I am a Research Engineer at MediaTek, working on Generative AI and Edge 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 image/video generation and restoration, efficient deep learning, and adversarial machine learning. 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
Selected Publications
MAE: A 3nm 0.168mm2 576MAC Mini Autoencoder with Line-Based Depth-First Scheduling for Generative AI in Vision on Edge Devices
Shih-Wei Hsieh, Chia-Hung Yuan, Ming-Hung Lin, Ping-Yuan Tsai, You-Yu Nian, Chia-Yuan Cheng, Hung-Wei Chih, Po-Han Chiang, Ming-Hsuan Chiang, Yuan-Jung Kuo, Yu-Wei We, Yi-Syuan Chen, Po-Heng Chen, Sandy Huang, Ming-En Shih, Chia-Ping Chen, Abrams Chen, ShenKai Chang, Chih-Ming Wang, Po-Yu Yeh, Jett Liu, Yung-Chang Chang, Chung-Yi Chen, Chi-Cheng Ju, CH Wang, Keven Jou ISSCC 2025 (Highlight) Paper
Proposed 3nm Al accelerator, which delivers 0.63 TOPS within an ultra-compact 0.168mm2 area, optimized for generative Al applications.
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).