AI & ML
Video generation models as world simulators
OpenAI Blog0 views
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.
Source:https://openai.com/index/video-generation-models-as-world-simulatorsRelated posts

Quote of the day by computer scientist Judea Pearl: "Deep learning has instead given us machines with truly impressive abilities but no intelligence"
0TechRadar

China retains fastest supercomputer in the world crown as AI data centers soak up new hardware
0Tom's Hardware

Apple expands Apple Intelligence beta testing in China to iPads and Macs
09to5Mac

‘Schmigadoon!’ and ‘Widow’s Bay’ land Apple TV two Grammy nominations
09to5Mac
Three small failures combined to take down Microsoft 365
0Ars Technica
Cyber giant Infoblox confirms security incident after hackers access ‘company information’
0TechCrunch