龙思凡，大连理工大学计算机科学与技术学院助理教授。2020年本科毕业于吉林大学软件学院，2025年博士毕业于吉林大学计算机科学与技术学院，师从王生生教授和王井东博士（加拿大工程院院士，Fellow of CAE & IEEE & IAPR）。主要研究方向为深度学习、计算机视觉、多模态视觉语言大模型等，近两年在IJCV、CVPR、ICCV、NeurIPS、ACM MM等国际期刊和会议上发表论文十余篇。受邀为IEEE TNNLS、IEEE TCSVT、IEEE TMM、NeurIPS、Pattern Recognition、Knowledge-Based Systems、Expert Systems With Applications等国际顶级期刊和会议的审稿人。

拟招收2026年硕士研究生及对计算机视觉、多模态视觉语言大模型等领域感兴趣的本科生，欢迎同学们与我联系：longsf@dlut.edu.cn。

主要论文成果:

[1] Sifan Long, Zhen Zhao, Junkun Yuan, Zichang Tan, Jiangjiang Liu, Jingyuan Feng, Shengsheng Wang, Jingdong Wang. Mutual Prompt Leaning for Vision Language Models[J]. International Journal of Computer Vision, 2024. (CCF-A 类推荐期刊，中科院 1 区)

[2] Sifan Long, Zhen Zhao, Jimin Pi, Shengsheng Wang, Jingdong Wang. Beyond attentive tokens: Incorporating token importance and diversity for efficient vision transformers[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp.10334-10343. (CCF-A 类推荐会议)

[3] Sifan Long, Zhen Zhao, Junkun Yuan, Zichang Tan, Jiangjiang Liu, Luping Zhou, Shengsheng Wang, Jingdong Wang. Task-Oriented Multi-Modal Mutual Learning for Vision-Language Models[C]. Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023, pp.21959-21969. (CCF-A 类推荐会议)

[4] Zhen Zhao*, Sifan Long*, Jimin Pi, Jingdong Wang, Luping Zhou. Instance Specific and Model-Adaptive Supervision for Semi-Supervised Semantic Segmentation[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp.23705-23714. (CCF-A 类推荐会议)

[5] Zhen Zhao, Lihe Yang, Sifan Long, Jimin Pi, Luping Zhou, Jingdong Wang. Augmentation Matters: A Simple-yet-Effective Approach to Semi-supervised Semantic Segmentation[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp.11350-11359. (CCF-A 类推荐会议)

指导学生论文成果:

[1] Siyu He, Shengsheng Wang, Sifan Long. A Slim Prompt-Averaged Consistency prompt learning for vision–language model[J]. Knowledge-Based Systems, 2024. (中科院 1 区)

[1] Yongguang Li, Sifan Long, Shengsheng Wang, Xin Zhao, Yiyang Li. Prompt-induced prototype alignment for few-shot unsupervised domain adaptation[J]. Expert Systems With Applications, 2024. (中科院 1 区)