Прати
Quan Dao
Quan Dao
CS PhD Student, Rutgers University
Верификована је имејл адреса на rutgers.edu - Почетна страница
Наслов
Навело
Навело
Година
Anti-DreamBooth: Protecting users from personalized text-to-image synthesis
T Van Le*, H Phung*, TH Nguyen*, Q Dao*, N Tran, A Tran
IEEE/CVF International Conference on Computer Vision (ICCV), 2023, 2023
1082023
Wavelet Diffusion Models are fast and scalable Image Generators
H Phung*, Q Dao*, A Tran
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, 2023
1032023
Flow matching in latent space
Q Dao*, H Phung*, B Nguyen, A Tran
arXiv preprint arXiv:2307.08698, 2023
562023
A High-Quality Robust Diffusion Framework for Corrupted Dataset
Q Dao*, B Ta*, T Pham, A Tran
European Conference on Computer Vision (ECCV), 2024, 2024
2*2024
Dice: Discrete inversion enabling controllable editing for multinomial diffusion and masked generative models
X He, L Han, Q Dao, S Wen, M Bai, D Liu, H Zhang, MR Min, F Juefei-Xu, ...
The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025, 2025
12025
Self-Corrected Flow Distillation for Consistent One-Step and Few-Step Text-to-Image Generation
Q Dao*, H Phung*, T Dao, D Metaxas, A Tran
Association for the Advancement of Artificial Intelligence (AAAI), 2025, 2024
12024
DiMSUM: Diffusion Mamba--A Scalable and Unified Spatial-Frequency Method for Image Generation
H Phung*, Q Dao*, T Dao, H Phan, D Metaxas, A Tran
The Conference on Neural Information Processing Systems (NeurIPS), 2024 …, 2024
12024
Improved Training Technique for Latent Consistency Models
Q Dao, K Doan, D Liu, T Le, D Metaxas
The Thirteenth International Conference on Learning Representations (ICLR), 2025, 2025
2025
Систем тренутно не може да изврши ову радњу. Пробајте поново касније.
Чланци 1–8