李文通

个人信息Personal Information

硕士生导师

性别:男

毕业院校:浙江大学

学历:博士研究生毕业

学位:工学博士学位

所在单位:人工智能学院

办公地点:将军路校区-西区1号楼-12层1205室

电子邮箱:

扫描关注

个人简介Personal Profile

李文通,南京航空航天大学人工智能学院,副教授,多媒体与视觉感知课题组(MVP Lab)(国家青A获得者-秦杰教授领衔)。


2024年博士毕业于浙江大学计算机科学与技术学院,主要从事计算机视觉、具身智能、多模态大模型等方向的相关研究。目前已在国际权威期刊和会议上发表论文四十余篇,包括TPAMI、IJCV、CVPR、 ICCV、ECCV、NeurIPS、ICLR、ICML等, Google Scholar引用2600余次, Github开源仓库累计收获Star 4000余次,担任CVPR、ICLR、NeurIPS、AAAI领域主席。主持国家自然科学基金青年项目(C类)、中央高校基本科研业务费、核心骨干参与科技部科技创新2030-“新一代人工智能”重大研究项目。曾获浙江大学优秀博士学位论文、指导大二本科生大创获省级优秀结题。


欢迎访问个人主页了解相关研究工作:https://cslwt.github.io/ 。


长期招收博士生、硕士生、科研实习生。

希望你:

1)有强烈的自驱力;

2)具有较强的自学能力、编程能力和英语水平;

3)上进、有正能量、有责任心。


欢迎感兴趣、有志科研的同学,邮件联系我并附上个人简历。


主要发表论文:


  • Wentong Li, Yuqian Yuan, Jian Liu, Dongqi Tang, Song Wang, Jie Qin, Jianke Zhu, Lei Zhang.  ``TokenPacker: Efficient Visual Projector for MultiModal LLM.''  In International Journal of Computer Vision (IJCV), 2025. (Citation: 200+)

  • Wentong Li, Wenyu Liu, Jianke Zhu, Miaomiao Cui, Risheng Yu, Xiansheng Hua, Lei Zhang. ``Box2Mask: Box-supervised Instance Segmentation via Level-set Evolution.'' IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2024.

  • Wentong Li, Yuqian Yuan, Song Wang, Wenyu Liu, Dongqi Tang, Jian Liu, Jianke Zhu, Lei Zhang. ``Label-efficient Segmentation via Affinity Propagation.'' Neural Information Processing Systems (NeurIPS), 2023.

  • Wentong Li, Yuqian Yuan, Song Wang, Jianke Zhu, Jianshu Li, Jian Liu, Lei Zhang. ``Point2Mask: Point-supervised Panoptic Segmentation via Optimal Transport.'' In Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2023.

  • Wentong Li, Wenyu Liu, Jianke Zhu, Miaomiao Cui, Xian-Sheng Hua, Lei Zhang. ``Box-supervised Instance Segmentation with Level Set Evolution.'' In Proceedings of the European Conference on Computer Vision (ECCV), 2022.

  • Wentong Li, Yijie Chen, Kaixuan Hu, Jianke Zhu. ``Oriented RepPoints for Aerial Object Detection.'' In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022. (Citation: 700+)

  • Yuqian Yuan*, Wentong Li*, Jian Liu, Dongqi Tang, Xinjie Luo, Chi Qin, Lei Zhang, Jianke Zhu.``Osprey: Pixel Understanding with Visual Instruction Tuning.'' In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024. (*Equal Contribution, Citation:200+)

  • Hanxun Yu*, Wentong Li*, Song Wang, Junbo Chen, Jianke Zhu.  ``Inst3D-LMM: Instance-Aware 3D Scene Understanding with Multi-modal Instruction Tuning.'' In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025. (*Equal Contribution, Highlight, 2.9%)

  • Hanxun Yu*, Wentong Li*, Xuan Qu, Song Wang, Junbo Chen, Jianke Zhu. ``VisionTrim: Unified Vision Token Compression for Training-Free MLLM Acceleration.'' In International Conference on Learning Representations (ICLR), 2026. (*Equal Contribution.)

  • Zihao Xin*, Wentong Li*, Yixuan Jiang, Bin Wang, Runmin Cong, Jie Qin, Sheng-Jun Huang. ``DecoVLN: Decoupling Observation, Reasoning, and Correction for Vision-and-Language Navigation.'' In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2026. (*Equal Contribution.)

  • Zihao Xin,  Wentong Li#, Yixuan Jiang, Bin Wang, Piji Li, Jianke Zhu, Jie Qin, Sheng-Jun Huang. ``Instruction Decomposition and Action Alignment for Vision-and-Language Navigation.'' In International Conference on Machine Learning (ICML), 2026. (#Corresponding Author.)

  • Zihao Xin, Wentong Li#, Yixuan Jiang, Ziyuan Huang, Bin Wang, Piji Li, Jianke Zhu, Jie Qin, Sheng-Jun Huang. ``AgentVLN: Towards Agentic Vision-and-Language Navigation.'' In European Conference on Computer Vision(ECCV), 2026. (#Corresponding Author.)

  • Yue Feng, Jingjing Li, Qijia Lu, Wei Ji, Jingrou Zhang, Fei Shen, Xiao Li, Yizhen Jia, Qiang Chen, Limin Wang, Wentong Li#, Jie Qin. Explainable Forensics of Manipulated Segments in Untrimmed Long Videos. In International Conference on Machine Learning (ICML), 2026. (#Corresponding Author.)

  • Yue Feng, Jinwei Hu, Qijia Lu, Jiawei Niu, Li Tan, Shuo Yuan, Ziyi Yan, Yizhen Jia, Qingzhi He, Shiping Ge, Ethan Q Chen, Wentong Li#, Limin Wang, Jie Qin. MUVR: A Multi-Modal Untrimmed Video Retrieval Benchmark with Multi-Level Visual Correspondence. Neural Information Processing Systems (NeurIPS), 2026. (#Corresponding Author.)


agent-vln.gif



  • 教育经历Education Background
  • 工作经历Work Experience
  • 研究方向Research Focus
  • 社会兼职Social Affiliations
  • 多模态场景理解:细粒度图像/视频理解与分析

  • 具身智能:基于实体机器人的长程感知、交互、推理、导航

  • 多模态大模型:多模态大模型及其轻量化+下游基础视觉任务

    2025.9 至今
    • IEEE Member