Sign in

James Zou

@jameszou.bsky.social
2.3K followers 12 following 52 posts

@Stanford Professor. AI for science and medicine.

PostsRepliesMedia
Reposted by James Zou
Biohub @biohub.org · 24/09/2026
Biohub Investigator @jameszou.bsky.social built a “virtual biotech”—37K AI agents that analyzed 57K clinical trials and found clues to what makes drugs succeed. The New York Times traces its roots to a collaboration sparked by our scientist John Pak: bit.ly/4hLrpnm
141
James Zou @jameszou.bsky.social · 24/08/2026
string2string is super fun and useful! Compare and visualize texts and sequences in your browser. Accepted as an EMNLP demo. Great job @msuzgun.bsky.social!
020
Reposted by James Zou
Mirac Suzgun @msuzgun.bsky.social · 05/08/2026
1/ Today, @jameszou.bsky.social, Professor Shieber, @jurafsky.bsky.social and I are releasing string2string Studio: an open-source, in-browser platform that brings alignment, comparison, search, and evaluation into one interactive, visual environment for strings and sequences. See: string2string.org
153
James Zou @jameszou.bsky.social · 31/07/2026
Happy to share our new Circulation article discussing agentic and generative AI for drug discovery 💊 www.ahajournals.org/doi/full/10.... Great job by Jake Silberg, Peter Eckmann, Joseph Boen! Also thanks to Bradley Maron for helpful guidance.
020
James Zou @jameszou.bsky.social · 14/07/2026
Bio databases/APIs weren't designed for AI agents 🧬 So we expanded #Paperclip to transform common molecular databases—UniProt, PDB, ChEMBL—into a unified agent-native virtual filesystem. Now you can do deep research across 10^6 molecules much more accurately and 10x faster! gxl.ai/blog/adding-...
040
Reposted by James Zou
Molecular Systems Biology @molsystbiol.org · 12/06/2026
6/2026 Issue ➡️ link.springer.com/journal/4432... plasmid-free protein engineering, #DMS analysis, microbial surface functionalization, glioma cell interactions, viral mimic evolution Cover: generative AI for antibiotic synthesis design by Jonathan Stokes and @jameszou.bsky.social labs
031
James Zou @jameszou.bsky.social · 22/06/2026
Thank you @molsystbiol.org for highlighting SyntheMol-RL on the June cover!
010
James Zou @jameszou.bsky.social · 25/05/2026
We added >220K FDA regulatory and >1M clinical trial docs to #paperclip. All natively indexed for agents and free. Now agents can easily reason over clinical studies w/o web search! E.g: find all trials that were approved despite missing endpoint gxl.ai/blog/adding-...
072
Reposted by James Zou
OncoDaily @oncodaily.bsky.social · 23/05/2026
Paperclip Expands With 220K+ FDA Regulatory and 1M+ Clinical Trial Documents - James Zou @jameszou.bsky.social oncodaily.com/voices/james... #OncoDaily #Oncology #Cancer #Health #Medicine
oncodaily.com
James Zou: Paperclip Expands With 220K+ FDA Regulatory and 1M+ Clinical Trial Documents - OncoDaily
James Zou: Paperclip Expands With 220K+ FDA Regulatory and 1M+ Clinical Trial Documents / cancer, James Zou, OncoDaily, Oncology, Paperclip
031
Reposted by James Zou
Emily R. Trunnell, Ph.D. @ertrunnell.bsky.social · 07/05/2026
In this review, Wu et al., including @jameszou.bsky.social, give an overview of recent advances in cellular models, microphysiological systems, computational approaches, & other #NAMs driving the human-centric shift in drug development & biomedical research. 🧪
121
James Zou @jameszou.bsky.social · 01/05/2026
#paperclip now includes full papers from all of arXiv, PubMed Central and 150 million abstracts! 🖇️ Give your LLM all that knowledge in one line—all natively indexed for agents. 100x faster than web search and free. Install: curl -fsSL paperclip.gxl.ai/install.sh | bash Blog: gxl.ai/blog/adding-...
