Introduction

👋 Nice to meet you! I am a final-year undergraduate student at The Chinese University of Hong Kong, Shenzhen (CUHK-SZ), where I have been conducting research under the guidance of Prof. Tianshu Yu and Xinjian Zhao. I am deeply grateful for their invaluable mentorship and continuous support, which have greatly shaped my academic growth.

🧑‍🏫 Looking ahead, I will be joining the Institute of Automation, Chinese Academy of Sciences (CASIA) as a PhD student under the supervision of Prof. Liang Wang. I am genuinely excited to take on new challenges!

🤔 My general research interests span Reinforcement Learning and AI for Science. However, I am still exploring my long-term research direction and remain open to discussions and collaborations across related areas.

Education

Publications

📄 The Underappreciated Power of Vision Models for Graph Structural Understanding

NeurIPS '25 — Xinjian Zhao*, Wei Pang*, Zhongkai Xue*, Xiangru Jian, Lei Zhang, Yaoyao Xu, Xiaozhuang Song, Shu Wu, Tianshu Yu.

Abstract: We conduct a systematic analysis that uncovers how visual perception and message‑passing offer complementary strengths in graph understanding, and introduce a novel benchmark to showcase these insights. Our findings reveal that vision models can significantly enhance graph structural understanding, outperforming traditional GNNs in various tasks.

[proceedings] [code]

📄 MJ-VIDEO: Fine-Grained Benchmarking and Rewarding Video Preferences in Video Generation

NeurIPS Spotlight '25 — Haibo Tong, Zhaoyang Wang, Zhaorun Chen, Haonian Ji, Shi Qiu, Siwei Han, Kexin Geng, Zhongkai Xue , Yiyang Zhou, Peng Xia, Mingyu Ding, Rafael Rafailov, Chelsea Finn, Huaxiu Yao

Abstract: We present MJ-VIDEO, a Mixture-of-Experts reward model for fine-grained video preference evaluation, which is built upon MJ-BENCH-VIDEO, a large-scale benchmark covering alignment, safety, coherence, and bias. Our model achieves significant improvements in preference judgment and enhances alignment in video generation.

[proceedings] [code] [site]

📄 Political-LLM: Large Language Models in Political Science

TMLR ’25 — Lincan Li, Jiaqi Li, Catherine Chen, Fred Gui, Hongjia Yang, Chenxiao Yu, Zhengguang Wang, Jianing Cai, Junlong Aaron Zhou, Bolin Shen, Alex Qian, Zhongkai Xue ... Yue Zhao, Yushun Dong et al. Lincan Li, Jiaqi Li, Catherine Chen, Fred Gui, Hongjia Yang, Chenxiao Yu, Zhengguang Wang, Jianing Cai, Junlong Aaron Zhou, Bolin Shen, Alex Qian, Zhongkai Xue , Lichao Sun, Lifang He, Hanjie Chen, Kaize Ding, Zijian Du, Fangzhou Mu, Jiaxin Pei, Jieyu Zhao, Swabha Swayamdipta, Willie Neiswanger, Hua Wei, Xiyang Hu, Shixiang Zhu, Tianlong Chen, Yingzhou Lu, Yang Shi, Lianhui Qin, Tianfan Fu, Zhengzhong Tu, Yuzhe Yang, Jaemin Yoo, Jiaheng Zhang, Ryan Rossi, Liang Zhan, Liang Zhao, Emilio Ferrara, Yan Liu, Furong Huang, Xiangliang Zhang, Lawrence Rothenberg, Shuiwang Ji, Philip S. Yu, Yue Zhao, Yushun Dong Full

Abstract: We propose Political-LLM, a framework that bridges large language models with political science. It provides a dual-perspective taxonomy, political tasks and computational methods, while outlining key challenges and future directions, aiming to guide ethical and effective AI use in political research.

[arxiv] [code] [site]

* indicates equal contribution.