Image

Fangrui Zhu


Ph.D. Student, Northeastern University
Boston, MA, U.S.
zhu.fang@northeastern.edu
CVGoogle ScholarGitHubX (Twitter)

About Me


I am a final-year PhD at Khoury College of Computer Sciences, Northeastern University, advised by Prof. Huaizu Jiang. I am also fortunate to collaborate closely with Dr. Jianwei Yang. Before that, I received my Bachelor's degree in Software Engineering from Tongji University and Master's degree in Statistics from Fudan University.

Research Interests


3D Reasoning, Multimodal LLMs, Video Understanding.

Publications and Preprints


Image

PhyWorldBench: A Comprehensive Evaluation of Physical Realism in Text-to-Video Models
Jing Gu, Xian Liu, Yu Zeng, Ashwin Nagarajan, Fangrui Zhu, Daniel Hong, Yue Fan, Qianqi Yan, Kaiwen Zhou, Ming-Yu Liu, Xin Eric Wang,
International Conference on Learning Representations (ICLR Oral), 2026.
[PDF] [Code] [Project Page]

Image

Struct2D: A Perception-Guided Framework for Spatial Reasoning in Large Multimodal Models
Fangrui Zhu*, Hanhui Wang*, Yiming Xie, Jing Gu, Tianye Ding, Jianwei Yang, Huaizu Jiang. (* equal contribution)
Annual Conference on Neural Information Processing Systems (NeurIPS), 2025.
[PDF] [Code]

Image

Diagnosing human-object interaction detectors
Fangrui Zhu, Yiming Xie, Weidi Xie, Huaizu Jiang.
International Journal of Computer Vision (IJCV), 2025.
[PDF] [Code] [Project Page]

Image

TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models
Mu Cai, Reuben Tan, Jianrui Zhang, Bocheng Zou, Kai Zhang, Feng Yao, Fangrui Zhu, Jing Gu, Yiwu Zhong, Yuzhang Shang, Yao Dou, Jaden Park, Jianfeng Gao, Yong Jae Lee, Jianwei Yang.
arXiv, 2024.
[PDF] [Code] [Project Page]

Image

Towards Flexible Visual Relationship Segmentation
Fangrui Zhu, Jianwei Yang, Huaizu Jiang.
Annual Conference on Neural Information Processing Systems (NeurIPS), 2024.
[PDF] [Code] [Project Page]

Image

Vessel-Aware Aneurysm Detection Using Multi-scale Deformable 3D Attention
Alberto M. Ceballos-Arroyo, Hieu T Nguyen, Fangrui Zhu, Shrikanth M Yadav, Jisoo Kim, Lei Qin, Geoffrey Young, Huaizu Jiang.
International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2024.
[PDF] [Code]

Image

Zero-shot referring expression comprehension via structural similarity between images and captions
Zeyu Han, Fangrui Zhu, Qianru Lao, Huaizu Jiang.
Computer Vision and Pattern Recognition (CVPR), 2024.
[PDF] [Code]

Image

A Unified Efficient Pyramid Transformer for Semantic Segmentation
Fangrui Zhu, Yi Zhu, Li Zhang, Chongruo Wu, Yanwei Fu, Mu Li.
International Conference on Computer Vision Workshop (ICCVW), 2021.
[PDF] [Code]

Image

Self-supervised video object segmentation
Fangrui Zhu, Li Zhang, Yanwei Fu, Guodong Guo, Weidi Xie.
arXiv, 2020.
[PDF]

Image

Long-Term Cloth-Changing Person Re-identification
Xuelin Qian, Wenxuan Wang, Li Zhang, Fangrui Zhu, Yanwei Fu, Tao Xiang, Yugang Jiang, Xiangyang Xue.
Asian Conference on Computer Vision (ACCV), 2020.
[PDF] [Project Page]

Image

Main-Secondary Network for Defect Segmentation of Textured Surface Images
Yu Xie, Fangrui Zhu, Yanwei Fu.
Winter Conference on Applications of Computer Vision (WACV), 2020.
[PDF]

Image

A Two-Point Method for PTZ Camera Calibration in Sports
Jianhui Chen, Fangrui Zhu, James J Little.
Winter Conference on Applications of Computer Vision (WACV), 2018.
[PDF] [Code]

Service


Reviewer for ICCV2021, ECCV2022, BMVC2022, CVPR2022-2025, ICCV2023, ECCV2024, NeurIPS2024, ICML2025, IEEE TPAMI.

Misc


I enjoy staying active with Pilates, Gyrotonic, and Snowboarding.