042
James Zou @jameszou.bsky.social · 20/04/2026
Excited to share our new papers at #ICLR2026 on (multi-)agents, efficient reasoning, long context, better tokenizers and scientific applications 🚀 My awesome students and collaborators will be presenting them at the main conference this week; check it out! 👇
041
Reposted by James Zou
Gal Sapir @sapir.bsky.social · 14/04/2026
been using the paperclip.gxl.ai by @jameszou.bsky.social and im just blown away but how much better it makes cc as a research assistant. i feel like they solved something smoothly. an elegant example of 'you need to translate problems to something that a CLI solves'. researchers - try it
paperclip.gxl.ai
Paperclip
Paperclip — search, read, and analyze 8M+ biomedical papers from the command line.
011
Reposted by James Zou
European Medical Journal @emjreviews.com · 14/04/2026
Did you know AI can predict disease from just one night’s sleep? According to @jameszou.bsky.social , AI models can analyse sleep data to predict over 100 different diseases. Explore the interview: t.co/qA1fUODuGC t.co/OhrbWuigDW
5176
Reposted by James Zou
VivienM @vivienm.bsky.social · 18/03/2026
In CellVoyager from @jameszou.bsky.social and teams AI agents pore over published papers. Seems intriguing to naive me that it can "uncover missing insights by autonomously analyzing biological data at scale. " 1/n www.nature.com/articles/s41...
nature.com
CellVoyager: AI CompBio agent generates new insights by autonomously analyzing biological data - Nature Methods
CellVoyager is an artificial intelligence agent capable of exploring new biological hypotheses by autonomously analyzing single-cell RNA sequencing datasets and accounting for background information a...
121
Reposted by James Zou
Eric Topol @erictopol.bsky.social · 26/02/2026
The data from sleep is incredibly rich, a window into health and risk of many diseases, decoded by AI. Our new essay today @jameszou.bsky.social @thelancet.com thelancet.com/journals/lan...
thelancet.com
Decoding the language of sleep with artificial intelligence
Sleep is one of medicine's underused data streams. Clinically, disturbed sleep has often been treated as a symptom of a disorder, but sleep is also a physiological state in which brain, cardiac, respi...
28925
Reposted by James Zou
Kaitlyn Zhou @kaitlynzhou.bsky.social · 17/02/2026
As speech models are being deployed in real-world taxi and emergency service settings, the failure to accurately transcribe named entities can cause delays and errors in critical settings.
121
Reposted by James Zou
BrunetLab @brunetlab.bsky.social · 13/02/2026
We have posted a Research Assistant (LSRP1) position to work on aging and 'rejuvenation' using mouse models!! 🐭 careersearch.stanford.edu/jobs/life-sc... Apply and join our awesome lab!! (please share) 😎
01411
James Zou @jameszou.bsky.social · 10/02/2026
What do LLMs think about on their own, when we let them think freely? We generated 250K “daydream” samples across models 🧠 GPT → coding Qwen → multiple-choice math exams Llama → literature DeepSeek → math, religion, psychology
020
James Zou @jameszou.bsky.social · 19/01/2026
#Squidiff is highlighted on the cover of Nature Methods! Read about our diffusion model for single cells www.nature.com/articles/s41... Great job Siyu He and all the wonderful collaborators!
041
James Zou @jameszou.bsky.social · 18/01/2026
🏆 Thank you @cp-patterns.bsky.social for selecting our work on LLM-assisted writing across society as a Best Paper of 2025! info.cell.com/collection-r...
info.cell.com
Patterns | Cell Press
060
James Zou @jameszou.bsky.social · 11/01/2026
Nice Stanford article discussing our SleepFM AI: predicting diseases while you sleep news.stanford.edu/stories/2026...
news.stanford.edu
AI model predicts disease risk while you sleep
The first artificial intelligence model of its kind can predict more than 100 health conditions from one night’s sleep.
