Amirali Aghazadeh

Georgia Tech

prof_pic.jpg

Coda S1209

Tech Square

Atlanta, GA 30308

I am an Assistant Professor in the School of Electrical and Computer Engineering at the Georgia Institute of Technology. I serve as program faculty for the Ph.D. programs in Machine Learning, Bioinformatics, and Bioengineering, and am affiliated with the IDEaS, IMS, and Petit Institute (IBB).

Prior to Georgia Tech, I was a postdoctoral researcher at Stanford and UC Berkeley, and earned my Ph.D. at Rice University. My research group develops principled algorithms and theoretical tools for building scalable, interpretable, and design-oriented AI systems, with a core focus on understanding and engineering biological functions.

Current research directions are:

  • Core ML/AI: Diffusion models, accelerated inference, high-dim statistical learning
  • Trustworthy AI: Explainability, Mech interp, Attribution methods
  • Agentic AI: Hypothesis generation, Validation, Multi-step reasoning
  • AI4Science: AI4Biology, AI4Protein, AI4CryoEM, AI4Chemistry, AI4Astrobio

I pronounce my first name Ah-meer-ah-lee and my last name Ah-gah-zah-deh.

news

Apr 30, 2026 ProtoMech has been accepted to ICML! ProtoMech cracks open protein language models to expose the hidden circuits they use and lets you steer them to design better proteins.
Apr 16, 2026 Happy to be named as a Scialog Fellow! Our mission is to develop agents that make sciecne discovery fully automated.
Feb 21, 2026 cryoSENSE has been accepted to CVPR! 🎉 We demonstrate that generative AI can dramatically increase data throughput in cryo-EM acquisition.
Sep 29, 2025 Our LifeTracer work with NASA on discriminating Abiotic and Biotic organics in meteorite and terrestrial samples is now accepted to PNAS Nexus! 🎉
Sep 18, 2025 SHAP zero has been accepted to NeurIPS! 🎉 If you are looking for an ultra-scalable algorithm to explain your ML/AL sequence models and find long-range, high-order interactions, check SHAP zero.

selected publications

  1. protomech.png
    Protein Circuit Tracing via Cross-layer Transcoders
    Darin Tsui, Kunal Talreja, Daniel Saeedi, and 1 more author
    International Conference on Machine Learning Research (ICML), 2026
  2. microscope.png
    Thinking microscopes: agentic AI and the future of electron microscopy
    Vida Jamali, Amirali Aghazadeh, and Josh Kacher
    npj Computational Materials, 2026
  3. ddpm.gif
    cryoSENSE: Compressive Sensing Enables High-throughput Microscopy with Sparse and Generative Priors on the Protein Cryo-EM Image Manifold
    Zain Shabeeb, Daniel Saeedi, Darin Tsui, and 2 more authors
    Conference on Computer Vision and Pattern Recognition (CVPR), 2026
  4. specme.png
    SpecMER: Fast Protein Generation with K-mer Guided Speculative Decoding
    Thomas Walton, Darin Tsui, Aryan Musharaf, and 1 more author
    Conference on Neural Information Processing Systems (NeurIPS) Spotlight (top 3% of 21,575 submissions), 2025
  5. SHAPzero.jpg
    SHAP zero Explains Biological Sequence Models with Near-zero Marginal Cost for Future Queries
    Darin Tsui, Aryan Musharaf, Yigit Efe Erginbas, and 2 more authors
    Conference on Neural Information Processing Systems (NeurIPS), 2025