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 · 8 stories
8 stories tagged world-models 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.
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.
Baidu says Apollo World generates live camera and lidar streams and reacts to the car's actions. It also proposed a '2+3' test for world models.
Genie 4 generates interactive worlds with native audio and characters that talk back, steered by text. It is now on AI Ultra and GA in the Gemini API.
VAST's EdenLive pairs a game engine with a neural renderer. 5B and 14B weights are public, but the licenses are mixed. 24 fps on an RTX 5090 is VAST's claim.
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.