Updates by date 4,939 published updates

Updates by date

Every published article and video from OpenAI, Gemini, and Claude in one calm date-based overview.

 ChatGPT ARTICLE

Video generation models as world simulators

We explore large-scale training of generative models on video data. Specifically, we train text-conditional diffusion models jointly on videos and images of variable durations, resolutions and aspect ratios. We leverage a transformer architecture that operates on spacetime patches of video and image latent codes. Our largest model, Sora, is capable of generating a minute of high fidelity video. Our results suggest that scaling video generation models is a promising path towards building general purpose simulators of the physical world.

Showing 2917 to 2928 of 4,939 updates.

Gemini komt eraan