Jay Shenoy

I am a computer science PhD student at Stanford University advised by Prof. Gordon Wetzstein. My research is focused on improving the capabilities of foundation models like AlphaFold to reconstruct protein dynamics from experimental cryo-electron microscopy and X-ray crystallography data. In the past, I have worked on developing computer vision techniques to solve inverse problems in scientific imaging.

Please reach out if you are interested in collaborating or have any questions about my work!

Research
Modeling Atomic Conformational Ensembles of Proteins via Test-Time Supervision of Boltz-2 on Cryo-EM Density Maps
Jay Shenoy, Miro Astore, Axel Levy, Frédéric Poitevin, Sonya M. Hanson, Gordon Wetzstein
arXiv, 2026

Fine-tuning Boltz-2 directly on cryo-EM map ensembles.

CrystalBoltz: End-to-End Protein Structure Determination via Experiment-Guided Diffusion for X-Ray Crystallography
Minseo Kim, Huanghao Mai*, Jay Shenoy*, Alec H. Hollmer, Gordon Wetzstein, Frédéric Poitevin
arXiv, 2026

Diffusion guidance of Boltz-2 with X-ray crystallography data.

Scalable 3D Reconstruction for X-Ray Single Particle Imaging With Online Machine Learning
Jay Shenoy, Axel Levy, Kartik Ayyer, Frédéric Poitevin, Gordon Wetzstein
Nature Communications, 2025

Online protein reconstruction from X-ray single particle imaging.

Featured in SLAC News
Optimization Methods for Tracking and Mapping the Human Retina
MS Thesis, 2022

Retina tracking and mapping in 2D and 3D.

Querying Labelled Data with Scenario Programs for Sim-to-Real Validation
Edward Kim, Jay Shenoy, Sebastian Junges, Daniel Fremont, Alberto Sangiovanni-Vincentelli, Sanjit Seshia
International Conference on Cyber-Physical Systems (ICCPS), 2022
Best Paper Award Nominee

Searching car-mounted image datasets using a domain-specific language.

R-SLAM: Optimizing Eye Tracking From Rolling Shutter Video of the Retina
Jay Shenoy*, James Fong*, Jeffrey Tan, Austin Roorda, Ren Ng
ICCV, 2021

State-of-the-art eye tracking and mapping at the cellular scale.


Site template courtesy of Jon Barron