基本信息

万方，中国科学院大学计算机科学与技术学院助理教授，博士生导师，博士后创新人才支持计划获得者、中国科学院百篇优秀博士论文。研究方向为视觉目标感知、多模态表征与理解、具身智能。发表包括IEEE CVPR, ICCV, NeurIPS, AAAI、ECCV等国际会议与TPAMI, TNNLS, TIP, TCSVT、PR、TGRS等国际期刊40余篇。获得2023年度国家技术发明奖二等奖1项（排名第五）、中国电子学会自然科学奖一等奖1项（排名第四），获得2023年度小米青年学者，阿里达摩院博士后合作导师，主持中科院重点部署项目1项，国家自然科学基金青年和面上基金等国家级项目3项。


电子邮件： wanfang@ucas.ac.cn

谷歌学术主页：https://scholar.google.com/citations?user=0IKavloAAAAJ

实验室主页： 机器学习与感知实验室（http://lamp.ucas.ac.cn/）

研究领域

视觉目标感知；多模态表征与理解；具身智能

招生信息

每年招收博士生1名，硕士生1-2名，欢迎感兴趣的学生联系报考！

教育和工作经历

2021.12--至今    中国科学院大学 长聘教轨助理教授

2019.07--2021.12    中国科学院大学   博士后

2019.03--2019.06    微软亚洲研究院   博士实习生


2016.09--2019.06   中国科学院大学   博士研究生

2013.09--2016.06   中国科学院大学   硕士研究生

2009.09--2013.06   武汉大学  本科

出版信息

Selected Publications

  1. Di Zhu, Ziheng Yan, Fang Wan. ActionUNet: Improving Robustness of VLA Models with Efficient Multi-scale Fine-tuning. Advances in Neural Information Processing Systems (NeurIPS), 2026. To appear.
  2. Yuzhong Zhao, Yue Liu, Junpeng Liu, Jingye Chen, Xun Wu, Yaru Hao, Tengchao Lv, Shaohan Huang, Lei Cui, Qixiang Ye, Fang Wan, Furu Wei. Geometric-Mean Policy Optimization. International Conference on Learning Representations (ICLR), 2026.
  3. Da Peng, Xuesong Yang, Zonghao Guo, Yichen Zhang, Chi Chen, Yidan Zhang, Yuan Yao, Fang Wan*, Wei Ke*, Maosong Sun. FlexiVideo: Variation-Aware Temporal Dynamics Modeling for Efficient Video Understanding. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026.
  4. Ziheng Yan, Xinyan Liu, Guorong Li, Weigang Zhang, Fang Wan, Qingming Huang. Compactness Driven Co-learning for Crowd Counting and Localization. Pattern Recognition, 179: 113638, 2026.
  5. Feng Liu, Shiwei Zhang, Xiaofeng Wang, Yujie Wei, Haonan Qiu, Yuzhong Zhao, Yingya Zhang, Qixiang Ye, Fang Wan*. Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025. Highlight.
  6. Yuzhong Zhao, Feng Liu, Yue Liu, Mingxiang Liao, Chen Gong, Qixiang Ye, Fang Wan. DynRefer: Delving into Region-level Multimodal Tasks via Dynamic Resolution. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.
  7. Mingxiang Liao, Fang Wan, Zonghao Guo, Qixiang Ye. Hierarchical AttentionShift for Pointly Supervised Instance Segmentation. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 36(8): 15528–15541, 2025.
  8. Zonghao Guo, Fang Wan, Mingxiang Liao, Yidan Zhang, Qixiang Ye. Discriminatively Matched Part Tokens for Pointly Supervised Instance Segmentation. International Journal of Computer Vision (IJCV), 133(11): 7855–7872, 2025.
  9. Mingxiang Liao, Hannan Lu, Xinyu Zhang, Fang Wan, Tianyu Wang, Yuzhong Zhao, Wangmeng Zuo, Qixiang Ye, Jingdong Wang. Evaluation of Text-to-Video Generation Models: A Dynamics Perspective. Advances in Neural Information Processing Systems (NeurIPS), 2024.
  10. Yuzhong Zhao, Yue Liu, Zonghao Guo, Weijia Wu, Chen Gong, Qixiang Ye, Fang Wan*. ControlCap: Controllable Region-level Captioning. European Conference on Computer Vision (ECCV), 2024.
  11. Feng Liu, Tengteng Huang, Qianjing Zhang, Haotian Yao, Chi Zhang, Fang Wan, Qixiang Ye, Yanzhao Zhou. Ray Denoising: Depth-Aware Hard Negative Sampling for Multi-view 3D Object Detection. European Conference on Computer Vision (ECCV), 2024.
  12. Fang Wan, Qixiang Ye, Tianning Yuan, Songcen Xu, Jianzhuang Liu, Xiangyang Ji, Qingming Huang. Multiple Instance Differentiation Learning for Active Object Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 45(10): 12133–12147, 2023.
