Shuo He

E-mail: shuohe123@gmail.com
[GitHub] [Google Scholar]


I am currently a Research Fellow at Nanyang Technological University (NTU), Singapore. I earned my PhD degree from University of Electronic Science and Technology of China (UESTC) in 2024.

Research Interests

• Weakly-supervised machine learning: During my master’s and PhD studies, I focused on developing efficient machine learning algorithms under limited supervision, particularly in areas such as noisy-label learning, partial-label learning, and (partial) multi-label learning.
• AI safety: Driven by the rapid advancement of large (vision-) language models demployed in real-world tasks, I have become interested in building safe and reliable foundation models, e.g., uncovering and defending against backdoor and jailbreak attacks on vision-language models.
• LLM-based agents: Currently, I am dedicated to exploring reinforcement learning techniques for training LLM-based agents deployed in real-world applications, such as [verl-agent]. My long-term goal is to develop efficient agents capable of robust decision-making in real-world tasks.

Top News

• [Jun 2025] Invited to serve as a Senior PC member for AAAI'26.
• [May 2025] Three papers were accepted by ICML'25.
• [Dec 2024] One paper was accepted by AAAI'25 as an oral presentation.
• [Jan 2024] One paper was accepted by ICLR'24 as an oral presentation.

Publications

(^* indicates equal contribution, ^† indicates corresponding author)

• Yuwei Niu^*, Shuo He^*, Qi Wei, Feng Liu, Lei Feng.
  BDetCLIP: Multimodal Prompting Contrastive Test-Time Backdoor Detection [pdf] [code]
  Proceedings of the 42th International Conference on Machine Learning (ICML'25).
• Shuo He, Zhifang Zhang, Feng Liu, Roy Ka-Wei Lee, Bo An, Lei Feng.
  A Closer Look at Backdoor Attacks on CLIP. [pdf] [code]
  Proceedings of the 42th International Conference on Machine Learning (ICML'25).
• Qi Wei, Shuo He, Jiahan Zhang, Lei Feng, Bo An.
  Representation Surgery in Model Merging with Probabilistic Modeling. [pdf] [code]
  Proceedings of the 42th International Conference on Machine Learning (ICML'25).
• Qi Wei, Shuo He, Enneng Yang, Tingcong Liu, Haobo Wang, Lei Feng, Bo An.
  Influence-Based Fair Selection for Sample-Discriminative Backdoor Attack. [pdf]
  Proceedings of the AAAI Conference on Artificial Intelligence (AAAI'25). (Oral)
• Shuo He, Chaojie Wang, Guowu Yang, Lei Feng.
  Candidate Label Set Pruning: A Data-centric Perspective for Deep Partial-label Learning. [pdf] [code]
  Proceedings of the International Conference on Learning Representations (ICLR'24). (Oral, Acceptance Rate: 1.16%)
• Shuo He, Lei Feng, Guowu Yang.
  Partial-label Learning with Mixed Closed-set and Open-set Out-of-candidate Examples. [pdf] [code]
  Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining (SIGKDD'23).
• Shuo He, Guowu Yang, Lei Feng.
  Candidate-aware selective disambiguation based on normalized entropy for instance-dependent partial-label learning. [pdf] [code]
  Proceedings of the International Conference on Computer Vision (ICCV'23).
• Senlin Shu, Shuo He, Haobo Wang, Hongxin Wei, Tao Xiang, Lei Feng.
  A generalized unbiased risk estimator for learning with augmented classes. [pdf] [code]
  Proceedings of the AAAI Conference on Artificial Intelligence (AAAI'23).
• Shuo He, Lei Feng, Fengmao Lv, Wen Li, Guowu Yang.
  Partial label learning with semantic label representations. [pdf] [code]
  Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining (SIGKDD'22).
• Shuo He, Ke Deng, Li Li, Senlin Shu, Li Liu.
  Discriminatively relabel for partial multi-label learning. [pdf] [code]
  Proceedings of the IEEE International Conference on Data Mining (ICDM'19).(Oral, Acceptance Rate: 9%).
• Lei Feng, Bo An, Shuo He.
  Collaboration based multi-label learning. [pdf]
  Proceedings of the AAAI Conference on Artificial Intelligence (AAAI'19).
• Shuo He, Lei Feng, Li Li.
  Estimating latent relative labeling importances for multi-label learning. [pdf] [code]
  Proceedings of the IEEE International Conference on Data Mining (ICDM'18).

Education

• Nanyang Technological University. Research Fellow. 2024-present
• University of Electronic Science and Technology of China. PhD. 2020-2024
• Southwest University. Master. 2017-2020
• Southwest University. Bachelor. 2013-2017

Academic Services

Conference reviewer:

• Annual Conference on Neural Information Processing Systems (NeurIPS), 2025
• International Joint Conference on Artificial Intelligence (IJCAI), 2024
• AAAI Conference on Artificial Intelligence (AAAI), 2022-2024, Senior PC member, 2026
• International Conference on Machine Learning (ICML), 2024-2025
• IEEE/CVF International Conference on Computer Vision (ICCV), 2025
• Winter Conference on Applications of Computer Vision (WACV), 2026
• International Conference on Artificial Intelligence and Statistics (AISTATS), 2025

Journal reviewer:

• IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
• IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)