Jingkang Wang      

CV  /  LinkedIn  /  GitHub  /  Google Scholar

I am a third-year Ph.D. student in Machine Learning Group, CS Department, University of Toronto. My advisors are Prof. Raquel Urtasun and Prof. Richard Zemel. I am also part of Vector Institute and Waabi. From 2019-2021, I was also a research scientist at Uber-ATG Toronto, working with Prof. Raquel Urtasun. I received my B.S. degree from Shanghai Jiao Tong University advised by Prof. Cewu Lu and Prof. Gongshen Liu.

My research interests involve Machine Learning and Computer Vision. Prior to UofT, I spent a wonderful year working with Prof. Bo Li at UIUC as a research intern and did some works on trustworthy machine learning.

University of Toronto, Canada
Ph.D. in Computer Science

Shanghai Jiao Tong University, China
B.S. in Engineering

Adversarial Attack Generation Empowered by Min-Max Optimization
Jingkang Wang*, Tianyun Zhang*, Sijia Liu, Pin-Yu Chen, Jiacen Xu, Makan Fardad and Bo Li
Advances in Neural Information Processing Systems (NeurIPS), 2021
[paper] [code]

Policy Learning Using Weak Supervision
Jingkang Wang*, Hongyi Guo*, Zhaowei Zhu and Yang Liu
Advances in Neural Information Processing Systems (NeurIPS), 2021
[paper] [code]

AdvSim: Generating Safety-Critical Scenarios for Self-Driving Vehicles
Jingkang Wang, Ava Pun, James Tu, Sivabalan Manivasagam, Abbas Sadat, Sergio Casas,
Mengye Ren and Raquel Urtasun
Conference on Computer Vision and Pattern Recognition (CVPR), 2021
[paper] [poster] [video] [website]

Just Label What You Need: Fine-Grained Active Selection for Perception and Prediction through Partially Labeled Scenes
Sean Segal*, Nishanth Kumar*, Sergio Casas, Wenyuan Zeng, Mengye Ren, Jingkang Wang, Raquel Urtasun
Conference on Robot Learning (CoRL), 2021
[paper]

Adversarial Attacks on Multi-Agent Communication
James Tu*, Tsunhsuan Wang*, Jingkang Wang, Sivabalan Manivasagam, Mengye Ren and Raquel Urtasun
International Conference on Computer Vision (ICCV), 2021
[paper] [video]

Learning to Communicate and Correct Pose Errors
Nicholas Vadivelu, Mengye Ren, James Tu, Jingkang Wang and Raquel Urtasun
Conference on Robot Learning (CoRL), 2020
[paper] [video]

Cost-Efficient Online Hyperparameter Optimization
Jingkang Wang*, Mengye Ren*, Ilija Bogunovic, Yuwen Xiong and Raquel Urtasun
International Conference on Machine Learning (ICML), RealML Workshop, 2020
arXiv preprint arXiv:2101.06590
[paper] [video]

Is Robust Neurons’ Activation Sufficient to Robustify CNNs against Adversarial Attacks?
Jingkang Wang*, Gaoyuan Zhang* and Sijia Liu
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), AdvML Workshop, 2020

BabyAI++: Towards Grounded-Language Learning beyond Memorization
Tianshi Cao*, Jingkang Wang*, Annie Zhang* and Sivabalan Manivasagam*
International Conference on Learning Representations (ICLR), BeTR-RL Workshop, 2020
[paper] [code] [media]

Reinforcement Learning with Perturbed Rewards
Jingkang Wang, Yang Liu and Bo Li
AAAI Conference on Artificial Intelligence (AAAI), 2020 (Spotlight)
[paper] [code]

On the Impact of Perceptual Compression on Deep Learning
Gerald Friedland, Ruoxi Jia, Jingkang Wang, Bo Li and Nathan Mundhenk.
International Conference on Multimedia Information Processing and Retrieval (MIPR), 2020.
[paper] [code]

Multiple Character Embeddings for Chinese Word Segmentation
Jingkang Wang*, Jianing Zhou*, Jie Zhou and Gongshen Liu
Annual Meeting of the Association for Computational Linguistics (ACL), Student Research Workshop, 2019 [paper] [code]

LiDAR-Video Driving Dataset: Learning Driving Policies Effectively
Yiping Chen*, Jingkang Wang*, Jonathan Li, Cewu Lu, Zhipeng Luo, Han Xue and Cheng Wang
Conference on Computer Vision and Pattern Recognition (CVPR), 2018
[paper] [code] [dataset]

Waabi Innovation Inc.
Research Scientist

Uber-ATG Toronto
Research Scientist

Ant Financial, Alibaba Group
Research Intern

University of Illinois at Urbana-Champaign
Research Intern at CSD*   (* = remote work)

University of California, Berkeley
Research Intern at BAIR Lab*   (* = remote work)

Machine Vision and Intelligence Group (MVIG)
Research Assistant

Thanks jonbarron for this amazing work.