
Kexin Huang
@kexinhuang5
PhD Student @Stanford CS with @jure; AI + Biomedicine
ID: 1025489425495678977
http://www.kexinhuang.com 03-08-2018 21:11:46
500 Tweet
2,2K Followers
583 Following

📡 🧬 Join us for the next Foundation Models for Biology Seminar Series (#FM4Bio) session on June 4 at 9 AM PT, featuring Kexin Huang. Kexin will present KGWAS, a geometric deep learning method that uses a massive functional genomics graph to enable rare variant discovery in


Very good highlight by Sri Kosuri but I’m still saying we need to do a LOT better as a field Reliability starts with what and how it’s published. We all live in the universe of positive and exciting results. Not the much larger one of ambiguity and failure. While publishing may



Exciting work just out today: 🤖🧬👉 Biomni is a general-purpose AI agent for biomedical research, brought to you by Kexin Huang Jure Leskovec and team!

The Biomni biomedical AI agent I was early testing has just been released, and it’s truly very impressive for an open-source system! I’m very excited about this! Kudos to everyone involved at Stanford AI Lab and Arc Institute and others for a fantastic contribution 👏





Tool use offers tremendous potential for integrating LLMs into biological experiment design, perhaps even more than scaling model size. Excited to build on our earlier results with BioDiscoverAgent, now with a significantly expanded tool suite. Great collab. led by Kexin Huang!

Love this work from Kexin Huang + colleagues. An AI co-pilot in my view is a very useful, practical framing of using agents to enhance the efficiency of biomedical science. Also appreciate Kexin Huang 's grounded presentation of his work. This was clearly an immense effort







1/ 🚨 #FM4Bio seminar update! 🚨 Due to strong interest in Biomni, our next Foundation Models for Biology (FM4Bio) seminar with Kexin Huang will now focus on: "Biomni: A General-Purpose Biomedical AI Agent." 📅 June 4, 9:00 AM PT 📍 Save your spot: x.genbio.ai/seminar
