I am a first year Ph.D. student in CSAIL of MIT EECS, under the supervision of Prof. Antonio Torralba and Prof. Stefanie Jegelka. 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. My research mainly focus on deep learning and its applications in Machine Learning and Computer Vision. In particular, I am interested in neural networks, optimization, Bayesian inference, generative models, and reinforcement learning.

Sep 18 - Present

Aug 17 - Dec 17

Apr 16 - May 17

Jun 16 - Sep 16

Sep13 - Jun 17

research

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

Winner of THOR Challenge 2017 using Deep Reinforcement Learning
Ching-Yao Chuang, Min Sun and Sanja Fidler
CVPR 2017 Workshop on Visual Understanding Across Modalities [challenge link]

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 [arXiv] [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 [arXiv] [project page] [dataset]

research and work experience

Sep 2018 - Present R.A. Computer Science and Artificial Intelligence Lab, MIT
Advisor: Prof. Antonio Torralba & Prof. Stefanie Jegelka
Aug 2017 - Dec 2017 R.A. Machine Learning Lab, UofT
Advisor: Prof. Sanja Fidler
July 2015 - Aug 2017 R.A. Vision Science Lab, NTHU
Advisor Prof. Min Sun
April 2016 - May 2017 Intern Industrial Technology Research Institute
Advisor: Dr. Dung-Chan Tsai
June 2016 - Sept 2016 Intern Umbo CV Inc.
Advisor: Dr. Ping-Lin Chang

teaching

Spring 2017 TA, Signals and Systems, National Tsing Hua University
Fall 2016 Lecturer, Deep Reinforcement Learning Tutorial, Industrial Technology Research Institute


Source stolen from here