Sean Wu

I'm a first year Ph.D. student in Computer Science at Stanford University. My research focuses on the reliability of AI agents and how to make them trustworthy in science and medicine.

Previously, I was a Rhodes Scholar at the University of Oxford, where I was advised by David Clifton and worked with the Torr Vision Group. I studied CS and Math at Pepperdine, advised by Fabien Scalzo, and previously worked with James Zou at Stanford. I've been awarded the NSF GRFP and the Goldwater Scholarship.

Email Scholar GitHub Twitter

Aug 2026

newGeometric Uncertainty for LLM hallucinations accepted to TMLR.

July 2026

newBehavioral Alignment Score (BAS) accepted to COLM 2026.

June 2026

newSemantic Self-Distillation accepted to UAI 2026.

May 2026

newReleased CUSP, forecasting scientific progress with AI, featured in the Top 10 AI Papers of the Week.

May 2026

newBioMedArena: open-source toolkit for biomedical deep-research agents.

May 2026

newMedMisBench: measuring epistemic resilience of LLMs under misleading medical context.

Apr 2026

New paper introducing the Behavioral Alignment Score for LLM confidence evaluation.

Mar 2026

Invited talk "Towards Reliable AI in an Agentic Era" at the Waves Innovation Summit. slides

Feb 2026

Paper on Semantic Self-Distillation for LLM uncertainty on arXiv.

Jan 2026

Paper on AI protein structure/function accepted to Nature Reviews Nephrology.

Dec 2025

Paper on glaucoma progression prediction accepted to American Journal of Ophthalmology.

Nov 2025

Received a Tinker Research Grant from Thinking Machines Lab.

Sep 2025

First paper from Oxford on detecting and correcting LLM uncertainty.

May 2025

Pepperdine Outstanding Division Researcher and Outstanding Natural Science Student.

Apr 2025

Awarded the NSF Graduate Research Fellowship.

Nov 2024

Selected as Pepperdine's first Rhodes Scholar. article

Feb 2024

Medical LLM research featured in ZDNET. article

Dec 2023

CRA Outstanding Undergraduate Researcher Honorable Mention.

Mar 2023

Awarded the Barry Goldwater Scholarship.

★ selected work · * equal contribution

AI for Science 2 papers

Forecasting Scientific Progress with Artificial Intelligence

Sean Wu*, Pan Lu*, Yupeng Chen, Jonathan Bragg, Yutaro Yamada, Peter Clark, David Clifton, Philip Torr, James Zou, Junchi Yu

arXiv preprint, 2026

arXiv Code Data

Bridging Structure and Function: AI-Based Modelling of Kidney Proteins

Sean Wu, Weiguang Wang, Z. Hong Zhou, Fabien Scalzo, Ira Kurtz

Nature Reviews Nephrology, 2026

Paper

Language Models & Reliability 8 papers

BAS: A Decision-Theoretic Approach to Evaluating Large Language Model Confidence

Sean Wu*, Fredrik K. Gustafsson*, Edward Phillips, Boyan Gao, Anshul Thakur, David A. Clifton

COLM 2026

arXiv Code

BioMedArena: An Open-source Toolkit for Building and Evaluating Biomedical Deep Research Agents

Jinge Wu*, Hongjian Zhou*, Mingde Zeng, Jiayuan Zhu, Junde Wu, Jiazhen Pan, Sean Wu, Honghan Wu, Fenglin Liu, David A. Clifton

arXiv, 2026

arXiv Code

MedMisBench: Measuring Epistemic Resilience of LLMs Under Misleading Medical Context

Hongjian Zhou*, Xinyu Zou*, Jinge Wu*, Sean Wu, et al., Fenglin Liu, David A. Clifton

bioRxiv, 2026

bioRxiv Code

Semantic Self-Distillation for Language Model Uncertainty

Edward Phillips, Sean Wu, Boyan Gao, David Clifton

UAI 2026

arXiv

Geometric Uncertainty for Detecting and Correcting Hallucinations in LLMs

Edward Phillips*, Sean Wu*, Soheila Molaei, Danielle Belgrave, Anshul Thakur, David Clifton

TMLR, 2026

arXiv

Entropy Alone is Insufficient for Safe Selective Prediction in LLMs

Edward Phillips, Fredrik K. Gustafsson, Sean Wu, Anshul Thakur, David A. Clifton

arXiv, 2026

arXiv

Self-Improving Clinical Reasoning via Textual Gradients

Sean Wu, Michael Koo, Fabien Scalzo, Ira Kurtz

ICLR 2026 Workshop on AI Recursive Self-Improvement

OpenReview

Adversarial Databases Improve Success in Retrieval-based Large Language Models

Sean Wu, Michael Koo, Liyo Kao, Andy Black, Lesley Blum, Fabien Scalzo, Ira Kurtz