  13. Yuzhong Zhao, Qixiang Ye, Weijia Wu, Chunhua Shen, Fang Wan. Generative Prompt Model for Weakly Supervised Object Localization. IEEE/CVF International Conference on Computer Vision (ICCV), 2023.
  14. Feng Liu, Xiaosong Zhang, Zhiliang Peng, Zonghao Guo, Fang Wan, Xiangyang Ji, Qixiang Ye. Integrally Migrating Pre-trained Transformer Encoder-decoders for Visual Object Detection. IEEE/CVF International Conference on Computer Vision (ICCV), 2023.
  15. Mingxiang Liao, Zonghao Guo, Yuze Wang, Peng Yuan, Bailan Feng, Fang Wan. AttentionShift: Iteratively Estimated Part-Based Attention Map for Pointly Supervised Instance Segmentation. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
  16. Mingxiang Liao, Fang Wan*, Yuan Yao, Zhenjun Han, Jialing Zou, Yuze Wang, Bailan Feng, Peng Yuan, Qixiang Ye. End-to-End Weakly Supervised Object Detection with Sparse Proposal Evolution. European Conference on Computer Vision (ECCV), 2022.
  17. Xiaosong Zhang, Fang Wan, Chang Liu, Xiangyang Ji, Qixiang Ye. Learning to Match Anchors for Visual Object Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 44(6): 3096–3109, 2022.
  18. Boyu Yang, Fang Wan*, Chang Liu, Bohao Li, Xiangyang Ji, Qixiang Ye. Part-Based Semantic Transform for Few-Shot Semantic Segmentation. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 33(12): 7141–7152, 2022.
  19. Qixiang Ye, Fang Wan*, Chang Liu, Qingming Huang, Xiangyang Ji. Continuation Multiple Instance Learning for Weakly and Fully Supervised Object Detection. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 33(10): 5452–5466, 2022.
  20. Wei Gao, Fang Wan*, Xingjia Pan, Zhiliang Peng, Qi Tian, Zhenjun Han, Bolei Zhou, Qixiang Ye*. TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization. IEEE/CVF International Conference on Computer Vision (ICCV), 2021.
  21. Tianning Yuan, Fang Wan*, Mengying Fu, Jianzhuang Liu, Songcen Xu, Xiangyang Ji, Qixiang Ye*. Multiple Instance Active Learning for Object Detection. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
  22. Mengying Fu, Tianning Yuan, Fang Wan*, Songcen Xu, Qixiang Ye*. Agreement-Discrepancy-Selection: Active Learning with Progressive Distribution Alignment. AAAI Conference on Artificial Intelligence (AAAI), 2021.
  23. Xiaosong Zhang, Fang Wan, Chang Liu, Rongrong Ji, Qixiang Ye. FreeAnchor: Learning to Match Anchors for Visual Object Detection. Advances in Neural Information Processing Systems (NeurIPS), 2019.
  24. Fang Wan, Chang Liu, Wei Ke, Xiangyang Ji, Jianbin Jiao, Qixiang Ye. C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019. Oral.
  25. Fang Wan, Pengxu Wei, Jianbin Jiao, Zhenjun Han, Qixiang Ye. Min-Entropy Latent Model for Weakly Supervised Object Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 41(10): 2395–2409, 2019.
  26. Haolan Xue, Chang Liu, Fang Wan*, Jianbin Jiao, Qixiang Ye*. DANet: Divergent Activation for Weakly Supervised Object Localization. IEEE/CVF International Conference on Computer Vision (ICCV), 2019.
  27. Caijing Miao, Lingxi Xie, Fang Wan, Chi Su, Hongye Liu, Jianbin Jiao, Qixiang Ye. SIXray: A Large-scale Security Inspection X-ray Benchmark for Prohibited Item Discovery in Overlapping Images. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019.

* Corresponding author.

培养指导

现指导学生

张宇 硕士研究生 方向：开放域视觉感知

严子恒 博士研究生 方向：具身智能

朱迪 硕士研究生 方向：具身智能

杨雪松 博士研究生 方向：多模态理解


已指导学生

刘峰 (2025毕业) 博士 毕业去向： 字节跳动

马文宇 (2026毕业) 硕士 毕业去向： 中国科学院大学

赵毓钟 (2026毕业) 博士 毕业去向： 微软亚洲研究院

廖明祥 (2025毕业，合作指导) 博士 毕业去向： 字节跳动

郭宗昊 (2024毕业，合作指导) 博士 毕业去向： QY实验室（国家实验室）