English
Ehsan Adeli
Report

Ehsan Adeli

@eadeli

Prof. at @Stanford @StanfordMed @StanfordPSY; @StanfordSVL; @StanfordAILab; @StanfordTAIL AI, Computer Vision, Neuroscience, Healthcare, Medical Image Analysis.

751 Following2.1K Followers1.1K Posts
  1. Ehsan Adeli@eadeli
    Patient activity in the hospital gets scattered across shifts, notes, and handoffs. Our recent work, TRACER, pulls it back together: a training-free harness that lets LLMs/VLMs track activity from bedside video + EHR. Harness and synthetic data are open. Led by @DuranteZane 👇
    Zane Durante @DuranteZane
    1/ Can AI help doctors make more informed decisions based on patient activity and behavior over the course of a hospital stay? Today we introduce TRACER: a training-free multimodal harness that enables LLMs and VLMs to track patient activity using bedside video and health records. Blogpost: Paper:
    0219951
  2. Zane Durante✓@DuranteZane
    1/ Can AI help doctors make more informed decisions based on patient activity and behavior over the course of a hospital stay? Today we introduce TRACER: a training-free multimodal harness that enables LLMs and VLMs to track patient activity using bedside video and health records. Blogpost: Paper:
    Download
    103818917.8K
  3. Ehsan Adeli@eadeli
    It feels like déjà vu to trade one homeland for another, only to end up in a kakistocracy!
    000180
  4. Ehsan Adeli@eadeli
    Do text-to-image models need language pretraining? We trained Halcyon from scratch on 100M image–text pairs with no LLM at all, and it beats LlamaGen & JiT-T2I using 18–275× less compute. Open weights, 0.1–4B, in recent work led by @keshigeyan; @__yuezhao__ @jcniebles @drfeifei.
    Keshigeyan Chandrasegaran @keshigeyan
    Excited to share Halcyon, our latest research on multimodal pretraining! Building strong text-to-image generative models is simpler than we think! Blog: Models: Paper:
    019821
  5. Keshigeyan Chandrasegaran✓@keshigeyan
    Excited to share Halcyon, our latest research on multimodal pretraining! Building strong text-to-image generative models is simpler than we think! Blog: Models: Paper:
    6329019.4K
  6. Ehsan Adeli@eadeli
    Ehsan Adeli
    RT @yaserzt: Maybe I'm dense, but it only just occurred to me that this "AI revolution" is the only pure-software technology jump that I can think of. Wheels, steam engine, cars, electricity, cinema and TV, computers, the internet, mobile phones, etc. were all enabled by new hardware.
    01010
  7. Ehsan Adeli@eadeli
    It is so funny how the tech industry spent 20 years building tests to prove you're not a bot. Now we're building AI agents to pass them for us to reserve a table online. We're now engineering the exact thing we spent years engineering against. Same tech, opposite team.
    51201.1K
  8. Ehsan Adeli@eadeli
    Ehsan Adeli
    RT @karanps: LLMs have tokens. Images have patches. What should the brain have? 🤔 HBAR, our hierarchical tokenizer for fMRI, was just accepted to NeurIPS 2026! 🎉 It compresses fMRI ~415× while preserving structure from voxels → parcels → functional networks.
