Zhuowei (Jack) Li

Hi! I am Zhuowei (Jack) Li, currently a 4th year Ph.D. candidate in Computer Science at Rutgers University under the supervision of Professor Dimitris N. Metaxas. Prior to this, I earned my Master’s degree from Columbia University, where I had the privilege of working under the guidance of Professors Andrew Laine and Shih-Fu Chang. I also spent two years as a Computer Vision Researcher at SenseTime, working with Professor Shaoting Zhang. My Bachelor’s degree was completed at Northeastern University, China.

My broad research interests span Machine Learning, Computer Vision, and Medical Image Analysis. Of late, my research focuses on inference‑time intervention of Large Language Models (LLMs) and Multi‑modal Large Language Models (MLLMs) to enhance their efficiency and reliability, as well as leveraging Reinforcement Learning to strengthen their reasoning capabilities.

selected publications

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering

Zhuowei Li, Haizhou Shi, Yunhe Gao, Di Liu, Zhenting Wang, Yuxiao Chen, Ting Liu, Long Zhao, Hao Wang, and Dimitris N Metaxas

arXiv:2502.03628 (pre-print), 2025

Bib PDF

@article{li2025hiddenlifetokensreducing,
  title = {The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering},
  author = {Li, Zhuowei and Shi, Haizhou and Gao, Yunhe and Liu, Di and Wang, Zhenting and Chen, Yuxiao and Liu, Ting and Zhao, Long and Wang, Hao and Metaxas, Dimitris N},
  journal = {arXiv:2502.03628 (pre-print)},
  year = {2025},
}

Implicit In-context Learning

Zhuowei Li, Zihao Xu, Ligong Han, Yunhe Gao, Song Wen, Di Liu, Hao Wang, and Dimitris N Metaxas

The Thirteenth International Conference on Learning Representations (ICLR), 2025

Bib PDF

@article{li2024implicit,
  title = {Implicit In-context Learning},
  author = {Li, Zhuowei and Xu, Zihao and Han, Ligong and Gao, Yunhe and Wen, Song and Liu, Di and Wang, Hao and Metaxas, Dimitris N},
  journal = {The Thirteenth International Conference on Learning Representations (ICLR)},
  year = {2025},
}

Steering prototypes with prompt-tuning for rehearsal-free continual learning

Zhuowei Li, Long Zhao, Zizhao Zhang, Han Zhang, Di Liu, Ting Liu, and Dimitris N Metaxas

In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2024

Bib PDF

@inproceedings{li2024steering,
  title = {Steering prototypes with prompt-tuning for rehearsal-free continual learning},
  author = {Li, Zhuowei and Zhao, Long and Zhang, Zizhao and Zhang, Han and Liu, Di and Liu, Ting and Metaxas, Dimitris N},
  booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
  pages = {2523--2533},
  year = {2024},
}

Training Like a Medical Resident: Context-Prior Learning Toward Universal Medical Image Segmentation

Yunhe Gao, Zhuowei Li, Di Liu, Mu Zhou, Shaoting Zhang, and DN Meta

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

Bib PDF

@inproceedings{Gao_2024_CVPR,
  author = {Gao, Yunhe and Li, Zhuowei and Liu, Di and Zhou, Mu and Zhang, Shaoting and Meta, DN},
  title = {Training Like a Medical Resident: Context-Prior Learning Toward Universal Medical Image Segmentation},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  pages = {11194-11204},
}

Towards self-supervised and weight-preserving neural architecture search

Zhuowei Li, Yibo Gao, Zhenzhou Zha, Zhiqiang Hu, Qing Xia, Shaoting Zhang, and Dimitris N Metaxas

In European Conference on Computer Vision, 2022

Bib PDF

@inproceedings{li2022towards,
  title = {Towards self-supervised and weight-preserving neural architecture search},
  author = {Li, Zhuowei and Gao, Yibo and Zha, Zhenzhou and Hu, Zhiqiang and Xia, Qing and Zhang, Shaoting and Metaxas, Dimitris N},
  booktitle = {European Conference on Computer Vision},
  pages = {3--19},
  year = {2022},
  organization = {Springer},
}

Contrastive and selective hidden embeddings for medical image segmentation

Zihao Liu, Zhuowei Li, Zhiqiang Hu, Qing Xia, Ruiqin Xiong, Shaoting Zhang, and Tingting Jiang

IEEE Transactions on Medical Imaging, 2022

Bib PDF

@article{liu2022contrastive,
  title = {Contrastive and selective hidden embeddings for medical image segmentation},
  author = {Liu, Zihao and Li, Zhuowei and Hu, Zhiqiang and Xia, Qing and Xiong, Ruiqin and Zhang, Shaoting and Jiang, Tingting},
  journal = {IEEE Transactions on Medical Imaging},
  volume = {41},
  number = {11},
  pages = {3398--3410},
  year = {2022},
  publisher = {IEEE},
}

A deep reinforced tree-traversal agent for coronary artery centerline extraction

Zhuowei Li, Qing Xia, Zhiqiang Hu, Wenji Wang, Lijian Xu, and Shaoting Zhang

In Medical Image Computing and Computer Assisted Intervention–MICCAI 2021: 24th International Conference, Strasbourg, France, September 27–October 1, 2021, Proceedings, Part V 24, 2021

Bib PDF

@inproceedings{li2021deep,
  title = {A deep reinforced tree-traversal agent for coronary artery centerline extraction},
  author = {Li, Zhuowei and Xia, Qing and Hu, Zhiqiang and Wang, Wenji and Xu, Lijian and Zhang, Shaoting},
  booktitle = {Medical Image Computing and Computer Assisted Intervention--MICCAI 2021: 24th International Conference, Strasbourg, France, September 27--October 1, 2021, Proceedings, Part V 24},
  pages = {418--428},
  year = {2021},
  organization = {Springer},
}