Maya Varma

Logo

PhD Candidate
Stanford University
Location  Location  Location 

about me

I am a PhD candidate in the Department of Computer Science at Stanford University, where I am a member of the Center for Artificial Intelligence in Medicine & Imaging (AIMI). My research aims to develop artificial intelligence methods for addressing healthcare challenges, with a particular emphasis on medical imaging applications. I am grateful to be supported by the Knight-Hennessy Fellowship, the U.S. Department of Defense NDSEG Fellowship, and the Quad Fellowship.

Previously, I graduated with a BS in computer science and a minor in electrical engineering from Stanford University. I was recognized as a Frederick E. Terman Scholar, a distinction awarded to the top thirty students in the Stanford School of Engineering by GPA. For my senior honors thesis at the Wall Lab, I developed artificial intelligence methods for improving the diagnosis of autism spectrum disorder. My research was awarded the David M. Kennedy Prize for the best thesis in the School of Engineering and the Ben Wegbreit Prize for the best thesis in computer science.

My interest in science began at an early age. In high school, I won first place at the Intel Science Talent Search (STS) and presented my research at the White House.

honors & awards
research
View Mode:

(* indicates equal contribution)


Domino: Discovering Systematic Errors with Cross-Modal Embeddings
International Conference on Learning Representations (ICLR), 2022
ribbon Oral Presentation (Top 1.5% of Submissions) Sabri Eyuboglu*, Maya Varma*, Khaled Saab*, Jean-Benoit Delbrouck, Christopher Lee-Messer, Jared Dunnmon, James Zou, Christopher Ré
[paper] [code]


RaVL: Discovering and Mitigating Spurious Correlations in Fine-Tuned Vision-Language Models
Conference on Neural Information Processing Systems (NeurIPS), 2024
Maya Varma, Jean-Benoit Delbrouck, Zhihong Chen, Akshay Chaudhari, Curtis Langlotz
[paper] [code]


TRoVe: Discovering Error-Inducing Static Feature Biases in Temporal Vision-Language Models
Conference on Neural Information Processing Systems (NeurIPS), 2025
Maya Varma, Jean-Benoit Delbrouck, Sophie Ostmeier, Akshay Chaudhari, Curtis Langlotz
[paper] [code]


MedVAE: Efficient Automated Interpretation of Medical Images with Large-Scale Generalizable Autoencoders
Medical Imaging with Deep Learning (MIDL), 2025
ribbon Best Paper Award ribbon Oral Presentation Maya Varma*, Ashwin Kumar*, Rogier van der Sluijs*, Sophie Ostmeier, Louis Blankemeier, Pierre Chambon, Christian Bluethgen, Jip Prince, Curtis Langlotz, Akshay Chaudhari
[paper] [code] [models]



CheXagent: A Vision-Language Foundation Model to Enhance Efficiency of Chest X-Ray Interpretation
Technical Report, 2024
Zhihong Chen*, Maya Varma*, Justin Xu, Magdalini Paschali, Dave Van Veen, Andrew Johnston,..., Sergios Gatidis, Jean-Benoit Delbrouck, Akshay Chaudhari, Curtis Langlotz
[paper] [code] [models]



ViLLA: Fine‑Grained Vision‑Language Representation Learning from Real‑World Data
International Conference on Computer Vision (ICCV), 2023
Maya Varma, Jean-Benoit Delbrouck, Sarah Hooper, Akshay Chaudhari, Curtis Langlotz
[paper] [code]


Automated Abnormality Detection in Lower Extremity Radiographs Using Deep Learning
Nature Machine Intelligence, 2019
Maya Varma, Mandy Lu, Rachel Gardner, Jared Dunnmon, Nishith Khandwala, Pranav Rajpurkar, Jin Long, Christopher Beaulieu, Katie Shpanskaya, Li Fei-Fei, Matthew Lungren, Bhavik Patel
[paper] [code] [data]


SMMILE: An Expert‑Driven Benchmark for Multimodal Medical In‑Context Learning
Conference on Neural Information Processing Systems (NeurIPS), 2025
Melanie Rieff*, Maya Varma*, Ossian Rabow, Subathra Adithan, Julie Kim, Ken Chang, Hannah Lee, Nidhi Rohatgi, Christian Bluethgen, Mohamed S. Muneer, Jean-Benoit Delbrouck, Michael Moor
[paper] [code] [data]


Toward Expanding the Scope of Radiology Report Summarization to Multiple Anatomies and Modalities
Association for Computational Linguistics (ACL), 2023
Zhihong Chen*, Maya Varma*, Xiang Wan, Curtis Langlotz, Jean-Benoit Delbrouck*
[paper] [data]


LieRE: Lie Rotational Positional Encodings
International Conference on Machine Learning (ICML), 2025
Sophie Ostmeier, Brian Axelrod, Maya Varma, Michael Moseley, Akshay Chaudhari, Curtis Langlotz
[paper] [code]


Foundation Models in Radiology: What, How, Why, and Why Not
Radiology, 2025
Magdalini Paschali, Zhihong Chen, Louis Blankemeier, Maya Varma, Alaa Youssef, Christian Bluethgen, Curtis Langlotz, Sergios Gatidis, Akshay Chaudhari
[paper]


CheXalign: Preference Fine-Tuning in Chest X-Ray Interpretation Models Without Human Feedback
Association for Computational Linguistics (ACL), 2025
Dennis Hein, Zhihong Chen, Sophie Ostmeier, Justin Xu, Maya Varma, Eduardo Pontes Reis, Arne Edward Michalson, Christian Bluethgen, Hyun Joo Shin, Curtis Langlotz, Akshay S Chaudhari
[paper]


Automated Structured Radiology Report Generation
Association for Computational Linguistics (ACL), 2025
Jean-Benoit Delbrouck, Justin Xu, Johannes Moll, Alois Thomas, Zhihong Chen, Sophie Ostmeier, Asfandyar Azhar, Kelvin Zhenghao Li, Andrew Johnston, Christian Bluethgen, Eduardo Reis, Mohamed Muneer, Maya Varma, Curtis Langlotz
[paper] [project page] [models]