Qi Fang(方淇)

I am a first-year CS Master student at University of Toronto.

My research interests are in Computer Vision, AI Security, and Robotics. Specifically, to make self-driving cars robust under the conditions of adverse weather and adversarial attacks.

I am also interested in LLM x Robotics, Embodied AI, HCI, and AI for Social Good.

I was fortunately in research collaboration at AI4CE LAB, New York University, supervised by Prof. Chen Feng and Dr. Felix Juefei Xu. Previously I interned at iDLAB, Tsinghua University, advised by Prof. Wenjun Wang, where I focused on human behavior interacting with self-driving vehicles.

Feel free to contact me by email: qifang at cs.toronto.edu

Gmail  |  Google Scholar  |  Github

profile photo
Among Us: Adversarially Robust Collaborative Perception by Consensus
Yiming Li*, Qi Fang*, Jiamu Bai, Siheng Chen, Felix Juefei-Xu, Chen Feng
International Conference on Computer Vision (ICCV), 2023
arXiv / code

We proposed a novel probability-guaranteed sampling method inspired by RANSAC to achieve a trust-worthy group of benign agents, outperforming adversarial training Method by 73%.

Occ4cast: LiDAR-based 4D Occupancy Completion and Forecasting
Xinhao Liu*, Moonjun Gong*, Qi Fang, Haoyu Xie, Yiming Li, Hang Zhao, Chen Feng
arXiv, 2023
arXiv / project / code / data

We proposed a new LiDAR perception task, Occupancy Completion and Forecasting (OCF), combining scene completion and forecasting in autonomous driving, and evaluates it using the newly curated OCFBench dataset.

Influence of the Relative Position of Surrounding Traffic on Drivers’ Take-over Performance
Qingkun Li, Andrej Naumenko, Qi Fang, Ali Muhammad Hadi, Lian Hou, Wenjun Wang, Quan Yuan, Bo Cheng
International Conference on Applied Human Factors and Ergonomics (AHFE), 2021

We validated a key indicator of relative position between the ego vehicle and surrounding vehicles having important effects on take-over performance and driving safety.

3D Perception in Adverse Weather Conditions
Personal Project

"To augment the performance of lidar perception under challenging meteorological conditions. Focusing on noise-removal and noise-utilization methods."

*Move cursor to the thumbnail to see the iterative process of noisy points removal.
Reverse Adversarial Learning
Personal Project

"To explore the potential of reverse adversarial attacks to realize robust vision as well as robust 'objects' to current deep vision models."

Education & Internships
Universit of Toronto, Toronto, Canada
Department of Computer Science, MS in Applied Computing (MScAC)
Concentration: Artificial Intelligence

New York University, New York City, USA (Remote)
Research Collaboration
Supervisor: Prof. Chen Feng and Dr. Felix Juefei Xu

Research Topics:
[1] Multi-agent Collaboration / [2] Adversarial Machine Learning / [3] Robust Robot Vision

[1][2] -> Among Us, accepted to ICCV 23'
[2] -> Reverse Adversarial Learning
[3] -> 3D Perception in Adverse Weather Conditions

DiDi Autonomous Driving, Beijing, China (Jul. 2021 - Feb. 2022)
Product Engineering Intern

Tasks: Design, develop, and test autonomous driving strategies for DiDi’s level-4 robotaxis to optimize the design of algorithms, data science models, and autonomous features in terms of their reliability, safety, and efficiency

Xpeng Motors, Guangzhou, China (Jan. 2021 - Mar. 2021)
Test Engineering Intern

Tasks: Research, quality assurance, user testing, evaluation and optimization of XPeng’s Valet Parking Assist (VPA) feature

Tsinghua University, Beijing, China (Sept. 2020 - Jan. 2021)
Research Intern
Supervisor: Prof. Wenjun Wang

Research Topics: Human factors and ergonomics in conditional automated driving. -> AHFE 2021 Paper

Beijing University of Posts and Telecommunications, Beijing, China (Sept. 2018 - Jun. 2023)
Bachelor of Engineering
Computer Science and Technology

Major Courses: Operating System / Database System / Discrete Mathematics / Machine Learning / Data Structures / Compilers / Computer Networks

1. You can call me Qi[tʃiː].
2. I am really into math rock. Come to listen to my favorite math rock bands Elephant Gym and Shanghai Qiutian.
3. Red pandas are super cute! Check out their fluffy moments:
4. I love exploring around and capturing moments. Check out some random photos by me:

Stole from Jon Barron. Thank you :)

Updated on December 22, 2023