Jingkang Wang      

CV  /  LinkedIn  /  GitHub  /  Google Scholar

I am a first-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 Uber ATG and Vector Institute. I received my B.S. degree from Shanghai Jiao Tong University advised by Prof. Cewu Lu.

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

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
arXiv preprint arXiv:2101.06549

Adversarial Attacks on Multi-Agent Communication
James Tu*, Tsunhsuan Wang*, Jingkang Wang, Sivabalan Manivasagam, Mengye Ren and Raquel Urtasun
arXiv preprint arXiv:2101.06560

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

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

Policy Learning Using Weak Supervision
Jingkang Wang*, Hongyi Guo*, Zhaowei Zhu and Yang Liu
Advances in Neural Information Processing Systems (NeurIPS), DeepRL and RWRL Workshops, 2020
arXiv preprint arXiv:2010.01748

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]

Towards a Unified Min-Max Framework for Adversarial Exploration and Robustness
Jingkang Wang*, Tianyun Zhang*, Sijia Liu, Pin-Yu Chen, Jiacen Xu, Makan Fardad and Bo Li
arXiv preprint arXiv:1906.03563

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]

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.