Hi, I am Zhiwei Chen (陈智伟).
Welcome to my homepage! I am currently a Ph.D. student in the School of Software, Shandong University, under the supervision of Prof. Liqiang Nie and Prof. Yupeng Hu, working closely with Dr. Zixu Li. My research interests mainly focus on Multimodal Large Language Models, robust representation learning, and trustworthy AI..
My research follows the trajectory of from multimodal understanding to evidence-driven large model evaluation. On the model side, I study fine-grained visual-textual semantic fusion, composed image/video understanding, attribute-aware representation learning, and robust intent disentanglement, with representative works including COMBINER, STABLE, ConeSep, Air-Know, INTENT, HABIT, HUD, OFFSET, and ENCODER. On the evaluation side, I have contributed to long-form video and egocentric vision reasoning systems, including the CVPRW challenge technical reports R3, TempRet, EgoAdapt, OmniEgo-R2, and EgoAction.
Beyond publications, I actively participate in open-source research and industry-scale systems. As a core member of the Huawei collaboration project on general-purpose vector search, I contributed to the QSGNGT graph-indexing algorithm and its optimization for high-throughput vector search. The project has continuously ranked first worldwide on ANN-Benchmarks since 2023 and supports Huawei Cloud GaussDB / CSS VectorDB. I have been recognized with the Huawei Outstanding Technical Collaboration Award, the BYD Scholarship, and the Grand Prize in the CICAS Smart Power Scenario Competition.
欢迎来到我的主页！我目前是山东大学软件学院博士研究生，师从 Prof. Liqiang Nie 与 Prof. Yupeng Hu，并与 Dr. Zixu Li 保持紧密合作。我的研究兴趣主要聚焦于多模态理解、鲁棒跨模态学习、可信评测与近似近邻检索。
我的研究围绕“从多模态理解到证据驱动的大模型评测”这一主线展开：一方面，我关注细粒度视觉-语言语义融合、组合式图文/视频理解、属性感知表征学习与复杂场景意图解耦，代表工作包括 COMBINER、STABLE、ConeSep、Air-Know、INTENT、HABIT、HUD、OFFSET 与 ENCODER；另一方面，我参与长视频理解、第一视角视觉推理与多模态评测系统构建，相关技术报告包括 R3、TempRet、EgoAdapt、OmniEgo-R2 与 EgoAction。
除学术论文外，我也积极参与开源研究与产业级系统研发。作为华为通用向量检索合作项目的核心成员，我参与 QSGNGT 图索引算法及其高吞吐向量检索优化；该项目自2023年至今蝉联 ANN-Benchmarks 官方测评世界第一，并支撑华为云 GaussDB / CSS VectorDB 的向量检索能力。相关工作曾获华为优秀技术合作成果奖，我也曾获得 BYD Scholarship 与 CICAS 智能电力场景竞赛特等奖。
I am affiliated with the Intelligent Media Research Center (iLearn). I believe open-source research makes multimodal learning more reproducible and collaborative. Our lab's projects and papers are open-source; please visit iLearn Lab and feel free to share your valuable feedback.
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。实验室论文代码与相关项目持续开源，欢迎访问 iLearn Lab 并提出宝贵意见。
Below are representative project pages and repositories from our recent works. Feedback, issues, and pull requests are warmly welcome.
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
📝 Selected Publications
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
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
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]
Zhiheng Fu, Yupeng Hu✉, Qianyun Yang, Shiqi Zhang, Zhiwei Chen, Zixu Li†
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
📝 More Publications
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
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
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
📝 Challenge Technical Report
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 a core contributor, I participated in the Huawei collaboration project on general-purpose vector search and contributed to the QSGNGT graph-indexing algorithm. In the official ANN-Benchmarks evaluation, QSGNGT outperformed competing algorithms from leading technology companies including Google, Microsoft, Meta, Yahoo, JD.com, Alibaba, and 01.AI, and has continuously ranked first worldwide since 2023. The system supports Huawei Cloud GaussDB / CSS VectorDB for large-scale vector search.
作为核心成员，我参与华为通用向量检索合作项目，并参与 QSGNGT 图索引算法及其优化。该算法在 ANN-Benchmarks 官方评测中超过 Google、Microsoft、Meta、Yahoo、京东、阿里巴巴、零一万物等代表性参与单位/基线算法，自2023年至今蝉联世界第一，并支撑华为云 GaussDB / CSS VectorDB 的大规模向量检索能力。
Google 
Microsoft 
Meta 
Yahoo 
JD.com 
Alibaba 🔖 Patent
- (已授权)一种基于类社交先验的多模态语义表征方法及系统 - 公开号: CN118194109A - [详情]
- 基于特征相似性和属性一致性协同约束的近似近邻混合检索的用户推荐方法及系统 - 公开号: CN117453991A - [详情]
🏆 Competition
- 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]
🎖 Honors and Awards
- 2025.11: BYD Scholarship
- 2025.10: Grand Prize in the CICAS Smart Power Scenario Competition
- 2024.09: Huawei Outstanding Technical Collaboration Award (Top 10 globally per year)
- 2024.06: Recipient of the Outstanding Graduate Award, Shandong University
📖 Educations
- 2024.09 - now, integrated Master-Ph.D. program in the School of Software, Shandong University.
- 2020.09 - 2024.08, Bachelor in the School of Software, Shandong University.
📃 Services
- Conference PC Member: AAAI, CIKM
- Journal Reviewer: Information Sciences