Henghui Ding

Henghui Ding is currently a Professor at Fudan University. Prior to that, he was a Presidential Postdoctoral Fellow (Principal Investigator) at Nanyang Technological University (NTU) in Singapore, a Postdoctoral Researcher at ETH Zürich in Switzerland, and a Research Scientist at ByteDance AI Lab in Singapore. He received the Ph.D. degree (winner of the Best Thesis Award) from NTU in 2020, and the B.E. degree from Xi’an Jiaotong University in 2016. His research interests broadly include machine learning and computer vision. Specifically, he focuses on scene understanding (e.g., video/image segmentation, detection), AIGC (e.g., video/image generation/editing), multi-modal learning (e.g., vision-language), low-shot learning, and human–computer interaction. He serves/served as an Area Chair for CVPR’(24-26), NeurIPS’(24-26), ICML’(25-26), ICLR’(25-26), ECCV’26, AAAI’26, ACM MM’(24-26), BMVC’(24-26), and a Senior Program Committee (SPC) member for AAAI’(22-25), IJCAI’(23-25). He serves as an Associate Editor for IEEE Transactions on Image Processing (TIP) and Pattern Recognition (PR).

News

Selected Publications

1. arXiv

   WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation

   Kaining Ying, Hengrui Hu, Siyu Ren, Jiamu Li, Fengjiao Chen, Ziwen Wang, Xuezhi Cao, Xunliang Cai, and Henghui Ding†

   arXiv (arXiv), 2026

   PDF Code Website
2. arXiv

   MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes

   Henghui Ding, Kaining Ying, Chang Liu, Shuting He, Xudong Jiang, Yu-Gang Jiang, Philip HS Torr, and Song Bai

   arXiv preprint arXiv:2508.05630 (arXiv), 2025

   PDF Code Website
3. arXiv

   Learning to Model the World: A Survey of World Models in Artificial Intelligence

   Jiahua Dong, Qi Lyu, Baichen Liu, Xudong Wang, Wenqi Liang, Duzhen Zhang, Jiahang Tu, Hongliu Li, Hanbin Zhao, Henghui Ding, Yulun Zhang, Zhi Han, Nicu Sebe, Fahad Shahbaz Khan, Salman Khan, and 4 more authors

   TechRxiv (arXiv), 2026

   PDF Code
4. TPAMI

   MeViS: A Multi-Modal Dataset for Referring Motion Expression Video Segmentation

   Henghui Ding, Chang Liu, Shuting He, Kaining Ying, Xudong Jiang, Chen Change Loy, and Yu-Gang Jiang

   IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025

   PDF Code Website
5. IJCV

   GREx: Generalized Referring Expression Segmentation, Comprehension, and Generation

   Henghui Ding, Chang Liu, Shuting He, Xudong Jiang, and Yu-Gang Jiang

   International Journal of Computer Vision (IJCV), 2026

   PDF Code Website
6. arXiv

   Multimodal Referring Segmentation: A Survey

   Henghui Ding, Song Tang, Shuting He, Chang Liu, Zuxuan Wu, and Yu-Gang Jiang

   arXiv preprint arXiv:2508.00265 (arXiv), 2025

   PDF Website
7. CVPR Highlight

   EffectErase: Joint Video Object Removal and Insertion for High-Quality Effect Erasing

   Yang Fu, Yike Zheng, Ziyun Dai, and Henghui Ding†

   In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR Highlight), 2026

   PDF Code Website
8. CVPR Highlight

   GlyphPrinter: Region-Grouped Direct Preference Optimization for Glyph-Accurate Visual Text Rendering

   Xincheng Shuai*, Ziye Li*, Henghui Ding†, and Dacheng Tao

   In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR Highlight), 2026

   PDF Code Website
9. CVPR

   PSDesigner: Automated Graphic Design with a Human-Like Creative Workflow

   Xincheng Shuai*, Song Tang*, Yutong Huang, Henghui Ding†, and Dacheng Tao

   In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

   PDF Code Website
10. ICML

    OcclusionFormer: Arranging Z-Order for Layout-Grounded Image Generation

    Ziye Li, and Henghui Ding†

    In International Conference on Machine Learning (ICML), 2026

    PDF Code Website
11. ICLR

    AutoFly: Vision-Language-Action Model for UAV Autonomous Navigation in the Wild

    Xiaolou Sun, Wufei Si, Wenhui Ni, Yuntian Li, Dongming Wu, Fei Xie, Runwei Guan†, He-Yang Xu, Henghui Ding†, Yuan Wu, Yutao Yue, Yongming Huang†, and Hui Xiong

