Learning the Koopman Operator using Attention Free Transformers
Nagdi, F., Nikolados, K., Yermakov, A., Gao, C., Kutz, J. N., & Menolascina, F. (2026). "Learning the Koopman Operator using Attention Free Transformers." IFAC World Congress.
CV
Education
- PhD, Electrical & Computer Engineering, University of Washington – Seattle (Sept 2023 – Present)
- Advisor: Dr. J. Nathan Kutz
- GPA: 3.98/4.00
- MS, Applied Mathematics, University of Washington – Seattle (Sept 2023 – June 2025)
- GPA: 3.98/4.00
- BS, Applied Mathematics, University of Colorado – Boulder (Aug 2019 – May 2023)
- Summa Cum Laude with Honors
- GPA: 4.00/4.00
- BS, Computer Science, University of Colorado – Boulder (Aug 2019 – May 2023)
- Summa Cum Laude with Honors
- GPA: 4.00/4.00
Internships
- Allen Institute for Artificial Intelligence (Ai2) (Summer 2026)
- I worked on the Climate Modeling team at Ai2 as a research intern working on out-of-distribution generalization
- I improved long-time climate forecasting performance through a variable masking strategy
- I also explored new transformer backbones and obtained the first positive results on an ACE foundation model trained with a mix of real and synthetic data
- NASA/Caltech Jet Propulsion Laboratory (Summer 2023)
- I spearheaded the development of a VxWorks 7 operating system abstraction layer (OSAL) in C for the Mars Sample Return (MSR) mission
- I also ported the open-source bsdiff and bspatch software to VxWorks 7 to reduce bandwidth usage during the MSR mission
- Lockheed Martin (Summer 2022)
- I implemented low-level software to communicate between a star tracker (ST) and a command & data handling (C&DH) board using the MIL-STD-1553 protocol
- I also worked on implementing functional verification tests (FVTs) to ensure written code followed logical requirements
- Lockheed Martin (Summer 2021)
- I implemented functional requirements for flight software built on top of NASA’s Core Flight Executive (cFE) framework in the VxWorks operating system
- I also wrote low-level code for satellite-to-ground radio communication for a technology demonstration that required testing code on real hardware
- Workiva (Summer 2020)
- I developed new visual and functional features for an internal search engine
- I added pagination capabilities and the TF-IDF statistic for page ranking, prevented Cross-Site Scripting (XSS) attacks, and enhanced the visual appeal of the site
Publications
CTF4Nuclear: Common Task Framework for Nuclear Fission and Fusion Models
Riva, Introini, Cammi, Price, Yermakov, A., et al. (2026). "CTF4Nuclear: Common Task Framework for Nuclear Fission and Fusion Models." arXiv:2605.15549.
The Seismic Wavefield Common Task Framework
Yermakov, A., Zhao, Z., Denolle, M., et al. (2026). "The Seismic Wavefield Common Task Framework." ICLR.
T-SHRED: Symbolic Regression for Regularization and Model Discovery with Transformer Shallow Recurrent Decoders
Yermakov, A., Zoro, D., Gao, L. M., & Kutz, J. N. (2026). "T-SHRED: Symbolic Regression for Regularization and Model Discovery with Transformer Shallow Recurrent Decoders." Philosophical Transactions of the Royal Society A, 384(2317), 20240586.
Latent Nonlinear Wave Dynamics in Image Datasets and Autoencoder Reconstructions
Yermakov, A., Ratliff, N., & Kutz, J. N. (2025). "Latent Nonlinear Wave Dynamics in Image Datasets and Autoencoder Reconstructions." ML and the Physical Sciences Workshop, NeurIPS.
Common Task Framework For a Critical Evaluation of Scientific Machine Learning Algorithms
Wyder, S., Goldfeder, J., Yermakov, A., et al. (2025). "Common Task Framework For a Critical Evaluation of Scientific Machine Learning Algorithms." NeurIPS.
Common Task Framework For a Critical Evaluation of Scientific Machine Learning Algorithms
Wyder, S., Goldfeder, J., Yermakov, A., et al. (2025). "Common Task Framework For a Critical Evaluation of Scientific Machine Learning Algorithms." Championing Open-source DEvelopment in ML Workshop @ ICML.
A Transformer-Based Deep Learning Approach to Anomaly Detection of High-Bandwidth Multivariate Time-Series Satellite Communications
Yermakov, A., Yun, D., Ratliff, N., & Kutz, J. N. (2025). "A Transformer-Based Deep Learning Approach to Anomaly Detection of High-Bandwidth Multivariate Time-Series Satellite Communications." International Conference on Space Operations.
Talks
The Common Task Framework for Scientific Machine Learning
Talk at AI-DEEDS, Banff, Alberta, Canada
The Seismic Wavefield Common Task Framework
Poster at ICLR, Rio de Janeiro, Brazil
Latent Nonlinear Wave Dynamics in Image Datasets and Autoencoder Reconstructions
Poster at ML and the Physical Sciences Workshop, NeurIPS, San Diego, California, USA
Common Task Framework For a Critical Evaluation of Scientific Machine Learning Algorithms
Poster at NeurIPS, San Diego, California, USA
Common Task Framework for a Critical Evaluation of Scientific Machine Learning Algorithms
Poster at CODEML@ICML25, Vancouver, British Columbia, Canada
Transformer-Based Anomaly Detection for DSN Time Series
Talk at D34 Technologist Seminar, JPL, Pasadena, CA, USA (remote)
A Transformer-Based Deep Learning Approach to Anomaly Detection of High-Bandwidth Multivariate Time-Series Satellite Communications
Talk at SpaceOps25, Montréal, Québec, Canada
Imaging Three-Dimensional Surface Waves Using a Synthetic Schlieren Method
Poster at Discovery Learning Apprenticeship Symposium, Boulder, Colorado, USA
Imaging Three-Dimensional Surface Waves Using a Synthetic Schlieren Method
Talk at SIAM-FRAMSC, Boulder, Colorado, USA
Awards and Fellowships
- National Science Foundation Graduate Research Fellowship Awardee (June 2025) — Three years of tuition and a living stipend
- Most Innovative Poster Award, 2025 UW ECE Research Showcase (May 2025) — Tour of Blue Origin facilities in Washington
- Robert E. Rushmer Endowed Fellowship Fund in ECE (Spring 2024) — One quarter of RA funding at UW
- ESCA Fellowship (Winter 2024) — One quarter of RA funding at UW
- GFSEI Top Scholar Recruitment Award (Fall 2023) — One quarter of RA funding at UW
- JPL Mission System Capture the Flag Award – Third Place (Summer 2023) — Recognition award for JPL interns
- CEAS Research Award (Spring 2023) — Recognition award for outstanding commitment to undergraduate researchers at CU Boulder
Service and leadership
- AI-DEEDS Organizer and Reviewer (2026)
- Elementary School Volunteer for UW Science Explorers (2026)
- NeurIPS Workshop Reviewer (2025)
- ICLR Reviewer (2025)
- ICML Workshop Reviewer (2025)
Certifications
- LE-1: Linux Essentials, Linux Professional Institute (LPI)
References
- J. Nathan Kutz, Professor, Applied Mathematics and Electrical & Computer Engineering, University of Washington — kutz@uw.edu