Long-Giang Vu

I am a first-year Master’s student in Computer Science at University of California, San Diego. Before moving to the US, I gained experience in various AI-related roles at Techcom Securities, Viettel Group and TopCV Vietnam. I also conducted research under the supervision of Professor Khoat Than at DSLab. My research interests include Deep Generative Models, Computer Vision and Model Optimization. I am currently seeking research opportunities at UCSD and internships for the Summer 2025 in the US. I would be grateful for any introductions to relevant opportunities.

news

Aug 03, 2024	This September, I will start pursuing my Masters of Science in Computer Science and Engineering at University of California, San Diego (UCSD).
Jul 06, 2024	I am very honored to be awarded a VinGroup Scholarship to pursue my Master’s degree in the US.
Dec 09, 2023	Paper On Inference Stability for Diffusion Models is accepted at AAAI2024.

latest posts

Aug 25, 2022	Variational Autoencoder explanation
Jun 24, 2022	Denoising Diffusion Probabilistic Model explanation

selected publications

AAAI Oral

On Inference Stability for Diffusion Models

Giang Vu*, Viet Nguyen* , Tung Nguyen Thanh , and 2 more authors

AAAI Conference on Artificial Intelligence, 2024

Oral Presentation
Abs PDF

Denoising Probabilistic Models (DPMs) represent an emerging domain of generative models that excel in generating di- verse and high-quality images. However, most current training methods for DPMs often neglect the correlation between timesteps, limiting the model’s performance in generating images effectively. Notably, we theoretically point out that this issue can be caused by the cumulative estimation gap between the predicted and the actual trajectory. To minimize that gap, we propose a novel sequence-aware loss that aims to reduce the estimation gap to enhance the sampling quality. Furthermore, we theoretically show that our proposed loss function is a tighter upper bound of the estimation loss in comparison with the conventional loss in DPMs. Experimental results on several benchmark datasets including CIFAR10, CelebA, and CelebA-HQ consistently show a remarkable improvement of our proposed method regarding the image generalization quality measured by FID and Inception Score compared to several DPM baselines. Our code and pre-trained checkpoints are available at https://github.com/VinAIResearch/SA-DPM.