Education
Mohamed bin Zayed University of Artificial Intelligence
PhD in Computer Vision, advised by Prof. Hao Li (primary) and Prof. Nils Lukas (secondary).
PhD in Computer Vision, advised by Prof. Hao Li (primary) and Prof. Nils Lukas (secondary).
Fall 2024 - Present
Abu Dhabi, UAE
Abu Dhabi, UAE
Ho Chi Minh University of Technology - VNUHCM
B.Eng. in Computer Science, advised by Prof. Duc Dung Nguyen.
B.Eng. in Computer Science, advised by Prof. Duc Dung Nguyen.
Fall 2017 - Spring 2021
Ho Chi Minh, Vietnam
Ho Chi Minh, Vietnam
Employment
VinAI Research
Research Resident, supervised by Dr. Anh Tran. Worked on CREPS, Anti-DreamBooth, SwiftBrush and SwiftBrush v2.
Research Resident, supervised by Dr. Anh Tran. Worked on CREPS, Anti-DreamBooth, SwiftBrush and SwiftBrush v2.
July 2022 - July 2024
Ho Chi Minh, Vietnam
Ho Chi Minh, Vietnam
Goback Technology
Machine Learning Engineer. Developed a Traffic Violation System in Kontum, Vietnam.
Machine Learning Engineer. Developed a Traffic Violation System in Kontum, Vietnam.
Jun 2021 - July 2022
Jeonju, South Korea
Jeonju, South Korea
Anttizen
Research Intern of the DeepHub team. Worked on improving CP-VTON+.
Research Intern of the DeepHub team. Worked on improving CP-VTON+.
Jun 2020 - Sep 2020
Ho Chi Minh, Vietnam
Ho Chi Minh, Vietnam
Publications
* means equal contribution
SwiftBrush v2: Make Your One-step Diffusion Model Better Than Its Teacher
An improved SwiftBrush that makes the one-step diffusion student beat its multi-step teacher.
ECCV, 2024
SwiftBrush: One-Step Text-to-Image Diffusion Model with Variational Score Distillation
An image-free distillation method that transforms multi-step text-to-image diffusion models into one-step generators.
CVPR, 2024
Anti-DreamBooth: Protecting Users from Personalized Text-to-Image Synthesis
A security booth safeguards your privacy against malicious threats of DreamBooth by preventing it from synthesizing photo-realistic images of you.
ICCV, 2023
Efficient Scale-Invariant Generator with Column-Row Entangled Pixel Synthesis
An efficient and geometry-invariant generator for synthesizing high-resolution images without using spatial convolutions or a coarse-to-fine design.
CVPR, 2023