Zhaoyang Liu (刘兆洋)

Zhaoyang Liu (刘兆洋)

I began my Ph.D. in Computer Science and Engineering at The Hong Kong University of Science and Technology (HKUST) in September 2023, advised by Prof. Qifeng Chen. Since then, I have worked closely with Shanghai AI Laboratory on multimodal foundation models and agentic systems, with recent efforts centered on open-source computer use agents, multimodal large language models, AI-generated content, and video understanding. My recent research includes projects such as ScaleCUA, InternVL, VisionLLM, ControlLLM, AudioX, and InternGPT, and I am broadly interested in building practical multimodal systems that can perceive, reason, and act in complex real-world settings.

🔥 News

  • 2026.04: 🎉 One paper accepted to ACL 2026.
  • 2026.03: 🎉 One paper accepted to SIGGRAPH 2026.
  • 2026.02: 🎉 Two papers accepted to CVPR 2026.
  • 2026.01: 🎉 Three papers accepted to ICLR 2026, including one Oral and two Posters.

💼 Experience

  • 2023.04 - 2025.10 | Research Intern, Shanghai AI Laboratory, Shanghai, China
    Worked with Wenhai Wang and Jifeng Dai on large language models and multimodal learning.
  • 2022.04 - 2023.04 | Part-time Researcher, Shanghai AI Laboratory, Shanghai, China
    Led interns on video understanding, multimodal learning, and pose pretraining.
  • 2020.07 - 2023.04 | Algorithm Engineer, SenseTime, Shanghai, China
    Led a project on detecting highlight moments in videos and worked on video classification, highlight detection, and boundary detection.
  • 2019.09 - 2020.07 | Research Intern, SenseTime, Beijing, China
    Worked on action recognition.
  • 2019.05 - 2019.09 | Research Intern, Tencent Youtu Lab, Shanghai, China
    Worked on action recognition.

📚 Selected Publications

ScaleCUA publication thumbnail

GitHub Hugging Face

ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data

Zhaoyang Liu, JingJing Xie, Zichen Ding, Zehao Li, Bowen Yang, Zhenyu Wu, et al.

ICLR 2026 Oral

InternVL3.5 publication thumbnail

GitHub Hugging Face

InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

Weiyun Wang*, Zhangwei Gao*, Lixin Gu*, Hengjun Pu*, Long Cui*, Xingguang Wei*, Zhaoyang Liu*, et al.

arXiv preprint, 2025

AudioX publication thumbnail

GitHub Hugging Face

AudioX: A Unified Framework for Anything-to-Audio Generation

Zeyue Tian, Zhaoyang Liu, Yizhu Jin, Ruibin Yuan, Liumeng Xue, et al.

Accepted to ICLR, 2026

VisionLLM v2 publication thumbnail

GitHub Hugging Face

VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks

Jiannan Wu*, Muyan Zhong*, Sen Xing*, Zeqiang Lai*, Zhaoyang Liu*, et al.

NeurIPS, 2024

ControlLLM publication thumbnail

GitHub Hugging Face

ControlLLM: Augment Language Models with Tools by Searching on Graphs

Zhaoyang Liu, Zeqiang Lai, Zhangwei Gao, Erfei Cui, Ziheng Li, et al.

ECCV, 2024

InternGPT publication thumbnail

GitHub Hugging Face

InternGPT: Solving Vision-Centric Tasks by Interacting with ChatGPT Beyond Language

Zhaoyang Liu, Yinan He, Wenhai Wang, Weiyun Wang, Yi Wang, et al.

arXiv preprint, 2023

Show All Publications from Google Scholar

Synced from Google Scholar on 2026-04-15.

🏆 Honors and Awards

  • 2023 RedBird PhD Award, The Hong Kong University of Science and Technology.
  • 2020 Excellent Student Award, Nanjing University.
  • 2020 Outstanding Graduate Award, Nanjing University.
  • 2018 First Place, China Postgraduate Innovation and Practice Competition, Action Recognition Track.
  • 2018 Huawei Scholarship, Nanjing University.
  • 2015 Second Prize, Oracle Cup, East China Division.
  • 2015 First Prize, Jingsheng Cup Computer Programming Competition, Anhui Province.

🤝 Academic Services

Journal Reviewer

  • IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
  • International Journal of Computer Vision (IJCV)
  • IEEE Transactions on Image Processing (TIP)
  • Pattern Recognition (PR)

Conference Reviewer

  • CVPR, ECCV, ICCV, NeurIPS, ICLR, ICML

🎓 Teaching

  • 2018 Spring Teaching Assistant, Experiments for Programming Design, Nanjing University.
  • 2024 Spring Teaching Assistant, Fundamentals of Artificial Intelligence, HKUST.
  • 2024 Autumn Teaching Assistant, Design and Analysis of Algorithms, HKUST.
  • 2025 Autumn Teaching Assistant, Exploring Artificial Intelligence, HKUST.