About me

I am currently a junior undergraduate student at the College of Computer Science and Technology, Jilin University, advised by Professor Hongxia Xie.

Research Interests

My research interests lie in multimodal reasoning and embodied intelligence, with a particular focus on vision-language models and multimodal large language models. I am interested in building intelligent agents that can integrate perception, reasoning, and action in complex environments. My recent work explores topics including theory-of-mind reasoning, emotion understanding, multimodal perception, and decision-making for embodied agents, with the goal of improving the reasoning ability, interpretability, and real-world adaptability of AI systems.

Research Assistant, Affective Vision and Computing Lab (AVCLab), Jilin University, 2025–Present

Emotional Companion Embodied Agent: An Affective Robotic System for Real-World Interaction
Undergraduate Research Training Program, 2025 – Present
Research on Automatic Assisted Driving Based on Large Language Models
National Innovation and Entrepreneurship Training Program for College Students, 2024 – 2026

MindPower: Enabling Theory-of-Mind Reasoning in VLM-based Embodied Agents.
Ruoxuan Zhang, Qiyun Zheng, Zhiyu Zhou, Ziqi Liao, Siyu Wu, Jian-Yu Jiang-Lin, Bin Wen, Hongxia Xie, Jianlong Fu, Wen-Huang Cheng.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2026).[PDF] [论文中文解读]

First-Class Scholarship, Jilin University
Outstanding Student, College of Computer Science and Technology, Jilin University

First Prize, China Collegiate Computer Design Competition（中国计算机博弈大赛）, 2025
Third Prize, National Finals of the Programming Skills Track, RAICOM Robotics Developer Competition（睿抗机器人开发者大赛全国总决赛编程技能竞赛项目）, 2025
First Prize, Jilin Regional Programming Skills Track, RAICOM Robotics Developer Competition（睿抗机器人开发者大赛吉林赛区编程技能竞赛项目）, 2025