Shi Yufei

Shi Yufei

Ph.D. Student from NTU, interested in Video LLM and Medical AI

About Me

I am a PhD student in the Department of Data Science at LKC Medical School, Nanyang Technological University, under the supervision of Prof. Si Yong Yeo, Prof. Yu Baosheng, and Prof. Li Ming.

I completed my master’s degree at the Department of Computer Engineering, Show Lab @ National University of Singapore, where I was supervised by Prof. Mike Zheng Shou.

You can find my CV here: Yufei Shi’s Curriculum Vitae and Chinese CV.

Email / Github

Recent News

  • [Jun. 2026] Seeing Through Multiple Views: Parameter-Efficient Fine-Tuning via Selective Neurons for Consistent Radiology Report Generation is accepted by MICCAI 2026!
  • [May. 2026] One Sentence, One Drama: Personalized Short-Form Drama Generation via Multi-Agent Systems is available on arXiv.
  • [May. 2026] 4DPC^2hat: Towards Dynamic Point Cloud Understanding with Failure-Aware Bootstrapping is accepted by ICML 2026!
  • [Mar. 2026] RIHA: Report-Image Hierarchical Alignment for Radiology Report Generation is published online in IEEE JBHI!
  • [Feb. 2026] SciEducator: Scientific Video Understanding and Educating via Deming-Cycle Multi-Agent System is accepted by CVPR 2026!
  • [Sep. 2025] ColonNeRF: Hierarchical Neural Radiance Fields for High-Fidelity Long-Sequence Colon Reconstruction is accepted by Neurocomputing 2025.
  • [Jun. 2025] PVChat: Personalized Video Chat with One-Shot Learning is accepted by ICCV 2025!

Publications

Seeing Through Multiple Views: Parameter-Efficient Fine-Tuning via Selective Neurons for Consistent Radiology Report Generation

Yucheng Chen, Jinjing Zhu, Yang Yu, Yufei Shi, Hane Naghshbandi, Jinhua Liu, Angela S. Koh, Fang Fen, Kian Eng Ong, Si Yong Yeo

MICCAI, 2026

[Paper]

A parameter-efficient framework that detects and selectively fine-tunes view-specific neurons to improve consistency in multi-view radiology report generation.

One Sentence, One Drama: Personalized Short-Form Drama Generation via Multi-Agent Systems

Yufei Shi*, Weilong Yan*, Naixuan Huang, Yucheng Chen, Chenyu Zhang, Tao He, Si Yong Yeo, Ming Li

Under Review, 2026

[Paper]

A multi-agent system for single-sentence to short-drama generation with pacing, narrative coherence, and 3D consistency.

4DPC^2hat: Towards Dynamic Point Cloud Understanding with Failure-Aware Bootstrapping

Xindan Zhang, Weilong Yan, Yufei Shi, Xuerui Qiu, Tao He, Ying Li, Ming Li, Hehe Fan

ICML, 2026

[Paper]

A failure-aware framework that helps multimodal large language models understand dynamic point cloud sequences.

RIHA: Report-Image Hierarchical Alignment for Radiology Report Generation

Yucheng Chen, Yang Yu, Yufei Shi, Conghao Xiong, Xulei Yang, Si Yong Yeo

IEEE JBHI, 2026

[Paper]

A hierarchical alignment framework for radiology report generation that aligns visual and textual features across paragraph, sentence, and word levels.

SciEducator: Scientific Video Understanding and Educating via Deming-Cycle Multi-Agent System

Zhiyu Xu, Weilong Yan, Yufei Shi, Xin Meng, Tao He, Huiping Zhuang, Ming Li, Hehe Fan

CVPR, 2026

[Paper]

The first multi-agent system for scientific video understanding and education.

ColonNeRF: Neural Radiance Fields for High-Fidelity Long-Sequence Colonoscopy Reconstruction

Yufei Shi, Beijia Lu, Jia-Wei Liu, Ming Li, Si Yong Yeo, and Mike Zheng Shou

Neurocomputing, 2025

[Paper] [Project]

PVChat: Personalized Video Chat with One-Shot Learning

Yufei Shi†, Weilong Yan†, Gang Xu, Yumeng Li, Yucheng Chen, Zhenxi Li, Fei Richard Yu, Ming Li*, Si Yong Yeo*

ICCV, 2025

[Paper] [Project]

Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation

Jay Zhangjie Wu, Yixiao Ge, Xintao Wang, Weixian Lei, Yuchao Gu, Yufei Shi, Wynne Hsu, Ying Shan, Xiaohu Qie, Mike Zheng Shou

ICCV, 2023

[Paper] [Project]