World Models News
The latest World Models coverage curated for game developers.
Researchers have built an Unreal Engine pipeline that generates action-conditioned video for world-model pretraining, pairing control inputs with rendered scene changes. The system produced 2,691 hours of 1080p footage and …
WorldRover turns long-horizon world exploration into a synthetic data problem, using Unreal Engine to render minute-scale traversals with full trajectories and scene geometry. The resulting 10M-sequence dataset pairs RGB with …
A new CG-World dataset packages 850,000 temporally aligned 1-5 second segments from industrial graphics pipelines into a world-state format. It records latent state, motion, camera, lighting, physics, and events, giving …
Wonder is a new video world model that turns a single image or conditioned clip into a playable scene you can explore by moving the camera in real time. The …
A controlled study of action-conditioned world models finds that memory design matters more than replay quality suggests. With a shared video diffusion backbone and fixed action interface, the authors show …
A study of video diffusion models found they can linearly expose physical plausibility in their internal states, even though that signal is missing from the VAE input. On IntPhys and …
A proof-of-concept rendering pipeline that spends less compute on raw frame count and more on temporal coherence looks promising for graphics teams. Using a 15 FPS anchor cadence and FSR4-based …
A new paper claims RAEv2 cuts diffusion training time by more than 10x while improving image quality, which is relevant for teams building generative tools and world models. The key …