Our article on using LLMs to improve health equity is out in NEJM AI! 85% of equity-related LLM papers focus on *harms*. But equally vital are the equity-related *opportunities* LLMs create: detecting bias, extracting structured data, and improving access to health info.

Agentic AI Meets Medicine!!! 🔬 Excited to announce MedRAX: a groundbreaking Medical Reasoning Agent for Chest X-ray interpretation, now on arXiv! Paper:arxiv.org/abs/2502.02673 Code: github.com/bowang-lab/Med… What is MedRAX? MedRAX is the first versatile AI agent that

🚀 Introducing scGPT-spatial! 🧬🌍 A game-changing spatial-omic foundation model, built on the powerful scGPT framework with MoE (mixture of experts) and continually pretrained on a massive 30 million spatial single-cell profiles! 🧠 What’s the challenge? Spatial

#AI meets genomic research. 🤖🧬 Evo 2, built using NVIDIA DGX Cloud on #AWS, is now the largest public AI model for analyzing DNA, RNA, & proteins across species. Learn more. 👇 go.aws/3X5Q5w4

As benchmarks for medical challenge problems become saturated with performance of LLMs, we need to build new, complex sets of challenges that better reflect real-world clinical tasks. Percy Liang Nigam Shah Matthew Lungren MD MPH Stanford Medicine @microsoft

Great paper, thread, & thanks for using synapse.org to deposit data: synapse.org/Synapse:syn619…

We are thrilled to present EchoNet-Measurements, an open source, comprehensive AI platform for automated #echofirst measurements. Using more than 1,414,709 annotations from 155,215 studies from 78,037 patients for training, this is the most comprehensive #echofirst segmentation

Speakers: dana_peer, Marinka Zitnik , Charlotte Bunne, Raul Rabadan, Christina Curtis, Ben Raphael, Anne Carpenter, Elana J. Fertig, and many others! aacr.org/meeting/aacr-s…

This startup has developed a noninvasive brain-computer interface: trib.al/oE1KaR7

Ready for the most powerful foundation model for medical images/videos? 🚨 Just dropped: MedSAM2 The next-gen foundation model for 3D medical image & video segmentation — built on top of SAM 2.1. • Project site: medsam2.github.io • Paper: arxiv.org/abs/2504.03600 Why

🚨NEW DATA ALERT! Data Release 25.4 includes updates to human and model studies, including new metabolomics data from the APOE-TR Study and new new plasma proteomics data from ROSMAP. For details, view Data Release 25.4 news.adknowledgeportal.org/data-release-2…

ResearchHub is partnering with Endaoment.eth | Endaoment.org to fund institutional research with crypto. You can now preregister studies and fund them with $RSC—with tax-deductible receipts and fast, fiat payouts to university labs.

nothing to see here – the LeRobot hackathon is just quietly shaping up to be the largest hackathon ever we passed 1000 registered participants. 80 local sessions. on every continent. all connected in a huge Zoom call curious about robotics? you can still join it's on 6/14

>700K people die each year due to S. aureus infection. Today we show that our AI designed new molecule, synthecin, stops drug-resistant S. aureus MRSA in mouse model💊 We created synthecin w/ SyntheMol-RL, our new RL generative AI. All open source biorxiv.org/content/10.110…

Many agents (Claude Code, Codex CLI) interact with the terminal to do valuable tasks, but do they currently work well enough to deploy en masse? We’re excited to introduce Terminal-Bench: An evaluation environment and benchmark for AI agents on real-world terminal tasks. Tl;dr

'A science project is akin to the ‘Stone Soup’ folk story: a guide comes into a village with little more than a stone and convinces each villager to contribute something to the emerging soup, thereby benefiting everyone involved' Long open science 👾🧪

You can now add Hugging Face to Cursor to find models, datasets, papers, apps,... Vibe coding a website is cool but imagine if the new AI powered code editors would turn everyone into an AI builder able to train AI themselves? How cool would that be?

More walking can be a path to better health. A countrywide study by University of Washington #UWAllen professor Tim Althoff, published in nature, found the strongest evidence to date that daily step count is influenced by the built environment. #datascience #PopulationHealth washington.edu/news/2025/08/1…

Sun's out, models out. 😎 IBM & NASA dropped Surya, an open-source heliophysics model trained on 14 years of observations from NASA’s Solar Dynamics Observatory, and it's 🔥🔥🔥.

🚨 New postdoc position in our lab UC Berkeley EECS! 🚨 (please retweet + share with relevant candidates) We seek applicants with experience in language modeling who are excited about high-impact applications in the health and social sciences! More info in thread 1/3