181
Reposted by James Zou
Eric Topol @erictopol.bsky.social · 06/01/2026
The first sleep AI foundation model for predicting diseases was published today @naturemedicine.bsky.social by @jameszou.bsky.social and colleagues nature.com/articles/s41... With Notebook LM, I made this infographic that tells the rich story pretty well
49222
James Zou @jameszou.bsky.social · 31/12/2025
Thanks to Nature Methods for highlighting AI agents for biology (and the Virtual Lab) as a 2025 Method to Watch! www.nature.com/articles/s41...
nature.com
Artificial intelligence agents for biology - Nature Methods
Artificial intelligence agents may have a transformative effect on how biological research is performed.
090
Reposted by James Zou
Nature Biotechnology @natbiotech.nature.com · 17/12/2025
Exploring the use of AI authors and reviewers at Agents4Science - @jameszou.bsky.social go.nature.com/4j1O7a3
go.nature.com
Exploring the use of AI authors and reviewers at Agents4Science - Nature Biotechnology
Nature Biotechnology - Exploring the use of AI authors and reviewers at Agents4Science
033
Reposted by James Zou
JCDL 2025 @jcdl2025.bsky.social · 04/12/2025
📣📣📣 Our second keynote speaker works on developing cutting-edge AI for biomedical applications. We're pleased to have James Zou (@jameszou.bsky.social) talk about "AI agents to accelerate scientific discoveries." To know more about the talk, check out: 2025.jcdl.org/keynotes/
032
Reposted by James Zou
Irving Institute for Cancer Dynamics @cancerdynamics.bsky.social · 10/11/2025
New paper out in @natmethods.nature.com from @elhamazizi.bsky.social, Kam Leong & @jameszou.bsky.social! The team developed Squidiff, a diffusion #AI model to predict cellular responses to environmental cues and accelerate #PrecisionMedicine. Learn more: bit.ly/3WRPNsx
Schematic of cell differentiation prediction (a) and drug response prediction (b).
185
Reposted by James Zou
Nature Portfolio @natureportfolio.nature.com · 03/11/2025
Large language models (LLMs) may not reliably acknowledge a user’s incorrect beliefs, according to a paper in Nature Machine Intelligence. The findings highlight the need for careful use of LLM outputs in high-stakes decisions. go.nature.com/48VRpIQ 🧪
This is figure 1, which shows LMs struggle to affirm first-person beliefs in factually false scenarios.
03110
James Zou @jameszou.bsky.social · 23/10/2025
It’s here! #Agents4Science recording is now on YouTube! 🏆 3 Best Paper talks ⚡️ 11 Spotlights 🧠 Panel on the future of AI agent-driven science 📚 Lessons + surprises from this first-of-its kind conf Full analysis of submissions + reviews coming soon! youtube.com/watch?v=7pXq...
030
Reposted by James Zou
Elizabeth Gibney @lizziegibney.bsky.social · 15/10/2025
Next week @jameszou.bsky.social & colleagues will host a conference where all the papers are written by AI agents & reviewed by them too. What do you reckon? A good chance to put AIs through their paces? Or a way to divert AI slop from elsewhere? 🧪🤖 My story here: www.nature.com/articles/d41...
nature.com
AI bots wrote and reviewed all papers at this conference
Event will assess how reviews by models compare with those written by humans.
0122
Reposted by James Zou
Kaitlyn Zhou @kaitlynzhou.bsky.social · 21/10/2025
As of June 2025, 66% of Americans have never used ChatGPT. Our new position paper, Attention to Non-Adopters, explores why this matters: AI research is being shaped around adopters—leaving non-adopters’ needs, and key LLM research opportunities, behind. arxiv.org/abs/2510.15951
A circular flow diagram that compares current and proposed practices for LLM development using data from adopters and non-adopters. Three gray boxes represent current practices: “R&D,” “Chat Models,” and “Adopters’ Needs and Usage Data,” connected in a clockwise loop with black arrows. A blue box labeled “Non-adopters’ Needs and Usage Data” adds a proposed feedback path, shown with blue arrows, linking non-adopter data back to R&D and adopters’ data.
