春日宴，綠酒一杯歌一遍
"A springtide banquet, green wine in hand -- and lo, the song is sung but once, then lost to time."
Objective
I am an undergraduate with a goal of pursuing a PhD in Computer Science starting in Fall 2026. My research interest spans broadly across multimodal foundation models and intersectional domains. I am always open to embracing new opportunities!
Explored the graph-structured data representation and reasoning in the era of LLMs.
Investigated the potential of molecular graph pretraining and applied it to real-world problems.
Publications
📄 Paper 1 to reveal
Preprint -- A, B, C, D
📄 Paper 2 to reveal
Preprint -- A, B, C, D, E
📄 Political-LLM: Large Language Models in Political Science
Under review '25 --
Lincan Li, Jiaqi Li, Catherine Chen ... 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, Weixin Chen, 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
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.
📄 MJ-VIDEO: Fine-Grained Benchmarking and Rewarding Video Preferences in Video Generation
Under review '25 --
Haibo Tong, Zhaoyang Wang, Zhaorun Chen ... Zhongkai Xue ... Huaxiu Yao, et al.
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, 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.
