Yen-Chen Lin

Ph.D. Student at MIT
yenchenl [at] mit [dot] edu

Twitter / Scholar / Github
Bio. I am a Ph.D. student at MIT CSAIL working with Phillip Isola and Alberto Rodriguez. I am interested in robotics.

Previously, I was lucky to have the opportunities to work with Raquel Urtasun at Uber ATG, Min Sun at National Tsing Hua University, Ming-Yu Liu at NVIDIA, and Jia-Bin Huang at Virginia Tech. In addition to my research experiences, I build interesting open-source projects such as DeepLearningFlappyBird, which has been featured on Hacker News.

See my CV (updated Sep 2019) for more details.

Selected Publications

(*indicates equal contribution)

Learning to See before Learning to Act: Visual Pre-training for Manipulation
Lin Yen-Chen, Andy Zeng, Shuran Song, Phillip Isola, Tsung-Yi Lin
ICRA 2020
Webpage / PDF / Google AI Blog
Experience-embedded Visual Foresight
Lin Yen-Chen, Maria Bauza, Phillip Isola
CoRL 2019
Webpage / PDF / Code

Previously publishes under Yen-Chen Lin:

Omnipush: accurate, diverse, real-world dataset of pushing dynamics with RGBD images
Maria Bauza, Ferran Alet, Yen-Chen Lin, Tomás Lozano-Pérez, Leslie P. Kaelbling,
Phillip Isola, Alberto Rodriguez
IROS 2019
Webpage / PDF / Code / MIT News
Deep 360 Pilot: Learning a Deep Agent for Piloting through 360° Sports Videos
Yen-Chen Lin*, Hou-Ning Hu*, Ming-Yu Liu, Hsien-Tzu Cheng, Yung-Ju Chang, Min Sun
CVPR 2017 (Oral)
Webpage / PDF
Tactics for Adversarial Attack on Deep Reinforcement Learning Agents
Yen-Chen Lin, Zhang-Wei Hong, Yuan-Hong Liao, Meng-Li Shih, Ming-Yu Liu, Min Sun
IJCAI 2017
Webpage / PDF
Detecting Adversarial Attacks on Neural Network Policies with Visual Foresight
Yen-Chen Lin, Ming-Yu Liu, Min Sun, Jia-Bin Huang
NIPS 2017 workshop
Webpage / PDF
Tell Me Where to Look: Investigating Ways for Assisting Focus in 360° Video
Yen-Chen Lin, Yung-Ju Chang, Hou-Ning Hu, Hsien-Tzu Cheng, Chi-Wen Huang, Min Sun
CHI 2017
Webpage / PDF

Side Projects

pix2pix-tensorflow is a tensorflow implementation of Image-to-Image Translation with Conditional Adversarial Networks from Isola et al.
DeepLearningFlappyBird uses Deep Reinforcement Learning to train an agent that beats human players on Flappy Bird.
awesome-adversarial-machine-learning is a curated list of awesome awesome adversarial machine learning resources.

Work Experiences

Google Summer of Code
In 2016, I participated Google Summer of Code program and worked with scikit-learn community. My mission is to make implementation of many algorithms, such as Stochastic Gradient Descent, Coordinate Descent, support Cython fused types and therefore reduce memory waste. Find my development logs here.
Real Forest
Real Forest is a feature I developed for well-known iOS app - Forest: Stay focused, be present when I was an intern there. This feature let user plant a real tree in the world using the coins they earned in the app. So far, it has helped planting 8000+ real trees in India and Zambia.