Log inSign up
Vivek Natarajan
829 posts
user avatar
Vivek Natarajan
@vivnat
Advancing science and medicine with AI @GoogleDeepMind | Previously @facebookai Research | Definite Optimist
Mountain View, CA
natviv.me
Joined December 2009
393
Following
9,702
Followers
  • Pinned
    user avatar
    Vivek Natarajan
    @vivnat
    Feb 19, 2025
    Accelerating scientific discoveries and helping cure diseases might be the most profound purpose of AI. Thrilled to introduce our @GoogleAI @GoogleDeepMind @googlecloud AI co-scientist system, which I believe is an important milestone towards this. Blog -
    Image
    research.google
    Accelerating scientific breakthroughs with an AI co-scientist
    42K
  • user avatar
    Vivek Natarajan
    @vivnat
    Dec 27, 2022
    Delighted to share our new @GoogleHealth @GoogleAI @Deepmind paper at the intersection of LLMs + health. Our LLMs building on Flan-PaLM reach SOTA on multiple medical question answering datasets including 67.6% on MedQA USMLE (+17% over prior work). arxiv.org/abs/2212.13138
    Image
    783K
  • user avatar
    Vivek Natarajan
    @vivnat
    Oct 10, 2024
    Google may not be perfect, and I am admittedly biased, but two Nobel Prizes awarded on consecutive days are a testament to its innovative spirit — a reason why so many of my generation associate it with magic. Modern-day academia with resources, great colleagues and freedom -
    92K
  • user avatar
    Vivek Natarajan
    @vivnat
    May 8, 2025
    Excited to share new validation results of our @GoogleDeepMind @GoogleAI AI co-scientist! Addressing the challenge of liver fibrosis, a condition affecting millions globally with few treatments options, we've been working with Dr. Gary Peltz @StanfordMed, exploring how
    Image
    GIF
    Image
    Image
    131K
  • user avatar
    Vivek Natarajan
    @vivnat
    Sep 10, 2025
    During Thanksgiving break last year, our AI co-scientist team @GoogleDeepMind @GoogleResearch - @Mysiak @alan_karthi met Prof @jrpenades @CostaT_Lab of @imperialcollege. They were nearing a breakthrough on how bacteria share resistance genes and proposed a test for our AI
    Image
    167K
  • user avatar
    Vivek Natarajan
    @vivnat
    Oct 17, 2025
    We are entering the "slop era" of AI for scientific discovery. Too much will be packaged as novel breakthroughs, cures to intractable diseases or solutions to unsolved problems, purely to chase attention and virality. Time and history will be the ultimate judge.
    102K
  • user avatar
    Vivek Natarajan
    @vivnat
    Sep 9, 2022
    We are looking for a research intern to work on an exciting project at the intersection of large language models (LLMs) and health in our team at @GoogleAI.
  • user avatar
    Vivek Natarajan
    @vivnat
    Sep 10, 2025
    Replying to @vivnat
    This is just the beginning. In the coming days and months, we'll share more prospective validated results where our AI co-scientist generated novel, testable hypotheses for complex open-ended problems, showing how the system can meaningfully accelerate scientific research.
    Image
    research.google
    Accelerating scientific breakthroughs with an AI co-scientist
    237K
  • user avatar
    Vivek Natarajan
    @vivnat
    Jul 27, 2023
    Medicine is inherently multimodal. Thrilled to share Med-PaLM M, the first demonstration of a generalist multimodal biomedical AI system with a stellar team @GoogleAI @GoogleDeepMind @GoogleHealth Paper: arxiv.org/pdf/2307.14334…
    Image
    GIF
    146K
  • user avatar
    Vivek Natarajan
    @vivnat
    May 17, 2023
    Pleased to share our latest @GoogleAI @googlehealth pre-print on Med-PaLM 2 where we detail our progress towards physician expert-level medical question answering performance! Link: arxiv.org/pdf/2305.09617…
    Image
    72K
  • user avatar
    Vivek Natarajan
    @vivnat
    Oct 1, 2025
    If i had a nickel for every serious scientist who told me @GoogleDeepMind AI co-scientist made a novel research discovery, I would have enough to buy lunch for the team 🙃 In all seriousness, though, real proof in science is experimental validation, peer-reviewed publication,
    user avatar
    Asher
    @asher5772
    Sep 30, 2025
    if i had a nickel for every MIT professor who told me GPT5 made a novel research discovery in the past week, i'd have 2 nickels. which isn't a lot, but it's strange that it happened twice
    60K
  • user avatar
    Vivek Natarajan
    @vivnat
    Jul 12, 2023
    Delighted to share that our Large Language Model (LLM) for medicine, Med-PaLM, has been published in @Nature today. nature.com/articles/s4158… With a dream team of co-authors @alan_karthi @AziziShekoofeh @taotu831 @thekaransinghal and many more at @GoogleAI @googlehealth
    Content cover image
    Large language models encode clinical knowledge
    From nature.com
    45K
  • user avatar
    Vivek Natarajan
    @vivnat
    Nov 18, 2025
    Gemini 3 Pro is a pretty cool model. The general advances in multimodal reasoning and coding are great but the most interesting part might actually be the science & medicine advances it enables. We'll share more soon :) Congrats to everyone at @GoogleDeepMind @GoogleAI!
    61K
  • user avatar
    Vivek Natarajan
    @vivnat
    Mar 6, 2025
    AMIE, our research AI doctor from @GoogleAI & @GoogleDeepMind, just got a nice upgrade! Not just diagnoses anymore, AMIE can converse, consult and provide treatment recommendations, prescriptions, multi-visit care, all guideline-compliant. Blog - research.google/blog/from-diag…
    Image
    GIF
    24K

New to X?

Sign up now to get your own personalized timeline!

Create account

By signing up, you agree to the Terms of Service and Privacy Policy, including Cookie Use.

Terms of Service|Privacy Policy|Cookie Policy|Accessibility|Ads info|© 2026 X Corp.
Don't miss what's happening
People on X are the first to know.
Log inSign up
Advertisement
Advertisement