Patrick Emami (he/him/his) is a researcher in the Artificial Intelligence (AI), Learning, and Intelligent Systems group at NREL.  His research interests include deep generative modeling, reinforcement learning, and probabilistic methods. Patrick aims to advance our understanding of how machine learning, particularly deep learning, can assist with climate change mitigation and adaptation efforts. At NREL, he has developed reinforcement learning algorithms for building energy management and sampling techniques for protein engineering (e.g., for biofuels) with protein language models. In one of his projects, he is studying generative AI as a novel paradigm for addressing certain clean energy challenges.

Patrick obtained his bachelor’s degree in computer engineering and doctorate degree in computer science from the University of Florida in 2016 and 2021, respectively. He received his doctoral degree for his work on efficient neural scene understanding algorithms, which spanned topics including object-centric deep generative modeling, dynamic point cloud modeling, and low-resource multi-object tracking for traffic signal control.

Research Interests

Deep generative models

Reinforcement learning

AI for climate change

Education

Ph.D., Computer Science, University of Florida

M.S., Computer Science, University of Florida

B.S., Computer Engineering, University of Florida

Professional Experience

Postdoctoral Researcher, NREL (2022–2023)

Graduate Intern, NREL (2021–2021)

Graduate Research Assistant, University of Florida (2016–2021)

Associations and Memberships

Member, IEEE

Member, Association for Computing Machinery

Featured Work

Plug & Play Directed Evolution of Proteins with Gradient-Based Discrete MCMC, Machine Learning: Science & Technology (2023)

Learning Scene Dynamics from Point Cloud Sequences, International Journal of Computer Vision (2022)

Efficient Iterative Amortized Inference for Learning Symmetric and Disentangled Multi-Object Representations, International Conference on Machine Learning (2021)

Long-Range Multi-Object Tracking at Traffic Intersections on Low-Power Devices, IEEE Transactions on Intelligent Transportation Systems (2021)

Machine Learning Methods for Data Association in Multi-Object Tracking, ACM Computing Surveys (2020)

On the Detection of Disinformation Campaign Activity with Network Analysis, ACM Conference on Cloud Computing Security Workshop (2020)

Awards and Honors

Top Reviewer, International Conference on Learning Representations (2022)

Top 10% Reviewer, International Conference on Machine Learning (2021)

Student of the Year, U.S. Department of Transportation STRIDE Center (2020)