Hi, I am Zixu Li (李子旭).
Welcome to my homepage! I am currently a Ph.D. student in Artificial Intelligence at Shandong University, and I am honored to be advised by Prof. Liqiang Nie and Prof. Yupeng Hu. Prior to this, I received my Bachelor's degree in Data Science and Big Data Technology from Shandong University in 2023. My research interests mainly focus on Multimodal Large Language Models, robust representation learning, and trustworthy AI.
In my research, I systematically explore the main theme of from multimodal understanding to evidence-driven large model evaluation. As first author or Project Leader, I have published more than ten papers in CCF-A international conferences and journals, including CVPR, ACL, AAAI, ACM MM, TIP, and TKDE. I have also won champion, runner-up, and third-place awards multiple times in top-tier conference challenges such as CVPR. In addition, I have long served as a PC Member for CVPR, ECCV, ICLR, NeurIPS, AAAI, ACM MM, and SIGIR, and as a reviewer for journals including IEEE TIP and IEEE TIFS.
For industrial deployment, I served as the student leader of a Huawei collaboration project on general-purpose vector retrieval, where I led the design and optimization of the QSGNGT algorithm. Since 2023, this work has continuously ranked first worldwide on the official ANN-Benchmarks leaderboard, outperforming competing algorithms from Google, Microsoft, Meta, Yahoo, JD.com, Alibaba, and other companies. The algorithm has also been successfully deployed as the retrieval core of Huawei Cloud GaussDB's hundred-billion-scale vector database. For these technical breakthroughs, I received the Huawei Outstanding Technical Collaboration Award (Top 10 globally per year, selected from over 6,000 projects) and the Huawei Outstanding Student Award (Top 30 globally per year).
欢迎来到我的主页！我目前是山东大学人工智能专业的博士生，很荣幸师从 Prof. Liqiang Nie 与 Prof. Yupeng Hu。在此之前，我于2023年在山东大学获得数据科学与大数据技术专业学士学位。我的研究兴趣主要聚焦于多模态大模型、鲁棒表征学习、可信AI。
在科研探索中，我紧密围绕“从多模态理解到证据驱动的大模型评测”这一主线展开系统性研究，以第一作者/Project Leader身份在 CVPR、ACL、AAAI、ACM MM、TIP、TKDE 等CCF A类国际会议与期刊上发表论文10余篇，并多次获得CVPR等顶会挑战赛的冠、亚、季军。此外，我长期担任 CVPR, ECCV, ICLR, NeurIPS, AAAI, ACM MM, SIGIR 等会议的PC Member和 IEEE TIP、IEEE TIFS 等期刊的审稿人。
在产业落地方面，我曾作为学生负责人参与华为通用向量检索合作项目，负责QSGNGT算法的设计与优化，该算法于2023年至今蝉联ANN-Benchmarks官方测评世界第一，算法性能超越谷歌、微软、Meta、雅虎、京东、阿里巴巴等企业的竞品算法。同时，该算法已作为检索核心成功应用于华为云GaussDB千亿级向量数据库。凭借上述技术突破，我荣获“华为优秀技术合作成果奖 (全球10项/年, 从6000余个项目中遴选产生)”与“华为优秀学生奖 (全球30人/年)”。
I firmly believe in the power of open science. Currently, all the major projects I am involved in are fully open source. Additionally, as a member of the Intelligent Media Research Center (iLearn), all of our lab’s papers and code 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。
💻 个人项目：我主要参与的项目均已全面开源，欢迎访问我们的项目主页，非常期待您的真实反馈（欢迎提出 Issue 或 PR）！
🏫 实验室组织：我隶属于智能媒体研究中心 (iLearn)，实验室的论文代码与相关项目也已悉数开源，欢迎访问 iLearn Lab 并提供宝贵意见。
I believe open-source research makes multimodal learning more reproducible and collaborative. Below are representative project pages and repositories from my recent works.
