Qidong Huang (黄启栋)

Ph.D student, USTC

Information process center, CAS Key Laboratory of Electro-magnetic Space Information

School of Cyber Science and Technology, University of Science and Technology of China

Email: hqd0037[AT]mail.ustc.edu.cn

Currently on the job market! Seeking faculty/job opportunities (begin in 2025 Summer/Fall)!

[Google Scholar] [GitHub] [CV] [Twitter]

News

10/2024: Check out our PyramidDrop, accelerating your LVLM with over 1.7X training speed and 2.0X inference speed!
10/2024: We introduce MIR&MoCa, a LVLM pre-training indicator and a light-weight modality calibration module!
04/2024: OPERA is selected as Highlight in CVPR 2024!
02/2024: Two papers are accepted by CVPR 2024. See you at Seattle!
02/2024: I have one paper accepted by IEEE TIP 2024.
12/2023: Please check out our new work OPERA for mitigating MLLM's hallucination!
07/2023: I have one paper accepted by ACM MM 2023.
07/2023: I have one paper accepted by ICCV 2023. See you at Paris!
07/2023: I have a new homepage.

About Me

I am currently an Ph.D student at School of Cyber Science and Technology, University of Science and Technology of China , working with Prof. Nenghai Yu and Prof. Weiming Zhang. Prior to that, I received my bachelor degree in School of Information Engineering, University of Science and Technology of China. My current research focuses on large vision-language models.

Biography

2023.08 - Present, Research Intern at Shanghai AI Lab, supervised by Jiaqi Wang and Xiaoyi Dong.

2020.09 - Present, Ph.D. in School of Cyber Science and Technology, University of Science and Technology of China .

2016.09- 2020.06, B.Eng. in School of Information Engineering, University of Science and Technology of China

Preprints

	Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate Qidong Huang, Xiaoyi Dong, Pan Zhang, Yuhang Zang, Yuhang Cao, Jiaqi Wang, Dahua Lin, Weiming Zhang, Nenghai Yu [arXiv] [Code]

	PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction Long Xing, Qidong Huang, Xiaoyi Dong, Jiajie Lu, Pan Zhang, Yuhang Zang, Yuhang Cao, Conghui He, Jiaqi Wang, Feng Wu, Dahua Lin [arXiv] [Code]

Publications

	OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation Qidong Huang, Xiaoyi Dong, Pan Zhang, Bin Wang, Conghui He, Jiaqi Wang, Dahua Lin, Weiming Zhang, Nenghai Yu IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024. (Highlight, 2.8% of submissions) [arXiv] [Code]

	PointCAT: Contrastive Adversarial Training for Robust Point Cloud Recognition Qidong Huang, Xiaoyi Dong, Dongdong Chen, Hang Zhou, Weiming Zhang, Kui Zhang, Gang Hua, Nenghai Yu IEEE Transactions on Image Processing (TIP), 2024. [arXiv] [Code]

	Improving Adversarial Robustness of Masked Autoencoders via Test-time Frequency-domain Prompting Qidong Huang, Xiaoyi Dong, Dongdong Chen, Yinpeng Chen, Lu Yuan, Gang Hua, Weiming Zhang, Nenghai Yu IEEE/CVF International Conference on Computer Vision (ICCV), 2023. [arXiv] [Code]

	Diversity-Aware Meta Visual Prompting Qidong Huang, Xiaoyi Dong, Dongdong Chen, Weiming Zhang, Feifei Wang, Gang Hua, Nenghai Yu IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023. [arXiv] [Code]

	Shape-invariant 3D Adversarial Point Clouds Qidong Huang, Xiaoyi Dong, Dongdong Chen, Hang Zhou, Weiming Zhang, Nenghai Yu IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022. [arXiv] [Code]

	Initiative Defense against Facial Manipulation Qidong Huang, Jie Zhang, Wenbo Zhou, Weiming Zhang, Nenghai Yu (Equal contribution) AAAI Conference on Artificial Intelligence (AAAI), 2021.* [arXiv] [Code]

	SimAC: A Simple Anti-Customization Method against Text-to-Image Synthesis of Diffusion Models Feifei Wang, Zhentao Tan, Tianyi Wei, Yue Wu, Qidong Huang* (Corresponding author) IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024. [arXiv]

	Ada3Diff: Defending against 3D Adversarial Point Clouds via Adaptive Diffusion Kui Zhang, Hang Zhou, Jie Zhang, Qidong Huang, Weiming Zhang, Nenghai Yu ACM International Conference on Multimedia (MM), 2023. [arXiv]

	Poison Ink: Robust and Invisible Backdoor Attack Jie Zhang, Dongdong Chen, Qidong Huang, Jing Liao, Weiming Zhang, Huamin Feng, Gang Hua, Nenghai Yu IEEE Transactions on Image Processing (TIP), 2022. [arXiv] [Code]

	Deep Template-based Watermarking Han Fang, Dongdong Chen, Qidong Huang, Jie Zhang, Zehua Ma, Weiming Zhang* and Nenghai Yu IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2020. [Paper]