Most genetic variants linked to human disease sit outside genes and act only in specific cell states.
Today we are sharing AlphaGenome 2 to help connect those variants to the cells and genes driving disease.
Preprint: https://t.co/1ZG79uxZsG
Blog: https://t.co/iU1PsxR9zO
Cell-specific enhancer maps also highlight safer therapeutic targets.
At BCL11A, AG2 separates brain, B-cell, and erythroid enhancers and finds the GATAA motif targeted by sickle cell CRISPR therapy. Near TAL1, it models non-coding insertions from T-cell leukemia.
SIMA 2 is our most capable AI agent for virtual 3D worlds. ๐พ๐
Powered by Gemini, it goes beyond following basic instructions to think, understand, and take actions in interactive environments โ meaning you can talk to it through text, voice, or even images. Hereโs how ๐งต
Happy to announce that our work has been accepted to workshops on Multi-turn Interactions and Embodied World Models at #NeurIPS2025! Frontier foundation models are incredible, but how well can they explore in interactive environments?
Paper๐
https://t.co/8Q9j1VMTYv
๐งต1/13
1/ Today we are releasing Gemini 2.5 Pro Experimental, our newest Gemini model with integrated โthinkingโ and significant performance gains. Very proud of the whole team! ๐งต
Iโm really sad that my dear friend @FelixHill84 is no longer with us. He had many friends and colleagues all over the world - to try to ensure we reach them, his family have asked to share this webpage for the celebration of his life: https://t.co/1QoyHmAD3p
Santa Arrived! The PDF (of a colorful Xmas version) of the "Introduction to Universal AI" book is now freely available online at https://t.co/r9COEBnf4S Wishing you all joyful reading, Merry Xmas & a :-) New Year.
A chess set inspired by art deco ๐จ, plants ๐ฑ, or even the universe ๐.
Our latest AI experiment GenChess in @LabsDotGoogle lets you create playable art pieces with the power of Imagen 3. Try it now โ https://t.co/9th9zNoVBR
Beautiful result. A grandmaster-level chess LLM that just generates the next move - no search! All that was required was training a 270M parameter model on 10M chess games annotated by Stockfish.
Since GPT3, we have known that large Transformer language models are effective few-shot learners.
But did you know that the nature of language itself makes language particularly rich pre-training data for inducing few-shot learning?
1/n