Hi, I’m Zach.

I’m an Electrical & Computer Engineering PhD student at UT Austin working with Prof. Jon Tamir in the Computational Sensing & Imaging Lab.

I’m working on provable learning methods for solving inverse problems in computational imaging and sequence modeling. Generally, I’m curious about AI/ML, signal processing, optimization, probability, statistics, and control.

Check out my notes to see what I’m thinking about and kū to see what I’m seeing!

I’m always open to new opportunities and collaborations within my interests. You can contact me at zstoebner@austin.utexas.edu.

CV GitHub LinkedIn Scholar

in progress

“Preconditioning for monotone operator learning”, Zachary A. Stoebner, Jonathan I. Tamir.

conference

“INFusion: Diffusion Regularized Implicit Neural Representations for 2D and 3D accelerated MRI reconstruction”, Yamin Arefeen, Brett Levac, Zach Stoebner, Jonathan I Tamir. Asilomar. (2024) arXiv

“Segmentation of kidney stones in endoscopic video feeds”, Zachary A. Stoebner, Daiwei Lu, Seok Hee Hong, Nicholas L. Kavoussi, and Ipek Oguz, Proc. SPIE 12032, Medical Imaging 2022: Image Processing (2022). DOI arXiv note

journal

“Reducing malware analysis overhead with coverings”, Michael Sandborn, Zach Stoebner, Westley Weimer, Stephanie Forrest, Ryan Dougherty, Jules White, Kevin Leach. IEEE‑TDSC (2023). DOI repo

“Comprehensive shape analysis of the cortex in Huntington’s disease”, Zachary A. Stoebner, Kilian Hett, Ilwoo Lyu, Hans Johnson, Jane S. Paulsen, Jeffrey Long, Ipek Oguz, Human Brain Mapping (2023). DOI repo note

poster

“Generalized system identification and joint signal reconstruction with implicit neural representations, with application to MRI”, Zachary A. Stoebner, Jonathan I. Tamir. {6G@UT, Oden SciML Workshop} (2024).

patent

“Systems and Methods for Navigation and Identification during Endoscopic Surgery”, Nicholas L. Kavoussi, Ipek Oguz, Jie Ying Wu, Zachary A. Stoebner, Daiwei Lu, Ayberk Acar. U.S. Patent Application No. 18/622,134.

• May 27, 2025: I’ve started working at Adobe in San Jose as an AI/ML research intern for Firefly, working on structured state-space models for long-form text-to-image/video generation.

• November 15, 2024: I presented a poster at the 6G@UT Student Research Showcase on Generalized system identification and joint signal reconstruction with implicit neural representations, with application to MRI.

• October 3, 2024: I presented a poster at the Oden SciML Workshop on Generalized system identification and joint signal reconstruction with implicit neural representations, with application to MRI.

• July 29, 2024: Asilomar 2024 accepted our paper INFusion: Diffusion Regularized Implicit Neural Representations for 2D and 3D accelerated MRI reconstruction.

• December 25, 2023: IEEE-TDSC published our journal paper Reducing Malware Analysis Overhead with Coverings.

• October 15-21, 2023: I attended the i2i Workshop and participated in the MRI4All Hackathon on the reconstruction team, during which 4 teams worked on building an ultra-low-field MRI in a week.

• September 28, 2022: Human Brain Mapping accepted our paper Comprehensive shape analysis of the cortex in Huntington’s disease.

• August 25, 2022: I started my PhD at UT Austin with Prof. Jon Tamir in the Computational Sensing & Imaging Lab!

• July 15, 2022: I successfully defended my thesis A deep-learning enabled automatic segmentation system for surgical endoscopy for my MS in CS at Vanderbilt University.

• May 13, 2022: I graduated from Vanderbilt University with a BS in CS & Neuroscience, minoring in Applied Math.

• April 4, 2022: SPIE 2022 published our paper Segmentation of kidney stones in endoscopic video feeds.