Hello, I'm Thanh Le

I am a first-year Computer Engineering PhD Student at Northeastern Unversity, advised by Prof. Raymond Fu. Previously, I had two wonderful years as an AI Research Resident at VinAI Research under the supervision of Dr. Anh Tran. My research aims to improve the safety and efficiency of deep generative models, especially within the field of computer vision.

CV Scholar Github Twitter

Publications

SwiftBrush v2: Make Your One-step Diffusion Model Better Than Its Teacher

Trung Dao*, Thuan Hoang Nguyen*, Thanh Le*, Duc Vu*, Khoi Nguyen, Cuong Pham, Anh Tran

ECCV, 2024

An improved SwiftBrush that makes the one-step diffusion student outperform its multi-step teacher.

Project Page PDF arXiv

Anti-DreamBooth: Protecting Users from Personalized Text-to-Image Synthesis

Thanh Le*, Hao Phung*, Thuan Hoang Nguyen*, Quan Dao*, Ngoc Tran, Anh Tran

ICCV, 2023

By perturbing user's images with adversarial noise, it becomes unusable for DreamBooth to generate subject-driven, photorealistic forgeries.

Project Page PDF arXiv Code

Efficient Scale-Invariant Generator with Column-Row Entangled Pixel Synthesis

Thuan Hoang Nguyen*, Thanh Le*, Anh Tran

CVPR, 2023

An efficient and geometry-invariant generator for synthesizing high-resolution images without using spatial convolutions or a coarse-to-fine design.

Project Page PDF arXiv Code