAN 2 pairs a language model that plans the next world state with a 29B video model that renders it, up to 20 seconds. Weights and code are Apache 2.0.
Topic · 12 stories
12 stories tagged robotics on AI Tamer, newest first.
PAN 2 pairs a language model that plans the next world state with a 29B video model that renders it, up to 20 seconds. Weights and code are Apache 2.0.
Praxis-1 weights, inference and fine-tuning code are public under Apache 2.0. The quick start needs one 80 GB GPU; Runway's benchmark numbers are its own.
Google DeepMind's new robot model reports 30% to 100% higher task success and 96% on a Mercedes-Benz line. Only partners get it; the safety benchmark is open.
GR00T 2 learns robot skills from 400,000+ hours of human video. NVIDIA reports 40% zero-shot on unseen tasks, 95% after five demos. Code not out yet.
NVIDIA posts four Cosmos 3 Nano open-weight checkpoints for interactive driving and robot world simulation under OpenMDW1.1.
A real-robot benchmark from NUS, Hugging Face, BitRobot and partners: blinded A/B trials, every run on the Hub, and 10,000 free evaluation hours.
Flora's segmenter, captioner and rewarder are on Hugging Face under a noncommercial license. NVIDIA's ~125x cost edge rests on an assumed GPU price.
HUMXN says it pays for plumbing, HVAC, electrical, duct and carpet work in Minneapolis, Chicago and Miami when technicians record the job for robot training.
Brooklyn robot maker Ultra says it raised a $50 million Series A, and Fortune puts the total with its seed at $62 million. Ultra leases packing robots; Physical Intelligence supplies the model.
Amazon's October posts describe an open-source physical AI toolchain on AWS, wired to NVIDIA Isaac and Cosmos. The sample repo is Apache-2.0, and its status table still marks edge deployment planned.
Odyssey says Odyssey-3 Pro scores 66.1 and 54.7 on Physics-IQ Verified. The benchmark README lists 66.10 on a best-of-8 video-to-video entry. Weights are not released; the preview is Flash.
Black Forest Labs published FLUX.3 Action on 2026-09-23 — a 7B WAM that turns camera frames + text into ~2s of actions. Open weights under FLUX Kommunity License v1.0 (not open source). RoboLab 42.92% is a BFL claim.