以下是我们近期代表性工作的项目主页与代码仓库，欢迎反馈、Issue 与 PR。
📝 Publications论文成果
📝 Selected Publications📝 代表性工作
COMBINER: Composed Image Retrieval Guided by Attribute-based Neighbor Relations [Paper] [Project] [Code] [Official Version]
Zixu Li, Yupeng Hu✉, Zhiwei Chen, Haokun Wen, Xuemeng Song, Liqiang Nie
TEMA: Anchor the Image, Follow the Text for Multi-Modification Composed Image Retrieval [Paper] [Project] [Code]
Zixu Li, Yupeng Hu✉, Zhiheng Fu, Zhiwei Chen, Yongqi Li, Liqiang Nie
ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrieval [Paper] [Project] [Code] [Official Version]
Zixu Li, Yupeng Hu✉, Zhiwei Chen, Mingyu Zhang, Zhiheng Fu, Liqiang Nie
Air-Know: Arbiter-Calibrated Knowledge-Internalizing Robust Network for Composed Image Retrieval [Paper] [Project] [Code] [Official Version] First-authored by undergraduate student
Zhiheng Fu, Yupeng Hu✉, Qianyun Yang, Shiqi Zhang, Zhiwei Chen, Zixu Li†
ReTrack: Evidence-Driven Dual-Stream Directional Anchor Calibration Network for Composed Video Retrieval [Paper] [Project] [Code] [Official Version]
Zixu Li, Yupeng Hu✉, Zhiwei Chen, Qinlei Huang, Guozhi Qiu, Zhiheng Fu, Meng Liu
HABIT: Chrono-Synergia Robust Progressive Learning Framework for Composed Image Retrieval [Paper] [Project] [Code] [Official Version]
Zixu Li, Yupeng Hu✉, Zhiwei Chen, Shiqi Zhang, Qinlei Huang, Zhiheng Fu, Yinwei Wei
ENCODER: Entity Mining and Modification Relation Binding for Composed Image Retrieval [Paper] [Project] [Code] [Official Version]
Zixu Li, Zhiwei Chen, Haokun Wen, Zhiheng Fu, Yupeng Hu✉, Weili Guan
FineCIR: Explicit Parsing of Fine-Grained Modification Semantics for Composed Image Retrieval [Paper] [Project] [Code]
Zixu Li, Zhiheng Fu, Yupeng Hu✉, Zhiwei Chen, Haokun Wen, Liqiang Nie
📝 More Publications📝 更多成果
STABLE: Efficient Hybrid Nearest Neighbor Search via Magnitude-Uniformity and Cardinality-Robustness [Paper]
Qianyun Yang, Zhiwei Chen, Yupeng Hu, Zixu Li, Zhiheng Fu, Liqiang Nie
REFINE: Composed Video Retrieval via Shared and Differential Semantics Enhancement [Paper] [Project] [Code] [Official Version]
Yupeng Hu, Zixu Li, Zhiwei Chen, Qinlei Huang, Zhiheng Fu, Mingzhu Xu✉, Liqiang Nie
INTENT: Invariance and Discrimination-aware Noise Mitigation for Robust Composed Image Retrieval [Paper] [Project] [Code] [Official Version]
Zhiwei Chen, Yupeng Hu✉, Zhiheng Fu, Zixu Li†, Jiale Huang, Qinlei Huang, Yinwei Wei
OFFSET: Segmentation-based Focus Shift Revision for Composed Image Retrieval [Paper] [Project] [Code] [Official Version]
Zhiwei Chen, Yupeng Hu✉, Zixu Li†, Zhiheng Fu, Xuemeng Song, Liqiang Nie
HUD: Hierarchical Uncertainty-Aware Disambiguation Network for Composed Video Retrieval [Paper] [Project] [Code] [Official Version]
Zhiwei Chen, Yupeng Hu✉, Zixu Li†, Zhiheng Fu, Haokun Wen, Weili Guan
📝 Challenge Technical Report📝 挑战赛技术报告
R3: Composed Video Retrieval via Reasoning-Guided Recalling and Re-ranking [Technical Report]
Zixu Li, Yupeng Hu✉, Zhiheng Fu, Zhiwei Chen, Weili Guan, Liqiang Nie
TempRet: Temporal Enhancement and Two-Stage Reranking for CVPR 2026 EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge [Technical Report]
Zixu Li, Yupeng Hu✉, Zhiwei Chen, Zhiheng Fu, Xiaowei Zhu, Weili Guan, Liqiang Nie
EgoAdapt: A Multi-Scene Egocentric Adaptation Method for CVPR 2026 HD-EPIC VQA Challenge [Technical Report]
Zhiwei Chen, Yupeng Hu✉, Zixu Li†, Zhiheng Fu, Guozhi Qiu, Weili Guan, Liqiang Nie
OmniEgo-R2: A Routed Reasoning Framework for the 1st Cross-Domain EgoCross Challenge at CVPR 2026 [Technical Report]
Zixu Li, Zhiwei Chen, Zhiheng Fu, Wenbo Wang, Yupeng Hu✉, Weili Guan, Liqiang Nie
EgoAction: Egocentric Action Composition with Reliability-Aware Temporal Fusion for the EPIC-KITCHENS Action Detection Challenge at CVPR 2026 [Technical Report]
Zhiheng Fu, Zixu Li†, Zhiwei Chen, Fangxu Liu, Yupeng Hu✉, Weili Guan, Liqiang Nie
🏭 Industry Project🏭 产业项目
As the student lead, I proposed QSGNGT, a general-purpose vector retrieval algorithm. In the official ANN-Benchmarks evaluation, QSGNGT outperformed competing algorithms from leading technology companies including Google, Microsoft, and Meta, and has continuously ranked first worldwide since 2023. Currently, QSGNGT serves as the core retrieval engine for Huawei Cloud GaussDB’s hundred-billion-scale vector database, supporting its global release. For this technical breakthrough, I received the Huawei Outstanding Technical Collaboration Award, selected as one of only 10 projects worldwide each year from over 6,000 projects, and the Huawei Outstanding Student Award, granted to no more than 30 students worldwide each year.
