Darin Tsui

Hi there! My name is Darin. I’m a Ph.D. student at the Georgia Institute of Technology studying Electrical and Computer Engineering and Bioengineering. I previously received my BS degree at the University of California San Diego in Bioengineering.
I currently work with Dr. Amirali Aghazadeh in the AI ML & Information Group, where I develop scalable, interpretable tools for generative models in the biosciences. I am currently supported by the NSF Graduate Research Fellowship. My research focuses on:
-
Explaining black-box models by bridging the gap between interpretability and signal processing.
-
Extracting higher-order interactions from models for scientific discovery.
-
Developing principled generative models that leverage domain priors.
My background is highlighly interdisciplinary. I previously validated deep learning models at Surgalign (acquired by Xtant Medical), developed an optical surgical platform in the Talke Biomedical Device Lab, and designed a bioelectronic COVID-19 test in the Integrated Systems Neuroengineering Laboratory.
Outside of research, I co-chair Bioengineering Day at Georgia Tech, which aims to highlight interdisciplinary research . Previously, I served as President of the IEEE student branch and helped found the IEEE EMBS chapter at UC San Diego.
News
Jul 16, 2025 | Our work on assessing and explaining mutations in myocilin was accepted to the Machine Learning in Computational Biology (MLCB) meeting. |
---|---|
Jun 27, 2025 | My work on developing sparse Fourier transforms for generalized q-ary functions was accepted to the IEEE Information Theory Workshop (ITW). |
May 11, 2024 | I presented my work on uncovering higher-order interactions in protein language models at the ICLR Generative and Experimental Perspectives for Biomolecular Design (GEM) workshop. |
Apr 04, 2024 | Excited to announce that I was awarded the National Science Foundation (NSF) Graduate Research Fellowship (GRFP) to support my PhD! |
Aug 31, 2023 | I had the opportunity to give a talk at the ASME Information Storage and Processing Systems (ISPS) on the promise of stereoscopic vision in computer-assisted surgery. |
Selected Publications
- Efficient algorithm for sparse Fourier transform of generalized q-ary functionsIn 2025 IEEE Information Theory Workshop (ITW) (Accepted) , 2025
- SHAP zero explains biological sequence models with near-zero marginal cost for future queriesarXiv preprint arXiv:2410.19236, 2025
- On recovering higher-order interactions from protein language modelsIn ICLR 2024 Workshop on Generative and Experimental Perspectives for Biomolecular Design (GEM) , 2024