Hi, I’m Yifan Li (李一帆), a 2-nd year Ph.D. student (2023-) at the Department of Computer Science and Engineering (CSE) of Michigan State University (MSU), supervised by Prof. Yu Kong. Before that, I obtained my Master’s degree (2020-2023) at the VIPL group, Institue of Computing Technology, Chinese Academy of Sciences (ICT, CAS) supervised by Prof. Hu Han, and I also collaborate closely with Prof. Shiguang Shan. I obtained my Bachelor’s degree (2016-2020) at Northeastern University supervised by Prof. Long Cheng.
My research interest includes computer vision (CV) and deep learning (DL). More specifically, my goal is to exploit the knowledge from imperfect data (unlabeled or mislabeled data) and improve the model’s generalization and robustness. My current research interest is Embodied AI so that humans can work with machines collaboratively.
I am so excited to witness and participate in the revolution of artificial intelligence. I am also open for collaboration to create better jobs, so if you are interested please reach out and do something cool.
🔥 News
- 2024.09： 🎉🎉🎉 One co-authored paper has been accepted by EMNLP2024! Thanks to all of my collaborators!
- 2024.07： 🎉🎉🎉 One first author paper has been accepted by ECCV2024! Thanks to all of my co-authors, you are awesome !!!
- 2024.05: 🎉🎉🎉 Starting my internship at Bosch!
- 2023.08: 🎉 One paper is accepted by BMVC!
- 2023.08: 🎉 Starting my Ph. D. journey at MSU!
- 2023.06: 🎉 One paper is accepted by CVPR 2023.
📝 Publications
👁️ Computer Vision
Facial Affective Behavior Analysis with Instruction Tuning
Yifan Li, Anh Dao, Wentao Bao, Zhen Tan, Tianlong Chen, Huan Liu, Yu Kong
ReCoT: Regularized Co-Training for Facial Action Unit Recognition with Noisy Labels
Yifan Li, Hu Han, Shiguang Shan, Zhilong Ji, Jinfeng Bai, Xilin Chen
DISC: Learning from Noisy Labels via Dynamic Instance-Specific Selection and Correction
Yifan Li, Hu Han, Shiguang Shan, Xilin Chen
Affective Behaviour Analysis Using Pretrained Model with Facial Prior
Yifan Li, Haomiao Sun, Zhaori Liu, Hu Han, Shiguang Shan
📖 Natural Language Processing
EMNLP 2024“Glue pizza and eat rocks” - Exploiting Vulnerabilities in Retrieval-Augmented Generative Models, Zhen Tan, Chengshuang Zhao, RahaMoraffah, Yifan Li, Song Wang, Jundong Li, Tianlong Chen, Huan Liu
📚 Other Research Papers
TII 2020An Indoor Localization Algorithm Based on Modified Joint Probabilistic Data Association for Wireless Sensor Network, Long Cheng, Yifan Li, Mingkun Xue, Yan Wang
🎖 Honors and Awards
- 2023.05: Zhiqiang Scholarship of ICT.
- 2023.05, 2022.05: Merit Student of Chinese Academy of Sciences.
- 2022.07: Our team (ICT-VIPL) reached the Runner-up in Mult-task learning track in Affective Behavior Analysis in-the-wild (ABAW4) competition.
- 2019.03: Meritorous Award, Mathematical Contest in Modeling (MCM).
- 2019.01: First Prize, Asia-Pacific Mathematical Contest in Modeling (APMCM).
- 2018.08: National Second Prize, 13-th NXP Cup College Students Intelligent Car Race.
- 2018.08: National Third Prize, iCAN International Innovation and Entrepreneurship Competition.
💬 Academic Services
Conference Reviewer
- IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR): 2023, 2024
- Conference on Neural Information Processing Systems (NeurlPS): 2021, 2023
- Association for the Advancement of Artificial Intelligence (AAAI): 2025
- British Machine Vision Conference (BMVC): 2021
- International Conference on Automatic Face and Gesture Recognition (FG): 2023
Journal Reviewer
- IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
- IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
- IEEE Transactions on Multimedia (TMM)
- IEEE Transactions on Biometrics, Behavior, and Identity Science (TBIOM)
- ACM Transactions on Multimedia Computing Communications and Applications (TOMM)
- Elsevier: Pattern Recognition (PR)
💻 Work Experience
Research Intern of Bosch Center for Artifical Intelligence (BCAI)
- 2024.5 - 2024.8: Develop an efficient fine-tuning method for vision foundation models, which can be utilized on dense prediction, detection and MLLM, etc. Happy to work with Wenbin He, Xin Li and Tianqin Li.
📖 Educations
- 2023.08 - now: Ph.D. Student of Computer Engineering, Michigan State University, United States.
- 2020.09 - 2023.06: Master of Computer Application, Institute of Computing Technology, Chinese Academy of Sciences, China.
- 2016.09 - 2020.06: Bachelor of Communication Engineering, Northeastern University, China.