Hanchen Wang
@hcwww_
AI for Science @StanfordAILab @Genentech
HLE has recently become the benchmark to beat for frontier agents. We @FutureHouseSF took a closer look at the chem and bio questions and found about 30% of them are likely invalid based on our analysis and third-party PhD evaluations. 1/7
Join the next #gestalt seminar by @hcwww_ this Friday- July 20 @10am EST globalspatial.org/seminar-series/ Dr Wang talks about SpatialAgent- #AI tool for #spatialbiology- using LLM & adaptive reasoning for expt design & #multimodal #spatialomic data analysis @LGMartelotto @ioavlachos
1/6 Excited to share our latest preprint: "MORPH Predicts the Single-Cell Outcome of Genetic Perturbations Across Conditions and Data Modalities". 🔗 biorxiv.org/content/10.110… 🧵 👇 Here is what MORPH is in a nutshell!
haha, I happen to know some seniors from Salk, Scripps, UCSD, Biotech startups and Pharmas. We'll see how things evolve. I also know the best ice cream place in the La Jolla Shore :))
Agreed. Heck I’m sure I could find sponsors to host an event for a day. This is too important an area, and too nice a line-up to miss.
Same here 🥲, we've invited ppl from Ai2, DeepMind, FutureHouse, Genentech, Harvard, Helmholtz, Microsoft, MILA, MIT, Meta, OpenAI, Princeton, Sakana, Stanford, xAI, to share experience on building AI Agents for Science. So curious which teams are more stellar and qualified
NeurIPS workshop proposal rejected. We had AMAZING speakers, and a great list of organizers. No rebuttal phase. No feedback. No dense reward :( Since I work full-time on Gemini and have zero time to publish, this was my chance to contribute to academia 😞
🤝Excited to announce @ProjectBiomni × @AnthropicAI! AI agents are set to transform how biologists do everyday research. Thanks to this partnership, the platform is now free for scientists worldwide: biomni.stanford.edu Learn more: anthropic.com/customers/biom…
Introducing Chai-2 - foundation model enabling low-N de novo antibody design. We experimentally validated Chai-2 on 50+ targets, >15% binding success rate - exceeding what a lab could previously achieve. Looking forward to scaling these progresses to the entire proteome.
We’re excited to introduce Chai-2, a major breakthrough in molecular design. Chai-2 enables zero-shot antibody discovery in a 24-well plate, exceeding previous SOTA by >100x. Thread👇
The @arcinstitute Virtual Cell Challenge: prizes worth up to $100,000 for accurately predicting cellular responses to genetic or chemical perturbations.
@sara_mostafavi (@genentech ) & I (@Stanford) r excited to announce co-advised postdoc positions for candidates with deep expertise in ML for bio (especially sequence to function models, causal perturbational models & single cell models). See details below. Pls RT 1/
It's official - I am thrilled to share that I am joining @MITBiology, the @kochinstitute, and @MIT_IMES as an Assistant Professor this fall! We will be a hybrid lab combining new technologies and computation to study ecDNA and tumor evolution. thejoneslaboratory.com
Celebration of the life of Atul Butte. Join colleagues from three universities to celebrate him at 10 am PST on Saturday.
Even the smartest LLMs can fail at basic multiturn communication Ask for grocery help → without asking where you live 🤦♀️ Ask to write articles → assumes your preferences 🤷🏻♀️ ⭐️CollabLLM (top 1%; oral @icmlconf) transforms LLMs from passive responders into active collaborators.…
there's data showing that hiring one toxic person can reduce the productivity of a team, but I am also convinced that hiring one high quality, demanding-but-warm/kind person can raise the bar for an entire team
Thank you Mo! Honestly, the proposed metric is especially helpful for flagging the drifting island distortions, more like a step towards next-generation metrics. Kudos to the scIB team @MDLuecken for creating the toolkit, and for continuing to develop new ones!
Integration metrics for evaluating batch effects on single cell atlases could be hacked! @hcwww_ and Aviv picked this up and proposed new metrics! Very interesting read
🤔 How do you get an LLM to reason like a CRISPR pro—or any top scientist? By training it on real expert conversations. 🛠️ What we built • An automated pipeline that distills learning signals from 10 + years of genomics discussions • Genome-Bench: 3,000 + curated Q&As on…
Defining “what is good” is central to both AI and Science. Despite massive efforts towards building the Virtual Cell, our recent @NatureBiotech article reflects on whether current gold standards (i.e., evaluation metrics) still hold up. nature.com/articles/s4158…
What makes a good cell embedding🧬? Is a higher score always better? Not quite! In this new preprint with @Jure & #Aviv, we ... [1/3] biorxiv.org/content/10.110…
I’m very excited to be joining MIT Biological Engineering @MITdeptofBE as an Assistant Professor and the Ragon Institute @ragoninstitute as a member in January 2026! I will be recruiting students and postdocs (see more info below).
We’re excited to start the 2025 HCA General Meeting today. Looking forward to many insightful discussions and collaborations. You can still register to attend virtually at buff.ly/eZiIwaB #HCA2025GM