Hi, I am Mingyu Zhang (张明宇).

Welcome to my homepage! I'm currently an undergraduate student in the School of Software, Shandong University, under the supervision of Prof. Liqiang Nie and Dr. Zixu Li, working closely with Dr. Zhiheng Fu.

My research interests include World Model, Agent and Information Retrieval.

欢迎来到我的主页！我目前是山东大学软件学院的本科生，师从 Prof. Liqiang Nie，并由 Dr. Zixu Li 共同指导，同时与 Dr. Zhiheng Fu 保持紧密合作。

我的研究兴趣包括世界模型、智能体与信息检索。

I am a member of the Intelligent Media Research Center (iLearn). I believe open-source research makes multimodal learning more reproducible and collaborative. My major projects and our lab projects are open-source; please visit iLearn Lab and feel free to share your valuable feedback.

作为开放科学的坚定拥趸，我致力于将研究成果开源，以促进社区的交流与发展。我隶属于智能媒体研究中心 (iLearn)，并相信开源研究能够提升多模态学习的可复现性与协作性。我主要参与的项目与实验室项目持续开源，欢迎访问 iLearn Lab 并提出宝贵意见。

💻 Open Science 💻 开放科学

Projects 项目主页

Below are representative project pages and repositories from my recent works. Feedback, issues, and pull requests are warmly welcome. 以下是我近期工作的代表性项目页面和代码仓库。欢迎提出反馈、问题和 Pull Request。

HINT

ICASSP 2026ICASSP 2026

Paper Project Code

ConeSep

CVPR 2026CVPR 2026

Paper Project Code

🔥 Updates 🔥 最新动态

News 新闻动态

2026.09.20

🎉🎉 Thrilled to share that our team won the 2nd Place 🥈 in the SceneFun3D Benchmark Challenge at the Open-World 3D Scene Understanding and Representations (OpenSUN3D) Workshop @ ECCV 2026! Congratulations to all members!🎉🎉 我们团队在 ECCV 2026 Open-World 3D Scene Understanding and Representations (OpenSUN3D) Workshop 的 SceneFun3D Benchmark Challenge 中获得亚军🥈！祝贺所有成员！

2026.03.03

🎉🎉 One paper was accepted by CVPR 2026! Congratulations to all co-authors!🎉🎉 一篇论文被 CVPR 2026 接收！祝贺所有合作者！

2026.01.18

🎉🎉 One paper has been accepted to ICASSP 2026! Congratulations to our co-authors!🎉🎉 一篇论文被 ICASSP 2026 接收！祝贺所有合作者！

2025.10.18

🏆 As the core member, our team wins the Grand Prize in the CICAS Smart Power Scenario Competition. Congratulations to all team members!🏆 作为核心成员，我们的团队在 CICAS 智慧电力场景竞赛中获得特等奖。祝贺所有团队成员！

📝 Publications📝 论文

⚓️ denotes project leader; 📧 denotes corresponding author. ⚓️ 表示项目负责人；📧 表示通讯作者。

CVPR 2026

ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrieval

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2026)

Zixu Li, Yupeng Hu📧, Zhiwei Chen, Mingyu Zhang, Zhiheng Fu, Liqiang Nie

Multimodal Understanding Robustness

[Paper] [Website] [Code]

ICASSP 2026

HINT: Composed Image Retrieval with Dual-Path Compositional Contextualized Network

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2026)

Mingyu Zhang, Zixu Li⚓️, Zhiwei Chen, Zhiheng Fu, Xiaowei Zhu, Jiajia Nie, Yinwei Wei, Yupeng Hu📧

First Author Multimodal Understanding

[Paper] [Website] [Code]

🏆 Honors and Awards🏆 荣誉与奖励

2025.10, Grand Prize in the CICAS Smart Power Scenario Competition.2025.10，CICAS 智慧电力场景竞赛特等奖。

🥈 Competitions🏅 竞赛

2nd place 🥈, ECCV OpenSUN3D Workshop, SceneFun3D Benchmark Challenge, 2026. Link亚军 🥈，ECCV OpenSUN3D Workshop，SceneFun3D Benchmark Challenge，2026.链接

📖 Educations📖 教育经历

2023.09 - Present, Undergrad in the School of Software, Shandong University.2023.09 - 至今，山东大学软件学院本科生。