    In International Conference on Learning Representations (ICLR), 2026

    PDF Code Website
12. AAAI

    Segment Anything Across Shots: A Method and Benchmark

    Hengrui Hu, Kaining Ying, and Henghui Ding†

    In AAAI Conference on Artificial Intelligence (AAAI), 2026

    PDF Code Website
13. NeurIPS Spotlight

    SceneDesigner: Controllable Multi-Object Image Generation with 9-DoF Pose Manipulation

    Zhenyuan Qin, Xincheng Shuai, and Henghui Ding†

    In Advances in Neural Information Processing Systems (NeurIPS Spotlight), 2025

    PDF Code Website
14. NeurIPS

    SAMA: Towards Multi-Turn Referential Grounded Video Chat with Large Language Models

    Ye Sun, Hao Zhang, Henghui Ding†, Tiehua Zhang, Xingjun Ma†, and Yu-Gang Jiang

    In Advances in Neural Information Processing Systems (NeurIPS), 2025

    PDF Code
15. ICCV

    Towards Omnimodal Expressions and Reasoning in Referring Audio-Visual Segmentation

    Kaining Ying, Henghui Ding†, Guangquan Jie, and Yu-Gang Jiang

    In IEEE/CVF International Conference on Computer Vision (ICCV), 2025

    PDF Code Website
16. ICCV

    MOVE: Motion-Guided Few-Shot Video Object Segmentation

    Kaining Ying*, Hengrui Hu*, and Henghui Ding†

    In IEEE/CVF International Conference on Computer Vision (ICCV), 2025

    PDF Code Website
17. ICCV

    Free-Form Motion Control: Controlling the 6D Poses of Camera and Objects in Video Generation

    Xincheng Shuai, Henghui Ding†, Zhenyuan Qin, Hao Luo, Xingjun Ma, and Dacheng Tao

    In IEEE/CVF International Conference on Computer Vision (ICCV), 2025

    PDF Code Website
18. ICCV

    AnyI2V: Animating Any Conditional Image with Motion Control

    Ziye Li, Hao Luo, Xincheng Shuai, and Henghui Ding†

    In IEEE/CVF International Conference on Computer Vision (ICCV), 2025

    PDF Code Website
19. ICCV

    CharaConsist: Fine-Grained Consistent Character Generation

    Mengyu Wang, Henghui Ding†, Jianing Peng, Yao Zhao, Yunpeng Chen, and Yunchao Wei^†

    In IEEE/CVF International Conference on Computer Vision (ICCV), 2025

    PDF Code Website
20. ICML Oral

    ReferSplat: Referring Segmentation in 3D Gaussian Splatting

    Shuting He, Guangquan Jie, Changshuo Wang, Yun Zhou, Shuming Hu, Guanbin Li, and Henghui Ding†

    In International Conference on Machine Learning (ICML Oral), 2025

    PDF Code
21. TPAMI

    Transformer-based Visual Segmentation: A survey

    Xiangtai Li, Henghui Ding, Haobo Yuan, Wenwei Zhang, Guangliang Cheng, Jiangmiao Pang, Kai Chen, Ziwei Liu, and Chen Change Loy

    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024

    PDF Code
22. TPAMI

    Towards Open Vocabulary Learning: A Survey

    Jianzong Wu, Xiangtai Li, Shilin Xu, Haobo Yuan, Henghui Ding, Yibo Yang, Xia Li, Jiangning Zhang, Yunhai Tong, Xudong Jiang, Bernard Ghanem, and Dacheng Tao

    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024

    PDF Code
23. TPAMI

    VLT: Vision-Language Transformer and Query Generation for Referring Segmentation

    Henghui Ding, Chang Liu, Suchen Wang, and Xudong Jiang

    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023

    PDF Code
24. ICCV

    MOSE: A New Dataset for Video Object Segmentation in Complex Scenes

    Henghui Ding, Chang Liu, Shuting He, Xudong Jiang, Philip H.S. Torr, and Song Bai

    In IEEE/CVF International Conference on Computer Vision (ICCV), 2023

    PDF Code Website
25. ICCV

    MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions

    Henghui Ding, Chang Liu, Shuting He, Xudong Jiang, and Chen Change Loy

    In IEEE/CVF International Conference on Computer Vision (ICCV), 2023

    PDF Code Website
26. CVPR Highlight

    GRES: Generalized Referring Expression Segmentation

    Chang Liu*, Henghui Ding*†, and Xudong Jiang

    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR Highlight), 2023

    PDF Code Website
27. TPAMI

    A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation

    He, Peilin Shuting Ji, Yitong Yang, Changshuo Wang, Jiayi Ji, Yinglin Wang, and Henghui Ding†

    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2026

    PDF Code