I am a second-year Computer Engineering Ph.D. student at Northeastern University, advised by Professor 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 for image and video generation. I am also interested in adapting these methods for robot control.
Proposes the first access-control mechanism for instruction-based image editing without architectural changes.
An improved SwiftBrush that makes the one-step diffusion student outperform its multi-step teacher.
By perturbing users' images with adversarial noise, the images become unusable for DreamBooth to generate subject-driven, photorealistic forgeries.
An efficient and geometry-invariant generator for synthesizing high-resolution images without using spatial convolutions or a coarse-to-fine design.