Edward J. Smith

Researcher, Borealis AI

Joined

July 2019

Names

Edward J. Smith

Emails

****@mail.mcgill.ca (Confirmed)

****@meta.com (Confirmed)

****@borealisai.com (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

Researcher

Borealis AI (borealisai.com)

2023 – Present

PhD student

McGill University (mcgill.ca)

2016 – 2023

Undergrad student

McGill University (mcgill.ca)

2013 – 2016

Advisors, Relations & Conflicts

Coworker

Vin Bhaskara

2023 – Present

PhD Advisor

Adriana Romero

2018 – Present

PhD Advisor

David Meger

2016 – Present

Expertise

Deep Learning

Graph Convolutional Networks

2019 – Present

Depp Learning

3D representation

Computer Vision

2017 – Present

Deep Learning

3D generation

Computer Vision

2017 – Present

Publications

Test-Time Adaptation for Event Prediction via Lightweight Adapters
Shivam Grover, Hossein Hajimirsadeghi, Zhitian Zhang, Edward J. Smith, Alexander Pashevich
- CAO Poster
- Readers: Everyone
RLTime: Reinforcement Learning-Based Feature Attribution for Interpretable Time Series Models
Fuyuan Lyu, Wesley Chung, Melissa Mozifian, Ankit Vani, Edward J. Smith
- Submitted to ICLR 2026
- Readers: Everyone
For SALE: State-Action Representation Learning for Deep Reinforcement Learning
Scott Fujimoto, Wei-Di Chang, Edward J. Smith, Shixiang Shane Gu, Doina Precup, David Meger
- NeurIPS 2023 poster
- Readers: Everyone
Uncertainty-Driven Active Vision for Implicit Scene Reconstruction
Edward J. Smith, Michal Drozdzal, Derek Nowrouzezahrai, David Meger, Adriana Romero-Soriano
- 22 Sept 2022 (modified: 15 Jan 2026)
- ICLR 2023 Conference Withdrawn Submission
- Readers: Everyone
Frame Averaging for Invariant and Equivariant Network Design
Omri Puny, Matan Atzmon, Edward J. Smith, Ishan Misra, Aditya Grover, Heli Ben-Hamu, Yaron Lipman
- Published: 28 Jan 2022, Last Modified: 13 Feb 2023
- ICLR 2022 Oral
- Readers: Everyone
Active 3D Shape Reconstruction from Vision and Touch
Edward J. Smith, David Meger, Luis Pineda, Roberto Calandra, Jitendra Malik, Adriana Romero, Michal Drozdzal
- Published: 09 Nov 2021, Last Modified: 26 May 2025
- NeurIPS 2021 Poster
- Readers: Everyone
3D Shape Reconstruction from Vision and Touch
Edward J. Smith, Roberto Calandra, Adriana Romero, Georgia Gkioxari, David Meger, Jitendra Malik, Michal Drozdzal
- 2020 (modified: 13 Nov 2024)
- CoRR 2020
- Readers: Everyone
GEOMetrics: Exploiting Geometric Structure for Graph-Encoded Objects
Edward J. Smith, Scott Fujimoto, Adriana Romero, David Meger
- 2019 (modified: 11 Nov 2022)
- ICML 2019
- Readers: Everyone
Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer.
Wenzheng Chen, Huan Ling, Jun Gao, Edward J. Smith, Jaakko Lehtinen, Alec Jacobson, Sanja Fidler
- 2019 (modified: 09 Nov 2022)
- NeurIPS2019
- Readers: Everyone
Kaolin: A PyTorch Library for Accelerating 3D Deep Learning Research
Krishna Murthy Jatavallabhula, Edward J. Smith, Jean-Francois Lafleche, Clement Fuji Tsang, Artem Rozantsev, Wenzheng Chen, Tommy Xiang, Rev Lebaredian, Sanja Fidler
- 2019 (modified: 16 Apr 2025)
- CoRR 2019
- Readers: Everyone

View all 12 publications

Co-Authors

View all 39 co-authors