top of page



Hi! I am an Associate Professor of Biomedical Data Science and, by courtesy, of Computer Science and Electrical Engineering at Stanford University. I work on making machine learning more reliable, human-compatible and statistically rigorous, and am especially interested in applications in human disease and health. Several of our algorithms are widely used in tech and biotech industries. I received a Ph.D from Harvard in 2014, and was a member of Microsoft Research, a Gates Scholar at Cambridge and a Simons fellow at UC Berkeley. I joined Stanford in 2016 and am excited to be a two-time Chan-Zuckerberg Investigator and the faculty director of the university-wide Stanford Data4Health hub. I'm also a member of the Stanford AI Lab. My research is supported by the Sloan Fellowship, the NSF CAREER Award, and Google, Amazon and Adobe AI awards

Email: jamesz at stanford dot edu                   Office: Packard 369


6/24: check out TextGrad, our PyTorch-for-text framework to optimize AI agents! published in Nature BME. AI model card analysis published in Nature Machine Intelligence.

5/24: EchoNet AI has received FDA clearance! 

5/24: 12 new ICML papers. Check it out here!

4/24: NEJM AI paper on the economics of medical AI. TMLR papers on watermarking and membership inference.

3/24: SyntheMol published in Nature Machine Intelligence (genAI for small molecule drugs).

2/24: Alignability testing in PNAS; off-label cancer drugs study in Cell Reports Medicine.

2/24: TISSUE: uncertainty-aware spatial transcriptomics published in Nature Methods

1/24: New ICLR papers on DataInf, LLM safety-training, analyses of datacards and zoology

1/24: New NEJM AI  paper using LLM to simplify medical consent for patients. 

12/23: Contrastive feature learning published in JMLR

11/23: Excited to co-organize the ML in Compbio Conference.

10/23: New NEJM AI  paper studies clinical adoption of AI using billions of insurance claims.

9/23: New Neurips papers on 1) OpenDataVal; 2) atypicality; 3) AI art on Twitter; 4) DataPerf 5) factorized contrastive learning

9/23: New npj Digital Medicine papers on predicting cardiovascular risk and assessing dermatology textbooks

8/23: New in Nature Medicine: we used Twitter data to build a visual-language AI for pathology.   

7/23: New Science paper on implications of AI-predicted race variables. Patterns paper shows that GPT detectors are biased against non-native speakers. 

5/23: See our Nature Biotech paper on who counts as an inventor. In silico spatial proteomics with 7-UP published in PNAS Nexus. Proteomic biomarkers of resilience to Alzheimer's published in Nature Communications.

4/23: 4 new ICML papers on data valuation with Data-OOB, moon-shaped correlation of ML performances, provable subgroup-discovery, and discover-and-cure spurious correlations.   

4/23: EchoNet randomized clinical trial published in Nature. Generative AI amplifies human bias published in FAccT.

3/23: New Cell  paper on advances in ML for cancer. Play our ArtWhisperer game and see how good you are at human-AI collaboration! Point-of-care EchoNet published. TrueImage clinical study public in JAMA Dermatology.

2/23: MetaViz published in Nature Communications (also selected for Outstanding Paper Award at 2023 Joint Statistics Meeting); EchoNet-Ped published in JASEJoined the editorial board of New England Journal of Medicine AI.

1/23: 5 new ICLR papers on: why vision-language models act like bag-of-words (top 2%); post-hoc concept bottleneck (top 10%); fair classifier on imbalanced data; fair classifier with small samples; and DrML. 2 new AISTATS papers on understanding multimodal contrastive learning and freeze-and-train 

1/23: Dynamic Visualization published in Nature Computational Science; dog precision cancer paper published in npj Precision Oncology.

11/22: SpaceGM (GNN for spatial proteomics) published in Nature Biomedical Engineering.

9/22: 7 new NeurIPS papers on: improving SHAP attribution; human-AI collaboration, sparse data shifts, modality gap, mixReg augmentation, SkinCon, and history of ML API shifts.   

8/22: Science Advances paper on disparity in skin cancer AI and new Diverse Derm data; Nature Machine Intelligence article on data-centric AI; analysis of 50 years of Stanford research commercialization published in Patterns

6/22: new Nature Medicine paper on precision cancer treatment.

