I am Ge Ya (Olga) Luo, currently a Ph.D. student at Mila – Quebec Artificial Intelligence Institute, where I am being supervised by Prof. Christopher Pal. My research focuses on the intersection of computer vision and generative models. In 2017, I completed my Bachelor of Arts & Science in Computer Science at the University of Toronto, and I finished my Master of Science in Computer Science at Université de Montréal in 2020. Between April and September 2025, I visited Prof. A. C. Öztireli’s CORE lab at the University of Cambridge to work on advancing 3D vision reconstruction. Currently, I started my visiting researcher role at Meta-Fair Montreal to work under the Supervision of Dr. Michal Drozdzal and Prof. Adriana R. Soriano on video generation starting from September 2025.
What I’ve Researched
- NeurIPS 2025 The Promise of RL for Autoregressive Image Editing
Saba Ahmadi, Rabiul Awal, Ankur Sikarwar, Amirhossein Kazemnejad, Ge Ya Luo, Juan A. Rodrigue, Sai Rajeswar, Siva Reddy, Christopher Pal, Benno Krojer, Aishwarya Agrawal - Preprint Ctrl-Crash: Controllable Diffusion for Realistic Car Crashes
Anthony Gosselin, Ge Ya Luo, Luis Lara, Florian Golemo, Derek Nowrouzezahrai, Liam Paull, Alexia Jolicoeur-Martineau, Christopher Pal - LMID 2025 Spatio-Temporal Conditional Diffusion Models for Forecasting Future Multiple Sclerosis Lesion Masks Conditioned on Treatments
Gian Favero, Ge Ya Luo, Nima Fathi, Justin Szeto, Douglas Arnold, Brennan Nichyporuk, Christopher Pal, Tal Arbel - ICLR 2025 Beyond FVD: Enhanced Evaluation Metrics for Video Generation Quality
Ge Ya Luo*, Gian Favero*, Zhi Hao Luo, Alexia Jolicoeur-Martineau, Christopher Pal - TMLR 2024 Ctrl-V: Higher Fidelity Video Generation with Bounding-Box Controlled Object Motion
Ge Ya Luo, Zhi Hao Luo, Anthony Gosselin, Alexia Jolicoeur-Martineau, Christopher Pal - 2024 DStruct2Design: Data and Benchmarks for Data Structure Driven Generative Floor Plan Design
Zhi Hao Luo, Luis Lara, Ge Ya Luo, Florian Golemo, Christopher Beckham, Christopher Pal - 2022-2023 Video Prediction via Spatio Temporal External Attention and Memory
Ge Ya Luo, Zhi Hao Luo, Alexia Jolicoeur-Martineau, Haozhe Zhang, Christopher Pal - 2018 RNNs with Private and Shared Representations for Semi-Supervised Sequence Learning
What I’m Exploring
My current research focuses on developing solutions for 3D vision generation, out-of-distribution scenario video generation, image editing, medical imaging and flow-matching.
What I Enjoy
I love working on various coding projects during my free time, including creating small games and solving LeetCode challenges. My GitHub repository contains a digital version of the beloved board game Codename, waiting for you to play and enjoy. Furthermore, I have also shared my solutions and explanations for different LeetCode problems in another GitHub repository.
I’m also passionate about ultra-endurance sports and achieved a milestone by completing my first 80km trail ultra-marathon in 2023, which featured a challenging 3300m elevation gain.
Hello, I am Ge Ya Luo :) 