Jiaqi Tang 唐家祺

Captured at Dolomites, Italy

I am an incoming Ph.D. student at Hong Kong University of Science and Technology and will transfer to Clear Water Bay in Fall 2025.

Currently, I have finished M.Phil. in Artificial Intelligence at Hong Kong University of Science and Technology (Guangzhou), supervised by Prof. Ying-Cong Chen and Prof. Qifeng Chen. Before that, I obtained B.Eng. in Data Science and Big Data Tech., from the School of Computer Science, Northwestern Polytechnical University, supervised by Prof. Wei Wei and Minor in Business Administration from the School of Management in 2022.

I maintain strong industry collaborations, working closely with Dr. Xiaogang Xu from Huawei 2012 Lab, Mr. Qingguo Chen and Mr. Yifeng Wu at Alibaba Group, Dr. Jiangbo Lu and Dr. Sixing Hu at SmartMore Corporation.

My research focuses on Multi-modal Large Language Models (MLLMs). If you are interested in collaborating with me, please feel free to contact.

news

Jun 27, 2025	Two papers are accepted by ICCV2025.
May 20, 2025	I am happy to pass my M.Phil. Thesis Defence.
Apr 06, 2025	One paper is accepted by CVPR2025 Highlight (Top 2.9%).
Nov 07, 2024	Congratulations! Our paper, “AdaShadow: Responsive Test-time Model Adaptation in Non-stationary Mobile Environments” is selected as Best Paper Honorable Mention in ACM SenSys 2024.
Sep 25, 2024	One paper is accepted by NeurIPS2024.

selected publications

CVPR

SURGEON: Memory-Adaptive Fully Test-Time Adaptation via Dynamic Sparsity Activation

Ke Ma , Jiaqi Tang, Fan Dang , Bin Guo† , Sicong Liu , Cheng Fang , Zhui Zhu , Lei Wu , Ying-Cong Chen , Zhiwen Yu , and Yunhao Liu†

In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , 2025

Highlight (Top 2.9%)

Bib Code

@inproceedings{ma2024,
  title = {SURGEON: Memory-Adaptive Fully Test-Time Adaptation via Dynamic Sparsity Activation},
  author = {Ma, Ke and Tang, Jiaqi and Dang, Fan and Guo†, Bin and Liu, Sicong and Fang, Cheng and Zhu, Zhui and Wu, Lei and Chen, Ying-Cong and Yu, Zhiwen and Liu†, Yunhao},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  selected = {true},
  note = {Highlight (Top 2.9\%)},
}

ACM SenSys

AdaShadow: Responsive Test-time Adaptation for Non-stationary Mobile Environments

Cheng Fang , Sicong Liu , Zimu Zhou , Bin Guo† , Jiaqi Tang, Ke Ma , and Zhiwen Yu

In ACM Conference on Embedded Networked Sensor Systems (SenSys) , 2024

Best Paper Honorable Mention (Top 7/313)

Bib

@inproceedings{zfang2024,
  title = {AdaShadow: Responsive Test-time Adaptation for Non-stationary Mobile Environments},
  author = {Fang, Cheng and Liu, Sicong and Zhou, Zimu and Guo†, Bin and Tang, Jiaqi and Ma, Ke and Yu, Zhiwen},
  booktitle = {ACM Conference on Embedded Networked Sensor Systems (SenSys)},
  year = {2024},
  note = {Best Paper Honorable Mention (Top 7/313)},
  selected = {true}
}

NeurIPS

Hawk: Learning to Understand Open-World Video Anomalies

Jiaqi Tang*, Hao Lu* , Ruizheng Wu , Xiaogang Xu , Ke Ma , Cheng Fang , Bin Guo , Jiangbo Lu , Qifeng Chen , and Ying-Cong Chen†

In Annual Conference on Neural Information Processing Systems (NeurIPS) , 2024

*: Equal Contribution

Bib Code Website

@inproceedings{atang2024hawk,
  title = {Hawk: Learning to Understand Open-World Video Anomalies},
  author = {Tang*, Jiaqi and Lu*, Hao and Wu, Ruizheng and Xu, Xiaogang and Ma, Ke and Fang, Cheng and Guo, Bin and Lu, Jiangbo and Chen, Qifeng and Chen†, Ying-Cong},
  year = {2024},
  booktitle = {Annual Conference on Neural Information Processing Systems (NeurIPS)},
  website = {https://huggingface.co/Jiaqi-hkust},
  note = {*: Equal Contribution},
  selected = {true}
}

CVPR

Learning to Remove Wrinkled Transparent Film with Polarized Prior

Jiaqi Tang, Ruizheng Wu , Xiaogang Xu , Sixing Hu , and Ying-Cong Chen†

In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , 2024

Bib Code Website

@inproceedings{tang2024learning,
  title = {Learning to Remove Wrinkled Transparent Film with Polarized Prior},
  author = {Tang, Jiaqi and Wu, Ruizheng and Xu, Xiaogang and Hu, Sixing and Chen†, Ying-Cong},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  website = {https://jqt.me/_FilmRemoval_/},
  selected = {true},
}

ECCV

An Incremental Unified Framework for Small Defect Inspection

Jiaqi Tang, Hao Lu , Xiaogang Xu , Ruizheng Wu , Sixing Hu , Tong Zhang , Tsz Wa Cheng , Ming Ge , Ying-Cong Chen† , and Fugee Tsung

In 18th European Conference on Computer Vision (ECCV) , 2024

Bib Code Website

@inproceedings{tang2024incremental,
  title = {An Incremental Unified Framework for Small Defect Inspection},
  author = {Tang, Jiaqi and Lu, Hao and Xu, Xiaogang and Wu, Ruizheng and Hu, Sixing and Zhang, Tong and Cheng, Tsz Wa and Ge, Ming and Chen†, Ying-Cong and Tsung, Fugee},
  booktitle = {18th European Conference on Computer Vision (ECCV)},
  year = {2024},
  website = {https://jqt.me/_IUF_},
  selected = {true},
}

ECAI

High Dynamic Range Image Reconstruction via Deep Explicit Polynomial Curve Estimation

Jiaqi Tang, Xiaogang Xu , Sixing Hu , and Ying-Cong Chen†

In 26th European Conference on Artificial Intelligence (ECAI) , 2023

Long Oral

arXiv Bib Code

@inproceedings{tang2023high,
  title = {High Dynamic Range Image Reconstruction via Deep Explicit Polynomial Curve Estimation},
  author = {Tang, Jiaqi and Xu, Xiaogang and Hu, Sixing and Chen†, Ying-Cong},
  booktitle = {26th European Conference on Artificial Intelligence (ECAI)},
  pages = {2330--2337},
  year = {2023},
  selected = {true},
  note = {Long Oral}
}