作为学生负责人，我提出了通用向量检索算法QSGNGT。该算法在ANN-Benchmarks官方评测中击败谷歌、微软、Meta等互联网头部企业的竞品算法，性能于2023年至今蝉联世界第一。目前，QSGNGT已作为核心检索引擎支撑华为云GaussDB千亿级向量数据库面向全球发布。凭借该技术突破，我荣获“华为优秀技术合作成果奖”（全球10项/年，从6000余个项目中遴选产生）与“华为优秀学生奖”（全球不超过30人/年）。
Google 
Microsoft 
Meta 
Yahoo 
JD.com 
Alibaba 🔖 Patent🔖 专利
- [Under substantive examination, second inventor] Data processing method, electronic device, readable storage medium and program product - Application No.: CN202410533951.9
- [国家发明专利实审，第二发明人] 数据处理方法、电子设备、可读存储介质和程序产品 - 申请号：CN202410533951.9
🎖 Honors and Awards🎖 荣誉奖励
- 2026.06 Shandong University Graduate Academic Star Award (Practical Application Category, 18 people in the whole university).
- 2025.10 Grand Prize (特等奖) in the CICAS Smart Power Scenario Competition.
- 2024.09 Huawei Outstanding Technical Collaboration Award (Top 10 globally per year).
- 2024.09 Huawei Outstanding Student Award (Top 30 globally per year).
- 2023.06 Outstanding Undergraduate Thesis (Ranked 1st out of 409 candidates).
- 2023.06 Outstanding Graduates of Shandong Province.
- 2023.06 Outstanding Graduates of Shandong University.
- 2026.06 山东大学研究生学术之星（实践应用类，全校18人）。
- 2025.10 CICAS 智能电力场景挑战赛特等奖。
- 2024.09 华为优秀技术合作成果奖（全球每年 Top 10）。
- 2024.09 华为优秀学生奖（全球每年 Top 30）。
- 2023.06 山东大学优秀本科毕业论文（409名候选人中排名第1）。
- 2023.06 山东省优秀毕业生。
- 2023.06 山东大学优秀毕业生。
🏆 Competition🏆 竞赛获奖
- 1st place 🏅, CVPR VidLLMs Workshop, Reasoned-Aware Composed Video Retrieval Challenge, 2026.
- 1st place 🏅, CVPR EgoVis Workshop, HD-EPIC Challenge, 2026. Link
- 1st place 🏅, CVPR EgoVis Workshop, EPIC-KITCHENS Challenge-Multi-Instance Retrieval Track, 2026. Link
- 2nd place 🥈, CVPR EgoVis Workshop, EgoCross Challenge-Source-Limited Track, 2026. Link
- 2nd place 🥈, CVPR EgoVis Workshop, EgoCross Challenge-Open-Source Track, 2026. Link
- 3rd place 🥉, CVPR EgoVis Workshop, EPIC-KITCHENS Challenge-Action Detection Track, 2026. Link
- 冠军 🏅，CVPR VidLLMs Workshop，Reasoned-Aware Composed Video Retrieval Challenge，2026。
- 冠军 🏅，CVPR EgoVis Workshop，HD-EPIC Challenge，2026。链接
- 冠军 🏅，CVPR EgoVis Workshop，EPIC-KITCHENS Challenge-Multi-Instance Retrieval Track，2026。链接
- 亚军 🥈，CVPR EgoVis Workshop，EgoCross Challenge-Source-Limited Track，2026。链接
- 亚军 🥈，CVPR EgoVis Workshop，EgoCross Challenge-Open-Source Track，2026。链接
- 季军 🥉，CVPR EgoVis Workshop，EPIC-KITCHENS Challenge-Action Detection Track，2026。链接
📖 Education📖 教育经历
- 2023.09 - now, Shandong University, Artificial Intelligence, Ph.D.
- 2019.09 - 2023.06, Shandong University, Data Science and Big Data Technology, Bachelor's Degree.
- 2023.09 - 至今，山东大学，人工智能，博士研究生。
- 2019.09 - 2023.06，山东大学，数据科学与大数据技术，学士。
📃 Services📃 学术服务
- Conference PC Member: CVPR, ECCV, ICLR, NeurIPS, AAAI, ACM MM, SIGIR, IJCAI, ICME, ICMR, ICASSP
- Journal Reviewer: IEEE TIP, IEEE TIFS, ACM ToMM
- 会议审稿人：CVPR, ECCV, ICLR, NeurIPS, AAAI, ACM MM, SIGIR, IJCAI, ICME, ICMR, ICASSP
- 期刊审稿人：IEEE TIP, IEEE TIFS, ACM ToMM