About Me

I am a Computer Science Ph.D. Candidate at the University of Florida advised by Dr. Sanjay Ranka and Dr. Anand Rangarajan. My research is motivated by a desire to build computational vision systems that mimic how humans perceive the world. I also enjoy collaborating on inter-disciplinary projects where I apply machine learning to transportation engineering and cybersecurity. My thesis research is on the development of efficient neural algorithms for object-centric scene understanding, with applications to traffic signal control and model-based reinforcement learning.

I’m a Florida McKnight Fellow. The McKnight Doctoral Fellowship program aims to address the under-representation of African American and Hispanic faculty in the state of Florida. I’m always looking for ways in which I can better promote diversity and inclusivity in the field of computing.

Here’s my CV and resume.

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

News

  • 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!
  • May 2021 I am interning this summer with the National Renewable Energy Lab’s (NREL) Complex Systems Simulation and Optimization group working on reinforcement learning for traffic signal control!
  • April 2021 I am now a Ph.D. Candidate!

Publications

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.