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. πΎπ
Powered by Gemini, it goes beyond following basic instructions to think, understand, and take actions in interactive environments β meaning you can talk to it through text, voice, or even images. Hereβs how π§΅
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?
Paperπ
https://t.co/8Q9j1VMTYv
π§΅1/13
1/ Today we are releasing Gemini 2.5 Pro Experimental, our newest Gemini model with integrated βthinkingβ and significant performance gains. Very proud of the whole team! π§΅
Iβm 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 π¨, plants π±, or even the universe π.
Our latest AI experiment GenChess in @LabsDotGoogle lets you create playable art pieces with the power of Imagen 3. Try it now β 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