23912
Reposted by James Zou
Juan Peces @juanpeces.bsky.social · 09/10/2025
"We found a troubling emergent behavior in LLM. —When LLMs compete for social media likes, they start making things up. —When they compete for votes, they turn inflammatory/populist. —When optimized for audiences, LLMs inadvertently become misaligned." → Moloch's Bargain @jameszou.bsky.social #AI
051
Reposted by James Zou
Cell Press @cellpress.bsky.social · 02/10/2025
#AI wrote nearly a quarter of corporate press releases in 2024 and the number is likely to keep rising. spkl.io/63324ATfBo Weixin Liang, @jameszou.bsky.social & colleagues @cp-patterns.bsky.social
First page of article: "The widespread adoption of large language model-assisted writing across society" published in Patterns
083
Reposted by James Zou
Andy Tseng @andytseng.bsky.social · 11/09/2025
Fantastic talk by @stanford.edu's @jameszou.bsky.social for the first Innovation Initiative Distinguished Lecture at @whiteheadinstitute.bsky.social. A fascinating look at how to use #AI to build intelligent research teams that can tackle open-ended scientific problems. #WhiteheadInstitute #MIT
032
James Zou @jameszou.bsky.social · 12/08/2025
🧠Can AI agents predict #Alzheimers? Participate in our DREAM challenge agentic track to find out! We provide unique training + test data for AI agents: snRNA-seq, IHC, stage, etc synapse.org/Synapse:syn6... Also co-submit your agent paper to agents4science.stanford.edu
153
Reposted by James Zou
Stanford HAI @stanfordhai.bsky.social · 11/08/2025
“Good science happens when we have deep, interdisciplinary collaborations, and often that’s one of the main bottlenecks and challenging parts of research,” said HAI Faculty Affiliate @jameszou.bsky.social who led a study on AI-driven virtual labs: med.stanford.edu/news/all-new...
med.stanford.edu
Researchers create ‘virtual scientists’ to solve complex biological problems
Stanford Medicine researchers created a team of virtual scientists backed by artificial intelligence to help solve problems in their real-world lab.
042
James Zou @jameszou.bsky.social · 31/07/2025
Nice @stanforduniversity.bsky.social article profiling our #VirtualLab of AI scientists news.stanford.edu/stories/2025...
news.stanford.edu
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.
050
Reposted by James Zou
NEJM AI @ai.nejm.org · 30/07/2025
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
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.
011
James Zou @jameszou.bsky.social · 29/07/2025
⚡️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.
2276
Reposted by James Zou
Eric Topol @erictopol.bsky.social · 29/07/2025
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...
2396
Reposted by James Zou
Damir Baranasic @da-bar.bsky.social · 22/07/2025
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 💻🤖
052
Reposted by James Zou
NEJM AI @ai.nejm.org · 23/07/2025
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
Figure 1. An Overview of the Fine-Tuning Case Study.
032
James Zou @jameszou.bsky.social · 15/07/2025
🏆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
021
James Zou @jameszou.bsky.social · 07/07/2025
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...
nature.com
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.
022
Reposted by James Zou
Hanlin Zhang @hlzhang109.bsky.social · 02/07/2025
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)
arxiv.org
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, ...
131
James Zou @jameszou.bsky.social · 05/06/2025
💡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!
131
Reposted by James Zou
Sten Linnarsson @sten.linnarsson.org · 28/05/2025
Very cool work from James Zou. Link to paper: www.nature.com/articles/s41...
nature.com
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...
041
James Zou @jameszou.bsky.social · 22/04/2025
Excited that nuclei.io is featured on the cover of Nature BME! AI-clinician collaboration paper rdcu.be/dLgV1
010
James Zou @jameszou.bsky.social · 10/04/2025
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!
nature.com
Intersectional analysis for science and technology - Nature
This Perspective offers a guide for researchers, peer-reviewed journals and funding agencies to make quantitative intersectional approaches a standard part of science and technology research design, w...
0101