Luke Rowe

I am a second-year Ph.D. student in the Robotics and Embodied AI Lab (REAL) Lab at Mila / Université de Montréal, advised by Prof. Liam Paull and Prof. Chris Pal. My research interests lie at the intersection of machine learning and autonomous driving, with a particular emphasis on data-driven simulation, edge-case generation, and end-to-end autonomy. I am particularly excited about the role that simulation can play in scaling Level 4+ autonomous vehicles and how generative models can improve the realism and controllability of driving simulators.

During my Ph.D., I have completed an internship at Torc Robotics on generative models for data-driven simulation, working closely with Roger Girgis and Felix Heide.

Prior to this, I obtained an Master’s degree in Computer Science from the University of Waterloo, where I worked with Prof. Krzysztof Czarnecki on joint motion prediction for autonomous driving. I received my Bachelor’s degree in Computer Science and Mathematics from the University of Victoria, where I worked with Prof. George Tzanetakis on machine learning for music.

In my free time, you can find me playing basketball, jazz piano, or walking around Montréal to find new vegan/vegetarian places to eat.

Selected Publications

* indicates equal contribution.
CtRL-Sim: Reactive and Controllable Driving Agents with Offline Reinforcement Learning
Luke Rowe*, Roger Girgis*, Anthony Gosselin, Bruno Carrez, Florian Golemo, Felix Heide, Liam Paull, Chris Pal,
Conference on Robot Learning (CoRL), 2024
[paper] [video] [project page] [code]
Amortizing intractable inference in diffusion models for vision, language, and control
Siddarth Venkatraman*, Moksh Jain*, Luca Scimeca*, Minsu Kim*, Marcin Sendera*, Mohsin Hasan, Luke Rowe, Sarthak Mittal, Pablo Lemos, Emmanuel Bengio, Alexandre Adam, Jarrid Rector-Brooks, Yoshua Bengio, Glen Berseth, Nikolay Malkin,
Conference on Neural Information Processing Systems (NeurIPS), 2024
[paper] [code]
FJMP: Factorized Joint Multi-Agent Motion Prediction over Learned Directed Acyclic Interaction Graphs
Luke Rowe, Martin Ethier, Eli-Henry Dykhne, Krzysztof Czarnecki,
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
[paper] [video] [project page] [code]
Out-of-Distribution Detection for LiDAR-based 3D Object Detection
Chengjie Huang, Van Duong Nguyen, Vahdat Abdelzad, Christopher Gus Mannes, Luke Rowe, Benjamin Thérien, Rick Salay, Krzysztof Czarnecki,
IEEE International Conference on Intelligent Transportation Systems (ITSC), 2022
[paper]

Teaching

  • Teaching Assistant for CS 360 - Theory of Computing, Winter 2022, Spring 2022, Fall 2022, Winter 2023, Spring 2023 at University of Waterloo
  • Teaching Assistant for CS 135 - Designing Functional Programs, Fall 2021 at University of Waterloo
  • Teaching Assistant for CSC 320 - Foundations of Computer Science, Fall 2019 at University of Victoria

Awards

  • NSERC Doctoral Scholarship (2024-2027)
  • FRQNT Doctoral Scholarship (2024-2028)
  • Ontario Graduate Scholarship (2021, 2022)
  • President’s Graduate Scholarship, University of Waterloo (2021, 2022)
  • NSERC USRA (Summer 2020)