About Me

I am a machine learning researcher interested in neural representation learning, reinforcement learning (RL), and AI for social good. Recently, I started as a postdoc at the National Renewable Energy Lab (NREL) where I will be developing multi-agent RL approaches to energy-efficient building control and neural algorithms for large-scale black-box optimization. NREL is a US Dept. of Energy national lab that is helping to advance our understanding of how machine learning can help tackle climate change, which I believe to be one of the most pressing scientific challenges of our time. I recently graduated with my Ph.D. in Computer Science from the University of Florida in December 2021 with generous support from the Florida McKnight Fellowship. My Ph.D. research was on neural scene understanding and spanned topics including: object-centric deep generative modeling, dynamic point cloud modeling, and low-resource multi-object tracking for traffic signal control.

[CV] [Resume] [Google scholar] [Github]

Contact: pemami[at]ufl[dot][edu]


  • January 2022 I am now a postdoc at NREL!
  • December 2021 I defended my thesis “Neural Algorithms for Object-centric Scene Understanding” and graduated with my Ph.D.!
  • December 2021 One paper accepted at AAAI’22 (15% acceptance rate)!
  • November 2021 One paper accepted for publication in IEEE Transactions on Intelligent Transportation Systems (T-ITS) and one paper accepted for publication in the International Journal of Computer Vision (IJCV)
  • July 2021 I was recognized as a Top 10% reviewer at ICML’21!
  • May 2021 My paper “Efficient Iterative Amortized Inference for Learning Symmetric and Disentangled Multi-Object Representations” has been accepted as a short talk at ICML’21!


Learning Scene Dynamics from Point Cloud Sequences

IJCV Special Issue on 3D Computer Vision, 2021
We introduce the sequential scene flow estimation problem and provide a novel baseline architecture and benchmark for evaluation.

Long-range Multi-Object Tracking at Traffic Intersections on Low-Power Devices

IEEE Transactions on Intelligent Transportation Systems, Oct. 2021
A CNN architecture for joint object detection and Re-ID on low-power edge devices and a multi-sensor tracking algorithm for radar.

Efficient Iterative Amortized Inference for Learning Symmetric and Disentangled Multi-Object Representations

ICML 2021
An efficient slot-based hierachical VAE for learning unordered, symmetric, and disentangled scene representations.

A Symmetric and Object-Centric World Model for Stochastic Environments

NeurIPS 2020 Workshop on Object Reps. for Learning and Reasoning (Spotlight)
We propose a state space model and training objective that achieves better stochastic future prediction for object-centric world models.

On the Detection of Disinformation Campaign Activity with Network Analysis

CCSW 2020: The ACM Cloud Computing Security Workshop
Characterizing the machine learning problem of detecting disinformation-like coordinated activity on Twitter.

Machine Learning Methods for Data Association in Multi-Object Tracking

ACM Computing Surveys, 53, 4, Article 69 (August 2020)
A survey on algorithmic and recent deep-learning-based approaches to the data association problem in multi-object tracking.

See my CV for a complete list including older publications.

Leeuwenberg, E. L. J. "A Perceptual Coding Language for Visual and Auditory Patterns." The American Journal of Psychology, vol. 84, no. 3, 1971, pg. 338.