World Model

Dyna Robotics has released Dyna-2, a world-action model pre-trained on more than one million hours of egocentric human video. The technical report establishes three results: a scaling law on human data to 1M hours, the first transfer of that law to unseen robot data, and evidence that video co-training drives cross-embodiment generalization.

LTX-2.5 brings frontier video generation to local NVIDIA hardware: 6.8-second clips, native multishot, day-one ComfyUI, open weights.

NVIDIA has released Cosmos 3 Edge, a 4-billion-parameter open world model built to run on-device. It helps robots and vision AI agents understand surroundings,...