5/22: 4 new ICML papers: explaining AI mistakes, using ML cheaply w/ frugalMCT, improving calibration w/ mix-up, and better robustness with selective augmentation.

5/22: RNA-ODE published in J. Molecular Biology; f-gan in ISIT; human-AI advice in AIES.  

4/22: Very honored that Trial Pathfinder is selected as a Top Ten Clinical Research Achievement.  

4/22: In silico IHC published in Cell Reports Methods, DynaMorph in Mol. Bio. Cell and evaluation of COVID data reporting in PLoS Global Health, forecasting clinical trial efficiency in AAPS.  

1/22: 3 new ICLR papers: MASA assesses model shifts; Domino finds fine-grained mistake clusters in AI (oral); MetaShift offers a resource of 1000s of distribution shifts.   

1/22: 3 new AISTATS papers: Beta-Shapley improves and unifies data valuation (oral); MLDemon

monitors ML performance over time; adapt ML to users with gradual performative gradient.  

1/22: Honored to be selected as a Chan-Zuckerberg Investigator for the 2nd term. 

10/21: NeurIPS paper shows adversarial training improves transfer learning; EBioMed paper infers biomarkers from cardiac videos; 2 PSB papers predict diseases from scRNA-seq and eye-motion

9/21: New JAMA Dermatology paper quantifies limitations in datasets used for derm AIs.  

6/21: New Nature Biotech paper uses patent citations to quantify research translational impact. Study of GPT-3 biases published in Nature Machine Intelligence.


5/21: ICML papers on performative gradient descent and task augmentation for meta-learning.

4/21: BABEL published in PNAS and new single-cell aging score published in eLife.

4/21: Our Nature paper uses real-world data and AI to make clinical trials more inclusive.


4/21: Our Nature Medicine paper identifies limitations in how medical AI are evaluated. 


2/21: Honored to receive the Sloan Research Fellowship 

1/21: 5 new papers at 2021 AISTATS and ICLR: how competition over data affects ML; how to use cheap unlabeled data to make models more robust; efficient data Shapley computation; how to delete data from trained predictors; and mixup as regularization.   

10/20: TrueImage improves photo quality for telehealth (PSB paper). ALICE shows how to use natural language explanation of contrasts to efficiently teach ML (EMNLP paper).    

9/20: FrugalML, Neuron Shapley and MOPO are accepted at NeurIPS. FrugalML selected for oral presentation as top 1% of submissions. 

7/20: Single-cell characterization of aging effects published in Nature

6/20: Our AI to generate spatial transcriptome from histology is in Nature Biomedical Engineering

6/20: Excited and honored to received the NSF CAREER Award!


6/20: New papers: statistical data value (ICML), improving dialogue systems (ACL), learning data alignment (ICLR), deep learning for proteomics (J. Proteomics), RNA-GPS (RNA), linking variants to genes (Bioinformatics), and SARS-CoV-2 subcellular localization (Cell Systems). 

3/20: Our video AI system to assess heart function is published in Nature

1/20: Our interactive ML platform is published in Nature Machine Intelligence.

11/19: Our paper on how sex and gender analysis improves science and engineering is in Nature.

9/19: Our papers on deleting data from ML (spotlight) and learning human meaningful concepts will be presented at NeurIPS.

7/19: Our machine learning for genome editing paper is published in Nature Biotechnology.  


5/19: AdaFDR won the RECOMB Best Paper. Extended version in Nature Communications.         


5/19: At ICML we'll present papers on data valuationconcrete autoencoderconditional features and adaptive Monte Carlo.    


4/19: Check out our two knockoff papers in AISTATS


2/19: Interpretation of neural network is fragile in AAAI and VetTag in Nature Digital Medicine.         

1/19: Feedback GAN for protein design published in Nature Machine Intelligence.                                                                           

11/18: Check out our interactive deep learning for genomics primer in Nature Genetics.  

9/18: Excited to receive a NIH Center for Excellence in Genomics and a NIH R21. 


7/18: Our paper on designing fair AI is published in Nature.  

6/18: Honored to receive a Google Faculty Award and a Tencent AI award.


4/18: NLP reveals 100 years of stereotypes is published in PNAS and highlighted in Science. 

bottom of page