Introducing Gemini Omni
Get smart on it
Gemini Omni is a new AI model that can generate high-quality videos from combinations of images, audio, video, and text inputs. The model can edit videos through natural language conversation, maintaining consistent characters and realistic physics while allowing users to change specific elements or entire scenes. Gemini Omni Flash, the first model in the Omni family, is being rolled out to subscribers through the Gemini app and at no cost to users on YouTube Shorts. All videos created with the model include a digital watermark called SynthID to help verify that content was AI-generated.
Related news
Vibe coding platform Base44 launches own model as AI startups seek defensibility
Wix-owned vibe coding platform Base44 has started rolling out its own AI model — with hopes that it will eventually outperform frontier models.
DiScoFormer: One transformer for density and score, across distributions
DiScoFormer is a transformer model that estimates both the density and score of a data distribution in a single forward pass without requiring retraining for new distributions. The density describes where data points cluster, while the score, the gradient of log-density, points toward more probable regions and is used in diffusion-based generative models, Bayesian sampling, and scientific simulations. Existing methods force a trade-off: classical kernel density estimation works on any distribution but loses accuracy in high dimensions, while neural score-matching models stay accurate in high dimensions but must be retrained for each new distribution. DiScoFormer significantly outperforms kernel density estimation, cutting score error by 6.5 times and density error by more than 37 times in 100 dimensions, while generalizing to distributions with shapes and complexities not seen during training.
