I am a Research Engineer at MediaTek, working on computer vision and Generative AI.
Before joining MediaTek, I was a Research Intern at MIT-IBM Watson AI Lab, working on
adversarial learning and meta-learning. I received my Master's degree in Computer Science
from National Tsing Hua University (NTHU), advised by Prof. Shan-Hung Wu.
I also got my B.Sc. at this fantastic place. I have had the privilege to work with
Dr. Pin-Yu Chen and
Prof. Chia-Mu Yu at MIT-IBM Watson AI Lab.
My research interest is mainly in robust deep learning, including adversarial and trustworthy
machine learning, domain adaptation, image/video restoration and enhancement, and generative model.
Currently, I'm exploring the intersection of Generative AI and Edge AI to develop the on-device generative model.
MediaTek Research Engineer Jun. 22 - Present
MIT-IBM Watson AI Lab Research Intern Oct. 21 - Nov. 21
NTHU M.Sc. in CS Sep. 19 - Jul. 21
NTHU B.Sc. in IPE Sep. 14 - Jun. 19
University of Tübingen Exchange Student Oct. 16 - Jul. 17
Proposed a meta adversarial perturbation (MAP), a better initialization that causes data to be misclassified with high probability after being updated through only a one-step gradient ascent update.
Proposed generalization attack, where an attacker aims to modify training data in order to spoil training process such that a trained network lacks generalizability.
Devised runtime masking and cleansing (RMC), a new defense method, to improve adversarial robustness.
Side Projects
TensorFlow2 Classification Model Zoo
95.76% on CIFAR-10 with TensorFlow2. A TF2 implementation of the classification models, including VGG, ResNet, DenseNet, SENet, MobileNet, etc.
Neural Networks from Scratch
A tutorial about how to build neural networks on our own, without the help of the deep learning frameworks. In this way, we can better understand deep learning and how all of the elements work.
Awesome Real-world Adversarial Examples
A curated list of awesome real-world adversarial examples resources. This repository only lists the mechanism which can be realized in the real-world, in other words, the physical attack or defense.
Scene Recognition with Bag of Words
An example of a typical bag of words classification pipeline. It begins with simplest method, tiny images and k-NN(k nearest neighbors) classification, and then move forward to bags of quantized local features and linear classifiers learned by SVC(support vector classifier).
YouTube 20K
