Radu Soricut (@rsoricut) 's Twitter Profile
Radu Soricut

@rsoricut

Distinguished Scientist at Google DeepMind. Gemini Multimodal Lead. My own views here.

ID: 1003062737696534528

calendar_today02-06-2018 23:56:07

11 Tweet

67 Followers

68 Following

Derya Unutmaz, MD (@deryatr_) 's Twitter Profile Photo

I got a bit emotional seeing this illustration from Nano Banana Pro, because it depicts one of our major discoveries from more than 15 years ago, & it is a beautiful & accurate illustration; NB Pro knew it all. 🥹 Prompt: “Draw an illustration of GARP biology for Tregs”

I got a bit emotional seeing this illustration from Nano Banana Pro, because it depicts one of our major discoveries from more than 15 years ago, & it is a beautiful & accurate illustration; NB Pro knew it all. 🥹

Prompt: “Draw an illustration of GARP biology for Tregs”
Google AI Developers (@googleaidevs) 's Twitter Profile Photo

Gemini 3 Pro is the frontier of multimodal AI, delivering SOTA performance across document, screen, spatial, and video understanding. Read our deep dive on how we’ve pushed our core capabilities to power hero use cases across: + Docs: "derender" complex docs into structured

Gemini 3 Pro is the frontier of multimodal AI, delivering SOTA performance across document, screen, spatial, and video understanding.

Read our deep dive on how we’ve pushed our core capabilities to power hero use cases across:

+ Docs: "derender" complex docs into structured
Radu Soricut (@rsoricut) 's Twitter Profile Photo

Meet Vision Banana 🍌 from Google DeepMind! We provide strong evidence that image generators are generalist vision learners. Traditional computer vision tasks (segmentation, depth estimation, normal prediction) can now be performed at/near SOTA with a single generalist model

Meet Vision Banana 🍌 from <a href="/GoogleDeepMind/">Google DeepMind</a>! We provide strong evidence that image generators are generalist vision learners. Traditional computer vision tasks (segmentation, depth estimation, normal prediction) can now be performed at/near SOTA with a single generalist model