NeurIPS 2024 Workshop on Adversarial ML spotlight (top 21%)

OpenReview

Benchmarking Open-Source LLMs, GPT-4, and Claude 2 on Multiple-Choice Questions in Nephrology

Sean Wu, Michael Koo, Lesley Blum, Andy Black, Zhe Fei, Fabien Scalzo, Ira Kurtz

NEJM AI, Vol. 1 No. 2, 2024

Paper

Neurovascular 3D Reconstruction 2 papers

Fourier Feature Network for 3D Vessel Reconstruction from Biplane Angiograms

Sean Wu, Kaneko Naoki, David S. Liebeskind, Fabien Scalzo

Journal of Machine Vision and Applications, 2024

Paper

3D Reconstruction from 2D Cerebral Angiograms as a Volumetric Denoising Problem

Sean Wu, Kaneko Naoki, Steve Mendoza, David S. Liebeskind, Fabien Scalzo

International Symposium on Visual Computing, 2023

Paper

Deep Learning in Medical Imaging 5 papers

An AI-Based Prognostic Model for Functional Glaucoma Progression from Clinical and Structural Data

Vahid Mohammadzadeh, Sean Wu, Sajad Besharati, et al., Kouros Nouri-Mahdavi

American Journal of Ophthalmology, 2026

Paper

Predicting Visual Field Progression from Baseline and Longitudinal Structural Measurements with Deep Learning

Vahid Mohammadzadeh, Sean Wu, Tyler Davis, et al., Kouros Nouri-Mahdavi

American Journal of Ophthalmology, 2024

Paper

Denoising Visual Field Data via Self-Supervised Masked Autoencoders for Glaucoma Progression Detection

Sean Wu, Vahid Mohammadzadeh, Jun Yu Chen, Jaewon Lee, Kouros Nouri-Mahdavi, Joseph Caprioli*, Zhe Fei*, Fabien Scalzo*

arXiv preprint, 2024

arXiv

Prediction of Visual Field Progression with Serial Optic Disc Photographs Using Deep Learning

Vahid Mohammadzadeh, Sean Wu, Tyler Davis, Arvind Vepa, Esteban Morales, et al., Kouros Nouri-Mahdavi

British Journal of Ophthalmology, 2023

Paper

Auxiliary-Domain Learning for a Functional Prediction of Glaucoma Progression

Sean Wu, Vahid Mohammadzadeh, Kiumars Edalati, Jack Martinyan, Arthur Martinyan, Joseph Caprioli, Kouros Nouri-Mahdavi, Fabien Scalzo

Int'l Workshop on Ophthalmic Medical Image Analysis, 2023

Paper Video

Prediction of Central Visual Field Measures from Macular OCT Volume Scans with Deep Learning

Vahid Mohammadzadeh*, Arvind Vepa*, Chuanlong Li, Sean Wu, et al., Kouros Nouri-Mahdavi

Translational Vision Science & Technology, 2023

Paper

Miscellaneous 2 papers

Foil-Net: Deep Wave Classification for Hydrofoil Surfing

Zachary Mossing, Sean Wu, Kevin Hong, Fabien Scalzo, Jesse Cha

International Symposium on Visual Computing, 2023

Paper

Deep Learning–Based Classification of Plant Xylem Tissue from Light Micrographs

Sean Wu, Reem Al Dabagh, Anna L. Jacobsen, Helen I. Holmlund, Fabien Scalzo

International Symposium on Visual Computing, 2022

Paper

Education

Stanford University — Ph.D. in Computer Science 2026 — incoming
University of Oxford — Rhodes Scholar, graduate researcher in AI 2025–
Pepperdine University — B.S. in Computer Science & Mathematics, GPA 4.0/4.0 2021–2025

Teaching

Teaching Assistant — CS 450 Programming Paradigms
Teaching Assistant — CS 320 Data Structures
Teaching Assistant — CS 220 Applied Data Science / ML
Teaching Assistant — CS 210 Introduction to Machine Learning

Basketball

2025 intramural team.

2024 intramural team.

2023 intramural team.

Midrange jumpshot.

Music

Tuba Scholarship at Pepperdine University.