Ching-Yao Chuang

PhD Student
CSAIL
Electrical Engineering and Computer Science
Massachusetts Institute of Technology
cychuang _at_ mit _dot_ edu


Curriculum vitæ / Google Scholar

I am a Ph.D. student in CSAIL and Machine Learning group of MIT EECS, under the supervision of Prof. Stefanie Jegelka and Prof. Antonio Torralba. I am supported by a IBM PhD Fellowship. Previously I worked with Prof. Sanja Fidler as a visiting student at University of Toronto and Prof. Min Sun as an undergraduate researcher at National Tsing Hua University, Taiwan. My research mainly focuses on building robust and generalizable deep learning systems from uncurated data. In particular, I am interested in computer vision, multimodal learning, self-supervised learning, and optimal transport.

Publications

Debiasing Vision-Language Models via Biased Prompts
Ching-Yao Chuang, Varun Jampani Yuanzhen Li, Antonio Torralba, and Stefanie Jegelka
arXiv Preprint 2023 [paper] [code]

InfoOT: Information Maximizing Optimal Transport
Ching-Yao Chuang, Stefanie Jegelka, and David Alvarez-Melis
arXiv Preprint 2022 [paper] [code]

Tree Mover’s Distance: Bridging Graph Metrics and Stability of Graph Neural Networks
Ching-Yao Chuang and Stefanie Jegelka
NeurIPS 2022 [paper] [code]

Robust Contrastive Learning against Noisy Views
Ching-Yao Chuang, R Devon Hjelm, Xin Wang, Vibhav Vineet, Neel Joshi, Antonio Torralba, Stefanie Jegelka, and Yale Song
CVPR 2022 [paper] [code]

Measuring Generalization with Optimal Transport
Ching-Yao Chuang, Youssef Mroueh, Kristjan Greenewald, Antonio Torralba, and Stefanie Jegelka
NeurIPS 2021 Spotlight [paper] [code]

Fair Mixup: Fairness via Interpolation
Ching-Yao Chuang, Youssef Mroueh
ICLR 2021 [paper] [code]

Contrastive Learning with Hard Negative Samples
Joshua Robinson, Ching-Yao Chuang, Suvrit Sra, and Stefanie Jegelka
ICLR 2021 [paper] [code]

Debiased Contrastive Learning
Ching-Yao Chuang, Joshua Robinson, Lin Yen-Chen, Antonio Torralba, and Stefanie Jegelka
NeurIPS 2020 Spotlight [paper] [code]

Estimating Generalization under Distribution Shifts via Domain-Invariant Representations
Ching-Yao Chuang, Antonio Torralba, and Stefanie Jegelka
ICML 2020 [paper] [project page]

The Role of Embedding Complexity in Domain-invariant Representations
Ching-Yao Chuang, Antonio Torralba, and Stefanie Jegelka
ICML 2019 AMTL Workshop [paper] [code]

Learning to Act Properly: Predicting and Explaining Affordances from Images
Ching-Yao Chuang, Jiaman Li, Antonio Torralba and Sanja Fidler
CVPR 2018 [paper] [project page]

Show, Adapt and Tell: Adversarial Training of Cross-domain Image Captioner
Tseng-Hung Chen, Yuan-Hong Liao, Ching-Yao Chuang, Wan-Ting Hsu, Jianlong Fu and Min Sun
ICCV 2017 [paper] [project page]

Leveraging Video Descriptions to Learn Video Question Answering
Kuo-Hao Zeng, Tseng-Hung Chen, Ching-Yao Chuang, Yuan-Hong Liao, Juan Carlos Niebles and Min Sun
AAAI 2017 [paper] [project page] [dataset]

work experience

May 2022 - Aug 2022 Research Intern Microsoft Research, New England
Host: Prof. David Alvarez-Melis
June 2021 - Aug 2021 Research Intern Microsoft Research, Redmond
Host: Dr. Yale Song
Jul 2020 - Sep 2020 Research Intern IBM Research AI
Host: Dr. Youssef Mroueh
Sep 2018 - Present R.A. Computer Science and Artificial Intelligence Lab, MIT
Host: Prof. Antonio Torralba & Prof. Stefanie Jegelka
Aug 2017 - Dec 2017 R.A. Machine Learning Lab, UofT
Host: Prof. Sanja Fidler
July 2015 - Aug 2017 R.A. Vision Science Lab, NTHU
Host Prof. Min Sun
June 2016 - Sept 2016 Intern Umbo CV Inc.
Host: Dr. Ping-Lin Chang
Accessibility