Mason Huang

黃稚筌

ML Researcher
Taiwan
masonhuang0320@gmail.com

About Me

I am a Master's student at the Graduate Institute of Networking and Multimedia (GINM), National Taiwan University. I conduct research at CLLAB under the supervision of Prof. Hsuan-Tien Lin. Previously, I was an undergraduate researcher at IGVI Lab with Dr. Min-Chun Hu and Dr. Hung-Kuo Chu at NTHU.

Research Interests

My research focuses on Machine Learning and Computer Vision, with particular interests in:

  • Model Reliability: Test-time Alignment and Machine Unlearning.

  • Generative Models: Vision-Language Models (VLMs) and Diffusion Models.

Industry Experience

From July 2024 to December 2025, I served as an AI Software Engineer Intern at Innovedus Inc., where I developed and optimized AI models for Kneron NPU, and contributed to the core applications KNEO X and KNEO cluster.

Updates

  • Jan. 2026: Started my M.S. degree at National Taiwan University!

  • Dec. 2025: Completed my AI Software Engineer Internship at Innovedus Inc.

  • Aug. 2025: One paper accepted by UIST 2025!

  • Jul. 2025: One paper accepted by TAICHI 2025!

  • Apr. 2024: One paper accepted by SIGGRAPH 2024!

Education

Jan. 2026 - Present
M.S. in Computer Science
National Taiwan University
Sep. 2021 - Jan. 2026
B.B.A. in Technology Management
National Tsing Hua University
Sep. 2018 - Jun. 2021
Senior High School Degree
The Affiliated Senior High School of NTNU

Interests

Machine Learning
Computer Vision
Open Source Community
Music

Selected Research

ImmerseSketch: Transforming Creative Prompts into Vivid 3D Environments in VR
Alfred Lan, 
Tai-Chen Tsai, 
Chih-Chuan Huang, 
Pu Ching, 
Tse-Yu Pan, 
Min-Chun Hu
Jul 28th 2024
SIGGRAPH 2024
#Virtual Reality
#HCI

We propose ImmerseSketch, a framework designed to transform creative prompts into vivid and detailed 3D content within a Virtual Reality (VR) environment. Our aim is to inspire creative ideation and to provide creators with 3D reference content for painting. We focus on generating initial panoramic images through diffusion models and then converting these images into rich 3D environments with the aid of depth estimation

Poster
Last Updated on Jan 13th 2026