|
I am a second-year PhD student of LONG Group, Hong Kong University of Science and Technology, fortunately advised by Prof. Long Chen. Before that, I obtained my M.S. degree from NTU (Singapore), where I was advised by Prof. Hanwang Zhang in Machine Reasoning and Learning Lab (MReal Lab). I got my B.S. degree from Sichuan University. I am fortunate to have internships at WeChat, Tiktok and 4Paradigm. Email: scuwyh2000@gmail.com / ywangtg@connect.ust.hk WeChat: sczhaoxi2000 |
|
|
My current research focuses on Diffusion Models, especially the Neural ODE and Flow Matching. Meanwhile, I am broadly interested in Computer Vision, Multimodal Learning, and Machine Learning. |
|
|
|
Yanghao Wang, Long Chen In Submission, 2025 paper / code We proposed a novel Noise Optimization (NoOp) method to learn matching noise for Diffusion Classifiers. By using an optimized noise, the performance (accuracy and efficiency) of the Diffusion Classifier can be significantly improved. |
|
Yanghao Wang, Long Chen CVPR, 2025 paper / code We proposed a novel Diffusion-based Inversion Interpolation DA method called Diff-II, which can generate faithful and diverse samples to expand the original training set in data-scarce scenarios. |
|
Yanghao Wang, Zhongqi Yue, Xian-Sheng Hua, Hanwang Zhang ICCV, 2023 paper / code We showed that classifiers trained with random region proposals achieve state-of-the-art Open-world Object Detection with our designed matching score. |
|
Yongyan Guo, Zhengyu Liu, Cheng Huang, Jiayong Liu, Wangyuan Jing, Ziwang Wang, Yanghao Wang ICICS, 2021, (Best Student Paper) paper We proposed CyberRel, a joint entity and relation extraction model for cybersecurity concepts. |
|
|