I am currently a Ph.D. candidate in a joint program between Harbin Institute of Technology (Shenzhen) and Great Bay University. I am supervised by Prof. Yong Xu and Prof. Zitong Yu. My research focuses on subtle human behavior understanding and multimodal intelligence, with particular interests in micro-gesture recognition, multimodal large language models, affective intelligence, and efficient 3D vision.

I received my B.Sc. degree in Cyberspace Security from Harbin Institute of Technology in 2023, where I was supervised by Prof. Xiaojun Tong, and my M.Sc. degree in Artificial Intelligence from Nanyang Technological University in 2025, under the supervision of Prof. Shijian Lu.

🔥 News

• 2026.08.11: Our method placed 2nd in Track 1 (Micro-gesture Classification) of the 4th MiGA-IJCAI Challenge. The accompanying paper, SwinT-Enhanced Class-Wise Fusion for Micro-gesture Classification, was published in the IJCAI 2026 workshop proceedings.
• 2026.07: Our paper GMoT was accepted to ACM Multimedia 2026.
• 2026.07: AffectAgent was accepted to ACM Multimedia 2026.
• 2026.06: DeceptionX, an explainable multimodal deception-detection framework, was released on arXiv.
• 2026.04: AffectAgent, a collaborative multi-agent approach to multimodal emotion recognition, was released on arXiv.
• 2026.03: Our micro-gesture survey appeared in Machine Intelligence Research.
• 2025: TC-GS was selected for an oral presentation at ICME 2025.

📝 Selected Publications

• GMoT: Gated Motion-Aware Tokenization for Fine-Grained Micro-Gesture Video Reasoning with Multimodal LLMs
  Taorui Wang, Wei Xia, Hui Ma, Zijia Song, Jiayu Zhang, Zeheng Wang, Yong Xu, Zitong Yu
  ACM Multimedia, 2026. Project

• Micro-gesture Recognition: A Comprehensive Survey of Datasets, Methods, and Challenges
  Taorui Wang^†, Xun Lin^†, Yong Xu, Qilang Ye, Dan Guo, Sergio Escalera, Ghada Khoriba, Zitong Yu
  Machine Intelligence Research, 2026. Project

• TC-GS: Tri-plane based Compression for 3D Gaussian Splatting
  Taorui Wang, Zitong Yu, Yong Xu
  IEEE International Conference on Multimedia and Expo (ICME), Oral, 2025. arXiv · Code

• AffectAgent: Collaborative Multi-Agent Reasoning for Retrieval-Augmented Multimodal Emotion Recognition
  Zeheng Wang, Zitong Yu, Yijie Zhu, Bo Zhao, Haochen Liang, Taorui Wang, et al.
  ACM Multimedia, 2026. Project

^† Equal contribution.

For the most up-to-date list, please see my Google Scholar profile.

💻 Projects

• Awesome Micro-Gesture: A continuously updated collection of datasets, methods, and resources for micro-gesture research.
• TC-GS: Official implementation of tri-plane based compression for 3D Gaussian Splatting.

📖 Education

• 2025–Present, Ph.D. Candidate, Harbin Institute of Technology (Shenzhen) & Great Bay University, Joint Program.
• 2025, M.Sc. in Artificial Intelligence, Nanyang Technological University, Singapore. Supervised by Prof. Shijian Lu.
• 2023, B.Sc. in Cyberspace Security, Harbin Institute of Technology, China. Supervised by Prof. Xiaojun Tong.