James Zou

Researchers create ‘virtual scientists’ to solve complex biological problems An AI lab developed by Stanford Medicine researchers has already shown promising results, generating ideas for a more effective COVID-19 vaccine in just a few days.

Nice @stanforduniversity.bsky.social article profiling our #VirtualLab of AI scientists news.stanford.edu/stories/2025...

Figure 1. An Overview of the Fine-Tuning Case Study.

Figure 2. Performance of Fine-Tuned Large Language Models on Each Medical Dataset.

Figure 3. Model Performance on MedQA after Updating.

Case Study by Eric Wu, PhD, Kevin Wu, PhD, and James Zou, PhD: Limitations of Learning New and Updated Medical Knowledge with Commercial Fine-Tuning Large Language Models nejm.ai/4nTx1Np

@jameszou.bsky.social #AI #MedSky

GitHub - zou-group/virtual-lab: A virtual lab of LLM agents for science research A virtual lab of LLM agents for science research. Contribute to zou-group/virtual-lab development by creating an account on GitHub.

The Virtual Lab is open source and can be applied to many problems! github.com/zou-group/vi...

👏Great job @kylewswanson.bsky.social John Pak, Wes Wu, Nash Bulaong @czbiohub.bsky.social

⚡️Thrilled that #VirtualLab is published in @nature.com! www.nature.com/articles/s41...

We created a team of AI agents to mirror my Stanford lab 🤖. Led by a PI agent, the AI scientists ran their own group meetings and discovered effective binders to new CoVID variants that we validated.

Who do you call when you need to design novel, potent nanobodies vs a pathogen?
The virtual lab of A.I. agents @nature.com @jameszou.bsky.social @kylewswanson.bsky.social
www.nature.com/articles/s41...

Day 3 of #ISMBECCB2025 started with an excellent talk from @jameszou.bsky.social which presented how AI can form virtual labs to discuss problems, how can AI reanalyse research data to get new biological results, and how we can interpret complex AI predictions 💻🤖

Figure 1. An Overview of the Fine-Tuning Case Study.

Six frontier large language models evaluated on incorporating newly updated medical knowledge through commercial fine-tuning application programming interfaces struggled to generalize updated information, despite modest gains. Learn more: nejm.ai/4nTx1Np

@jameszou.bsky.social

🏆Thrilled that #CollabLLM won the #ICML2025 Outstanding Paper Award!

We propose a new approach to optimize human-AI collaboration, which is critical for agents. Congratulations to my fantastic co-authors; great job Shirley Wu and Michel Galley driving the project! 👏

Paper: arxiv.org/pdf/2502.00640

AI ‘scientists’ joined these research teams: here’s what happened Emerging ‘co-scientist’ systems use chatbots to mimic the deliberations of a research group. Nature asked researchers to test them out.

What is it like for scientists to work with AI co-scientists?

Excellent @nature.com feature discussing researchers' experience interacting with our #VirtualLab and other tools www.nature.com/articles/d41...

EvoLM: In Search of Lost Language Model Training Dynamics Modern language model (LM) training has been divided into multiple stages, making it difficult for downstream developers to evaluate the impact of design choices made at each stage. We present EvoLM, ...

Introducing EvoLM, a model suite with 100+ decoder-only LMs (1B/4B) trained from scratch, across four training stages —

🟦 Pre-training
🟩 Continued Pre-Training (CPT)
🟨 Supervised Fine-Tuning (SFT)
🟥 Reinforcement Learning (RL)

Great job by Sam Alber, Bowen Chen, Alina Isakova, Aaron Wilk!

High throughput data are goldmines that we often only scratch the surface. Great for AI to systematically analyze! CellVoyager makes Jupyter notebooks for easy replication
📜https://www.biorxiv.org/content/10.1101/2025.06.03.657517v1
💻https://github.com/zou-group/CellVoyager

💡IMO one of the best use of AI Scientist is to reanalyze data to find new insights.

Introducing #CellVoyager: AI Compbio Agent that makes new discoveries by autonomously analyzing papers/data, which we then validate🚀

New findings on aging, Covid, scRNAseq etc. Open source!

Very cool work from James Zou. Link to paper: www.nature.com/articles/s41...

Excited that nuclei.io is featured on the cover of Nature BME! AI-clinician collaboration paper rdcu.be/dLgV1

We discuss how to conduct intersectional analysis in science and technology in @nature.com
nature.com/articles/s41...

I learned a ton from working w/ dream team co-authors! Great job by Londa Schiebinger + Mathias Nielson leading this project 👏 Also thanks @meharpist.bsky.social for guidance!

