← All speakers

James Zou

Conference affiliation: Together AI · 2026

James Zou leads the Stanford AI for Science Lab and is an associate professor of biomedical data science, with courtesy appointments in computer science and electrical engineering. His research connects statistically rigorous machine learning with applications in science and human health. Across data valuation, medical-model evaluation, and scientific agents, he examines how AI systems can learn from feedback that tests whether their results are useful.

On this page

From applied mathematics to scientific AI

Zou studied mathematics and physics at Duke, pursued advanced mathematics at Cambridge, and completed his doctorate at Harvard. After a Simons fellowship at UC Berkeley and work at Microsoft Research, he joined Stanford in 2016. His research there spans machine-learning theory, genomics, and medicine. He received Chan–Zuckerberg Biohub Investigator awards in 2017 and 2023.

With Amirata Ghorbani, Zou introduced Data Shapley in 2019 to estimate how individual training examples contribute to a model’s predictive performance. The framework makes data quality a question about a particular learning task: which examples help the predictor, which may be corrupted, and what additional data would improve it? This gives researchers a way to assess a dataset beyond its size and make more informed decisions about cleaning and acquisition.

His medical collaborations show why those distinctions matter. With Roxana Daneshjou and colleagues, Zou co-authored the Diverse Dermatology Images study, using clinically curated, biopsy-confirmed skin lesions spanning different skin tones. Their 2022 study found weaknesses in leading dermatology models, especially on darker skin and uncommon diseases. Fine-tuning with the diverse images reduced performance disparities. The result connected model reliability to the patients and conditions represented in training and evaluation data.

Zou also co-authored the original 2019 Gradio paper. Its browser interfaces let people test machine-learning models without setting up a specialist computing environment. For interdisciplinary work, that makes expert feedback easier to obtain: a physician or other domain specialist can supply realistic inputs, inspect predictions, and identify problems directly.

Feedback that changes the system

As language models became capable of using tools and carrying out extended analyses, Zou’s collaborative research expanded to systems that revise their work, coordinate expertise, and test proposed solutions. TextGrad, published in Nature in 2025, propagates written feedback through systems containing language models and other tools. A critique of a final result can guide revisions to the earlier components that produced it. Its applications include prompts, code, molecules, and radiotherapy treatment plans, extending optimization to objects scientists and engineers can inspect and change. The open-source framework makes this feedback process available for experimentation.

Virtual Lab applies agent collaboration to interdisciplinary research. Zou and John Pak co-supervised the work; Kyle Swanson built the framework and computational design pipeline, and experimental collaborators tested the resulting nanobodies. A principal-investigator agent coordinates scientist agents through research meetings, while a human supplies high-level feedback. For SARS-CoV-2 nanobody design, the agents assembled a pipeline combining ESM, AlphaFold-Multimer, and Rosetta. The team designed 92 candidates, and laboratory experiments identified functional binders, including two with improved binding to newer variants. Those experiments supplied a physical check on the computational proposals; the candidates remained subjects for further investigation.

Environments for collective intelligence

Zou’s scientific-agent work with Together AI, in collaboration with Stanford, develops an argument for environments for collective intelligence. His concern is that prescribed workflows can constrain increasingly capable agents. An environment instead supplies problems, resources, incentives, guardrails, and feedback, leaving agents more freedom to choose how to work. EinsteinArena and DSGym develop this idea through different kinds of executable evaluation.

James developed EinsteinArena with Federico Bianchi, Yongchan Kwon, and Aneesh Pappu so agents could submit solutions for automated checks and build on one another’s attempts. By sharing and refining candidate solutions, agents raised the known lower bound for the 11-dimensional kissing-number problem from 593 to 604. Their construction showed that at least 604 equal spheres can touch a central sphere of the same size without overlapping one another.

James and his DSGym collaborators found that agents could answer some existing data science benchmark questions without examining the datasets. They curated tasks that required agents to work with the underlying data, then ran the agents’ code to check the results. Successful attempts could then serve as training examples for smaller models.

Read the topics behind these talks

1 conference talk

Loading more talks and highlights…

References