Education
Northeastern University
Ph. D in Computer Engineerinng, advised by Prof. Raymond Fu
Ph. D in Computer Engineerinng, advised by Prof. Raymond Fu
Fall 2024 - Present
Boston, MA, USA
Boston, MA, USA
FPT University
B.S. in Computer Engineering
B.S. in Computer Engineering
Fall 2015 - Spring 2019
Hanoi, Vietnam
Hanoi, Vietnam
Employment
VinAI Research
Research Resident, supervised by Dr. Anh Tran. Worked on CREPS, Anti-DreamBooth and SwiftBrush v2.
Research Resident, supervised by Dr. Anh Tran. Worked on CREPS, Anti-DreamBooth and SwiftBrush v2.
March 2022 - July 2024
Hanoi, Vietnam
Hanoi, Vietnam
VietAI
Lecturer - part-time. Taught Deep Learning and NLP Courses, worked on VietAI's GPT-J project.
Lecturer - part-time. Taught Deep Learning and NLP Courses, worked on VietAI's GPT-J project.
Sep 2021 - May 2024
Hanoi, Vietnam
Hanoi, Vietnam
Thanh Cong JSC
Machine Learning Engineer. Developed a pronunciation evaluation system for English learners and word-sense disambiguation for Vietnamese.
Machine Learning Engineer. Developed a pronunciation evaluation system for English learners and word-sense disambiguation for Vietnamese.
Sep 2019 - Mar 2021
Hanoi, Vietnam
Hanoi, Vietnam
Viettel Network Corporation
Data Engineer Intern. Analyzed and visualized data for the network traffic system and demand forecasting.
Data Engineer Intern. Analyzed and visualized data for the network traffic system and demand forecasting.
May 2018 - Sep 2018
Hanoi, Vietnam
Hanoi, 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 outperform its multi-step teacher.
ECCV, 2024
Anti-DreamBooth: Protecting Users from Personalized Text-to-Image Synthesis
By perturbing user's images with adversarial noise, it becomes unusable for DreamBooth to generate subject-driven, photorealistic forgeries.
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