Here's the non-paywall version of our #TextGrad paper rdcu.be/efRp4! 📜

SCI member @jameszou.bsky.social & others present a method for genAI self-improvement via a new calculus of text. They show TextGrad’s power in optimizing agents, molecules, code, treatments, & more, solving PhD-level problems and enabling impactful #AI development. www.nature.com/articles/s41...

Optimizing generative AI by backpropagating language model feedback - Nature Generative artificial intelligence (AI) systems can be optimized using TextGrad, a framework that performs optimization by backpropagating large-language-model-generated feedback; TextGrad enable...

Scholars developed a versatile framework called TextGrad to improve complex AI systems by leveraging natural language feedback. @jameszou.bsky.social

Read more about this research supported by @stanfordhai.bsky.social in a new paper published in Nature: www.nature.com/articles/s41...

Tiny satellite sets new record for secure quantum communication Hear the biggest stories from the world of science | 19 March 2025

I had a lot of fun discussing #textgrad on the @nature.com podcast with @climateadam.bsky.social! It starts at around 12 minutes here www.nature.com/articles/d41...

Tiny satellite sets new record for secure quantum communication Hear the biggest stories from the world of science | 19 March 2025

Thrilled to be back on The @nature.com Podcast!

Covering a nifty approach to give feedback to AI systems using normal speech.

www.nature.com/articles/d41...

Optimizing generative AI by backpropagating language model feedback - Nature Generative artificial intelligence (AI) systems can be optimized using TextGrad, a framework that performs optimization by backpropagating large-language-model-generated feedback; TextGrad enable...

💡The key idea of #textgrad is to optimize by backpropagating textual gradients produced by #LLM

Paper: www.nature.com/articles/s41...
Code: github.com/zou-group/te...

Amazing job by Mert Yuksekgonul leading this project w/ Fede Bianchi, Joseph Boen, Sheng Liu, Pan Lu, Carlos Guestrin, Zhi Huang

⚡️Really thrilled that #textgrad is published in @nature.com today!⚡️

We present a general method for genAI to self-improve via our new *calculus of text*.

We show how this optimizes agents🤖, molecules🧬, code🖥️, treatments💊, non-differentiable systems🤯 + more!

Purple gradient background with a medication tablet illustration on the bottom left. At the top, the text reads: “AI-driven in silico drug screening ... represents a substantial leap beyond traditional experimental or animal testing, offering a more efficient and cost-effective pathway by preemptively identifying possible shortcomings of drug candidates.” On the middle right, the text states: Yildirim Z, Swanson K, Wu X, Zou J, Wu J. Next-gen therapeutics: Pioneering drug discovery with iPSCs, genomics, AI, and clinical trials in a dish. Annu Rev Pharmacol Toxicol. 2025;65(1):71-90. doi:10.1146/annurev-pharmtox-022724-095035. The SAO logo, in purple, is at the bottom left.

Great review by @jameszou.bsky.social & colleagues from @stanfordmedicine.bsky.social on how integrating #iPSC technology with #AI can accelerate therapeutic discovery, enhance drug screening & advance personalized medicine. 🧪 #medsky www.annualreviews.org/content/jour...

Thank you Anne!

Introducing MedArena medarena.ai/app/?__theme... for clinicians to ask medical questions and compare results of LLM models @jameszou.bsky.social @doximity.bsky.social

How it works: For each medical query, you’ll get responses from two randomly selected LLMs and choose the one you prefer. #MedArena then aggregates all the clinicians’ feedback to rank medical chatbots.

Go to medarena.ai to find out which LLMs you prefer!

📢Thrilled to introduce #MedArena medarena.ai 🏥, a platform for clinicians to try frontier #LLMs for free (o3, Gemini, Perplexity + more).

Compare and rank medical chatbots and help shape the future of medical AI! 🏆 Current leaderboard👇

Please share #MedSky

Incredibly grateful and honored to receive the 2025 Overton Prize ♥️

Surreal to follow the steps of my science heroes🙏 Truly, credit goes to my amazing students, collaborators and mentors who make research so inspiring!

Also underscores the value of open academic environment that make this possible

New A.I. models in spatial omics
—singe cell GPT @bowang87.bsky.social
www.biorxiv.org/content/10.1...
—CORAL @jameszou.bsky.social
www.biorxiv.org/content/10.1...
These are coming along incredibly fast and helping us learn the language of life
www.science.org/doi/10.1126/... @science.org