    0509
  9. Ehsan Adeli@eadeli
    Ehsan Adeli
    RT @PuyinLi: 💰 Announcing prizes for the QuantiPhy Challenge @ NeurIPS 2026! 🏆 $3,500 total cash prizes Main Track 🥇 $1,000 · 🥈 $500 · 🥉 $250 Open-Weight Track 🥇 $1,000 · 🥈 $500 · 🥉 $250 ⏰ Team registration: Oct 9, 23:59 AoE ⏰ Submission deadline: Oct 23, 23:59 AoE
    03011
  10. Ehsan Adeli@eadeli
    Ehsan Adeli
    RT @xxtiange: Today we announce 💰exciting prizes💰 for winners at the QuantiPhy Challenge @NeurIPSConf 2026. Register your team before 9th Oct. and submit csv files before 23rd Oct. to join the NeurIPS competition and win the prize!!! See more at:
    Puyin Li @PuyinLi
    💰 Announcing prizes for the QuantiPhy Challenge @ NeurIPS 2026! 🏆 $3,500 total cash prizes Main Track 🥇 $1,000 · 🥈 $500 · 🥉 $250 Open-Weight Track 🥇 $1,000 · 🥈 $500 · 🥉 $250 ⏰ Team registration: Oct 9, 23:59 AoE ⏰ Submission deadline: Oct 23, 23:59 AoE
    01010
  11. Ehsan Adeli@eadeli
    Ehsan Adeli
    RT @youngjoongkwon: Code for GenFusion: Feed-forward Human Performance Capture via Progressive Canonical Space Updates (ICLR 2026) is now public. Like watching a dancer spin, it fuses each frame into a canonical space and renders novel views from what was actually seen.
    01009
  13. Ehsan Adeli@eadeli
    One of the biggest shifts we're seeing in AI is moving beyond scaling data or scaling models in isolation toward co-evolving both together. @karanps's ICML2026 paper is a great example of that thinking: as a model matures, its learning environment should mature with it. 1/2
    Karan Singh @karanps
    Published at ICML 2026, with the final version and code now available! Curriculum-Guided Layer Scaling for Language Model Pretraining 📄 Paper: 💻 Code: With Neil Band (@neilbband) and Ehsan Adeli (@eadeli)
    10121.2K
  14. Karan Singh✓@karanps
    Posts @karanps
    Published at ICML 2026, with the final version and code now available! Curriculum-Guided Layer Scaling for Language Model Pretraining 📄 Paper: 💻 Code: With Neil Band (@neilbband) and Ehsan Adeli (@eadeli)
    0081.4K
  15. Ehsan Adeli@eadeli
    Posts @eadeli
    @karanps That's similar to how humans learn; we don't just get bigger brains; we tackle progressively harder problems as our capabilities grow. A synchronized evolution between model architecture and training curriculum is likely to become a way for FM training or agent systems. 2/2
    003218
  16. Ehsan Adeli@eadeli
    Ehsan Adeli
    RT @StanfordBioX: Week 6 of the Stanford Sapp Family CS Bio-X Undergraduate Summer Research Program included 3 more amazing faculty presentations! The cohort enjoyed this week's talks from Dr. Annelise Barron ( @annelise_b ), Dr. Martha Cyert ( @CyertMartha ) , and Dr. Ehsan Adeli ( @eadeli )!
    01010
  17. Ehsan Adeli@eadeli
    Ehsan Adeli
    RT @StanfordHAI: 📢 New issue brief: World models will reshape how AI interacts with the physical world. Our latest brief examines their emergence, opportunities, risks, and national security implications, and proposes a governance framework to guide policy conversations as the technology matures.
    02104
  18. Ehsan Adeli@eadeli
    Passionate about physical AI? Join our QuantiPhy Challenge!
    Tiange Xiang @xxtiange
    The QuantiPhy Challenge is now officially open! Register your team at: Submit your results to win amazing prizes!!!
    0171.4K
  19. Tiange Xiang✓@xxtiange
    The QuantiPhy Challenge is now officially open! Register your team at: Submit your results to win amazing prizes!!!
