I am a third-year Ph.D. student at The Chinese University of Hong Kong, advised by Prof. Pheng-Ann Heng and Prof. Chi-Wing Fu. Prior to my Ph.D. studies, I worked as an algorithm engineer at Tencent AI Lab, where I developed RL-based game agents and designed diverse reward strategies to encourage varied playstyles. I hold an M.Sc. in Big Data Technology from The Hong Kong University of Science and Technology and a B.Sc. (Hons) in Computer Science and Technology from Beijing Normal–Hong Kong Baptist University.

My research focuses on multimodal understanding and agentic reasoning, exploring native active perception to bridge passive audio-visual understanding with active, agentic decision-making in foundation models. Currently, I am translating this vision into practice as a Research Intern at Alibaba Qwen, where I design agentic RL frameworks, algorithms, and data pipelines to enhance the complex audio-visual reasoning capabilities of foundational models.

My long-term goal is to teach machines to perceive and interact like humans. I believe that video, naturally coupled with audio, serves as the essential bridge to understand the world and ground foundational models in real-world dynamics.

Beyond academia, I am passionate about basketball, tennis, and regular gym workouts—sports define my mindset.

News & Announcements

• [01/2026] One paper accepted to ICLR 2026.
• [01/2026] One paper accepted to IJCV.
• [09/2025] Qwen3-Omni released. Check it out!
• [09/2025] One paper accepted to NeurIPS 2025.
• [02/2025] One paper accepted to CVPR 2025.
• [09/2024] One paper accepted to IEEE TIP.
• [07/2024] I finally got into the dormitory from the waiting list! 🎉

Selected Publications

• Omni-Captioner: Data Pipeline, Models, and Benchmark for Omni Detailed Perception
  Ziyang Ma*, Ruiyang Xu*, Zhenghao Xing*, Yunfei Chu, Yuxuan Wang, Jinzheng He, Jin Xu, Pheng-Ann Heng, Kai Yu, Junyang Lin, Eng Siong Chng, and Xie Chen.
  The Fourteenth International Conference on Learning Representations (ICLR), 2026.
  [Conference] [arXiv] [Code]


• Qwen3-Omni Technical Report
  Qwen Team
  ArXiv Tech Report, 2025
  [Technical Report] [arXiv] [Code] [Qwen Chat]


• EchoInk-R1: Exploring Audio-Visual Reasoning in Multimodal LLMs via Reinforcement Learning
  Zhenghao Xing, Xiaowei Hu, Chi-Wing Fu, Wenhai Wang, Jifeng Dai, and Pheng-Ann Heng.
  ArXiv Tech Report, 2025
  [Technical Report] [arXiv] [Code]


• EchoTraffic: Enhancing Traffic Anomaly Understanding with Audio-Visual Insights
  Zhenghao Xing*, Hao Chen*, Binzhu Xie, Jiaqi Xu, Ziyu Guo, Xuemiao Xu, Jianye Hao, Chi-Wing Fu, Xiaowei Hu, and Pheng-Ann Heng.
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025.
  [Conference] [Paper] [Code]


• Unveiling Deep Shadows: A Survey and Benchmark on Image and Video Shadow Detection, Removal, and Generation in the Deep Learning Era
  Xiaowei Hu*, Zhenghao Xing*, Tianyu Wang, Chi-Wing Fu, and Pheng-Ann Heng.
  International Journal of Computer Vision (IJCV), 2026.
  [Journal] [arXiv] [Code]


• Video Instance Shadow Detection Under the Sun and Sky
  Zhenghao Xing*, Tianyu Wang*, Xiaowei Hu, Haoran Wu, Chi-Wing Fu, and Pheng-Ann Heng.
  IEEE Transactions on Image Processing (IEEE TIP), 2024.
  [Journal] [Paper] [arXiv] [Code]