Haoyu Kuang

I am Haoyu Kuang (旷皓予), a second year master student at Fudan University in the School of Data Science, Shanghai, China. I’m currently advised by Prof. Zhongyu Wei and carrying out my research at the Data Intelligence and Social Computing Lab (Fudan DISC).

Research Interests

My interested research topics are mostly around computational social science and graph representation learning, including:

• Computational Social Science via Large Vision Language Model
• Agents Simulation powered by Large Language Model
• Text-Attributed Graph Pre-training

Publication

* indicates equal contributions.

• Multi-agent KTO: Reinforcing Strategic Interactions of Large Language Model in Language Game. Preprint 2025
  Rong Ye*, Yongxin Zhang*, Yikai Zhang, Haoyu Kuang, Zhongyu Wei, Peng Sun.
• AgentSense: Benchmarking Social Intelligence of Language Agents through Interactive Scenarios. NAACL 2025
  Xinyi Mou*, Jingcong Liang*, Jiayu Lin*, Xinnong Zhang*, Xiawei Liu, Shiyue Yang, Rong Ye, Lei Chen, Haoyu Kuang, Xuanjing Huang, Zhongyu Wei.
• AI-Press: A Multi-Agent News Generating and Feedback Simulation System Powered by Large Language Models. COLING 2025 Demo
  Xiawei Liu*, Shiyue Yang*, Xinnong Zhang, Haoyu Kuang, Libo Sun, Yihang Yang, Siming Chen, Xuanjing Huang, Zhongyu Wei.
• SoMeLVLM: A Large Vision Language Model for Social Media Processing. Findings of the Association for Computational Linguistics: ACL 2024
  Xinnong Zhang*, Haoyu Kuang*, Xinyi Mou, Hanjia Lyu, Kun Wu, Siming Chen, Jiebo Luo, Xuanjing Huang, Zhongyu Wei.
• Unleashing the Power of Language Models in Text-Attributed Graph. Findings of the Association for Computational Linguistics: EMNLP 2023
  Haoyu Kuang, Jiarong Xu, Haozhe Zhang, Zuyu Zhao, Qi Zhang, Xuanjing Huang, Zhongyu Wei.