    Tiange Xiang @xxtiange
    Thrilled to announce the 🏎️QuantiPhy Challenge🏃 to appear in #NeurIPS2026 Competition Track! Read more at: We host this competition to bring together attention from two important communities: VLMs and physics reasoning. How numerically accurate can your model estimate size/velocity/acceleration from video? Submit your results to the Quantiphy Challenge!! P.S. We are seeking sponsors to prepare exciting prizes for winners! Please reach out for sponsors that are open to collaborate :)
    06133.7K
  20. Ehsan Adeli@eadeli
    Ehsan Adeli
    RT @agisummitai: 🧠 Speaker Spotlight: Ehsan Adeli @eadeli AI in medicine is moving beyond research papers and prototypes. Ehsan Adeli is building translational AI systems that can move from the lab into real clinical care — combining medical AI, computer vision, ambient intelligence, and mental health research. 🔹 Director, STAI — Stanford Translational AI in Medicine & Mental Health @StanfordAILab 🔹 Co-Director, Stanford AI for Mental Health Initiative 🔹 Works across computer vision, ambient intelligence & computational neuroscience 🔹 Focused on real-world applications in aging, neurodegeneration, mental health & clinical care As AI becomes part of healthcare, the question is not just what models can predict — it’s how they can support clinicians, patients, and care systems in the real world. Hear Ehsan on stage at AGI Summit SF 2026. 📅 July 18–19, 2026 📍 Palace of Fine Arts, San Francisco 🎟 Tickets: 🏷️ 15% off automatically applied through the link #AGISummit #MedicalAI #HealthcareAI #MentalHealthAI #sanfrancisco
    01010
  21. Ehsan Adeli@eadeli
    Ehsan Adeli
    RT @zamir_ar: Turns out it's possible to generate videos that maximally excite an arbitrary brain region using a simple search-based algorithm. It's a fully computational approach, so it's another way to speculate what a brain region represents, alongside other neuroscientific methods. Select an arbitrary brain region->algorithmically generate a video that jacks it up. See the visuals on the webpage In silico (for now)
    Yingtian Tang @yingtian_david
    🚨 NEW PREPRINT Videos strongly shape activity across the visual cortex. But can we design videos that maximally drive specific brain regions? We present NEvo 🧬🧠 — a neural-guided evolutionary framework that synthesizes videos to maximally activate target visual ROIs. (1/10)
    024108
  22. Yingtian Tang@yingtian_david
    🚨 NEW PREPRINT Videos strongly shape activity across the visual cortex. But can we design videos that maximally drive specific brain regions? We present NEvo 🧬🧠 — a neural-guided evolutionary framework that synthesizes videos to maximally activate target visual ROIs. (1/10)
    Download
    2373731343K
  23. Ehsan Adeli@eadeli
    Ehsan Adeli
    RT @BaadeAlan: I'll be at ICML to present Latent Forcing! Come stop by the poster on Tuesday at 2:00 PM KST, Hall A #3507 Reach out if you want to chat about the future of generative models!
    Alan Baade @BaadeAlan
    What's the right space to diffuse in: Raw Data or Latents? Why not both! In Latent Forcing, we order a joint diffusion trajectory to reveal Latents before Pixels, leading to improved convergence while being lossless at encoding and end-to-end at inference. w/ @drfeifei+... 1/n
    01008
  24. Alan Baade✓@BaadeAlan
    What's the right space to diffuse in: Raw Data or Latents? Why not both! In Latent Forcing, we order a joint diffusion trajectory to reveal Latents before Pixels, leading to improved convergence while being lossless at encoding and end-to-end at inference. w/ @drfeifei+... 1/n
    Download
    874572141K
  25. Ehsan Adeli@eadeli
    Ehsan Adeli
    RT @xxtiange: Thrilled to announce the 🏎️QuantiPhy Challenge🏃 to appear in #NeurIPS2026 Competition Track! Read more at: We host this competition to bring together attention from two important communities: VLMs and physics reasoning. How numerically accurate can your model estimate size/velocity/acceleration from video? Submit your results to the Quantiphy Challenge!! P.S. We are seeking sponsors to prepare exciting prizes for winners! Please reach out for sponsors that are open to collaborate :)
    0303.3K
  26. Ehsan Adeli@eadeli
    Ehsan Adeli
    RT @StanfordHAI: Last week, @StanfordHAI & AI4MH's 2026 symposium explored responsible AI adoption in mental health. CA Assembly Member @AsmMiaBonta stressed the need to protect youth as they turn to chatbots & other AI tools for mental health challenges. Full session ↘️
    0301.2K