I am now a master’s student at School of Artificial Intelligence, Nanjing University, and a member of NJU NLP Group. Before that, I received my B.Eng. degree from Huazhong University of Science and Technology in 2024.

My research interests include multimodal large language models and visual agents.

🔥 News

  • 2026.08: MultiModal Code-Switching was accepted to EMNLP 2026 Main.
  • 2026.08: Released OpenVisTool, an open framework for synthesizing instructive visual tool-use trajectories.
  • 2026.05: GePBench was accepted to ICML 2026.

📑 Publications

OpenVisTool overview

OpenVisTool: An Open Recipe for Synthesizing Instructive Visual Tool-Use Trajectories

Changhao Xiang*, Shilin Zhang*, Zheng Ma, Kanzhi Cheng, Ruize Ma, Yi Feng, Jianbing Zhang, Zhi Wang, Zhen Wu, Xinyu Dai, Lewei Lu

arXiv preprint, 2026

[Paper] [Code]

MultiModal Code-Switching overview

MultiModal Code-Switching: Interleaving Visual Objects into Language for Explicit Object-Level Alignment

Changhao Xiang, Shangyu Xing, Zhen Wu, Jianbing Zhang, Xinyu Dai

EMNLP 2026 Main

[Paper] [Code]

GePBench construction pipeline

GePBench: Evaluating Fundamental Geometric Perception for Multimodal Large Language Models

Shangyu Xing*, Changhao Xiang*, Yuteng Han, Yifan Yue, Zhen Wu, Xinyu Liu, Zhangtai Wu, Fei Zhao, Xinyu Dai

ICML 2026

[Paper] [Code]

📖 Education

  • 2024.09 - Present, M.S. at School of Artificial Intelligence, Nanjing University.
  • 2020.09 - 2024.06, B.E. at School of Artificial Intelligence and Automation, Huazhong University of Science and Technology.

💻 Internships

  • 2026.06 - Present, ByteDance.
  • 2025.11 - 2026.05, SenseTime Research.