Zhenghao Xing邢正昊

Zhenghao Xing

I am a fourth-year Ph.D. student at The Chinese University of Hong Kong (CUHK), advised by Prof. Pheng-Ann Heng and Prof. Chi-Wing Fu.

My research focuses on multimodal agents and video reasoning: building foundation models that can see, hear, reason, and act.

I am now a research scientist intern at ByteDance, San Jose, working on multimodal agents for video understanding and code-driven creation.

Previously, I interned at Alibaba Qwen, working on omni-modal reasoning, multimodal agents, and RL post-training.

On the job market in 2027. Happy to connect about opportunities.

More about my background

During my Ph.D., I interned at Alibaba Qwen, building agentic RL frameworks, algorithms, and data pipelines for omni-modal reasoning in foundation models. Before CUHK, I worked at Tencent AI Lab on RL-based game agents, designing reward strategies for diverse playstyles.

I hold an M.Sc. in Big Data Technology from The Hong Kong University of Science and Technology (HKUST). I completed my undergraduate studies in Computer Science and Technology at Beijing Normal-Hong Kong Baptist University (BNBU), earning a B.Sc. (Hons) awarded by Hong Kong Baptist University (HKBU).

My long-term goal is to build multimodal agents that understand the world as it unfolds. I see video, naturally coupled with audio, as the bridge from multimodal perception to agentic interaction in open-ended environments.

Research

Google Scholar ↗

Selected publications and technical reports. * Equal contribution.

  1. Technical Report2026

    Qwen3.8-Omni: Towards Native Omni-Modal Agents

    Qwen Team

    arXivBlogQwen Chat
  2. Preprint2026

    Omni2Web: Benchmarking Audiovisual Website Development

    Minghao Han*, Zhenghao Xing*, Xize Cheng, Yuxuan Wang, Junming Lin, Ling Wang, Yinsong Yan, Yunfei Chu, Qize Yang, and Jin Xu.

    arXivProject
  3. ICML2026

    Native Active Perception as Reasoning for Omni-Modal Understanding

    Zhenghao Xing*, Ruiyang Xu*, Yuxuan Wang*, Jinzheng He, Ziyang Ma, Qize Yang, Yunfei Chu, Jin Xu, Junyang Lin, Chi-Wing Fu, and Pheng-Ann Heng.

    PaperarXivCodeModelSlides
  4. Technical Report2026

    Qwen3.5-Omni Technical Report

    Qwen Team

    arXivBlogQwen Chat
  5. ICLR2026

    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.

    PaperarXivCodeModel
  6. IJCV2026

    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.

    PaperarXivCodeModel
  7. Technical Report2025

    Qwen3-Omni Technical Report

    Qwen Team

    arXivBlogCodeModelQwen Chat
  8. Technical Report2025

    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.

    arXivCodeModel
  9. CVPR2025

    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.

    PaperCodeModel
  10. TIP2024

    Video Instance Shadow Detection Under the Sun and Sky

    Zhenghao Xing*, Tianyu Wang*, Xiaowei Hu, Haoran Wu, Chi-Wing Fu, and Pheng-Ann Heng.

    PaperarXivCodeModel

News

Earlier updatesFewer updates

  • Invited to give a booth talk on OmniAgent at the Alibaba Qwen booth during ICML 2026 in Seoul (#B400, Jul 8, 13:20–13:40); slides are now available on Hugging Face Spaces.

  • Selected for the Tencent Project Up Scholarship for ICML 2026.

  • One paper accepted to ICML 2026! OmniAgent introduces the first native omni-modal agent for active perception, treating video perception as an iterative reasoning process. The arXiv paper, code, and models are now publicly released.

  • Qwen3.5-Omni is here!

  • One paper accepted to ICLR 2026.

  • One paper accepted to IJCV.

  • Qwen3-Omni is here!

  • One paper accepted to NeurIPS 2025.

  • One paper accepted to CVPR 2025.

  • One paper accepted to TIP.

  • Moved into campus housing after a long wait!

Academic service & honors

Reviewer

  • CVPR 2026
  • ICML 2026 (Silver Reviewer)
  • ECCV 2026
  • WACV 2027

Awards

  • 2026Project Up Scholarship (ICML), Tencent
  • 2023Postgraduate Scholarship, The Chinese University of Hong Kong
  • 2019President's Honour Roll & First Class Scholarship, Beijing Normal-Hong Kong Baptist University

Invited talks

Native Active Perception as Reasoning for Omni-Modal Understanding

Alibaba Qwen Booth #B400, ICML 2026
Jul 8, 2026, 13:20–13:40 · Seoul, Korea

View slides ↗

Research figure