Introduction

👋 I am a first-year PhD student at the Institute of Automation, Chinese Academy of Sciences (CASIA), supervised by Prof. Liang Wang. Previously, I obtained my bachelor's degree from The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), where I worked with Prof. Tianshu Yu and Xinjian Zhao, and interned at ByteDance.

🤖 I am currently working on building agent systems that efficiently structure, retrieve, and utilize knowledge. Always happy to discuss research ideas or collaborations — feel free to reach out!

Education

Selected Publications Full

RoboMemory: A Brain-Inspired Multi-Memory Framework for Interactive Environmental Learning in Physical Embodied Systems

Under Review '26 — Mingcong Lei, Honghao Cai, Yuyuan Yang, Yimou Wu, Jinke Ren, Zezhou Cui, Liangchen Tan, Junkun Hong, Gehan Hu, Shuangyu Zhu, Zhongkai Xue ... Yatong Han et al. Mingcong Lei, Honghao Cai, Yuyuan Yang, Yimou Wu, Jinke Ren, Zezhou Cui, Liangchen Tan, Junkun Hong, Gehan Hu, Shuangyu Zhu, Shaohan Jiang, Ge Wang, Junyuan Tan, Zhenglin Wan, Zhongkai Xue, Li Zheng, Zhen Li, Shuguang Cui, Yiming Zhao, Yatong Han. Full

Abstract: We present RoboMemory, a brain-inspired framework that integrates spatial, temporal, episodic, and semantic memory within a parallelized architecture for embodied agents. Equipped with a dynamic spatial knowledge graph and a closed-loop planner with a critic module, RoboMemory enables efficient long-horizon planning and interactive environmental learning.

[arxiv] [code]

When Vision Meets Graphs: A Survey on Graph Reasoning and Learning

IJCAI '26 — Xinjian Zhao, Wei Pang, Zhixuan Yu, Xiangru Jian, Xiaozhuang Song, Yaoyao Xu, Zhongkai Xue, Dingshuo Chen, Shu Wu, Philip Torr, Tianshu Yu.

Abstract: We survey recent advances at the intersection of vision and graph learning, highlighting how visual representations can complement symbolic graph reasoning. Based on existing work into three major threads (vision for graph reasoning, vision for graph learning, and scientific graphs), we delve into a unified taxonomy and outline future directions toward more effective graph understanding.

[techrxiv]

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.

[arxiv] [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.

[arxiv] [code] [site]

Political-LLM: Large Language Models in Political Science

Arxiv '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.

Research Experience

Industry Experience

Miscellaneous