Get the latest news
Subscribe to receive updates from the School of Data Science.
Faculty
Sheng Li
Quantitative Foundation Associate Professor of Data Science
School of Data Science
Sheng Li is an artificial intelligence researcher and his long-term goal is to develop intelligent systems in open and dynamic environments. Li joined the School of Data Science in 2022.
Prior to the University of Virginia, Li was an Assistant Professor of Computer Science at the University of Georgia from 2018 to 2022 and a Data Scientist in Adobe Research from 2017 to 2018. He directs the Reasoning and Knowledge Discovery Laboratory. Li's research interests include trustworthy machine learning (e.g., robustness, fairness, causality, transferability), generative AI (e.g., large language models, diffusion models), computer vision, and causal inference.
Li has extensive publications in major peer-reviewed journals and conferences. He has served as associate editor of six journals, including Transactions on Machine Learning Research, IEEE Transactions on Neural Networks and Learning Systems, IEEE Transactions on Circuits and Systems for Video Technology, and IEEE Transactions on Cognitive and Developmental Systems, and also served as Area Chair for NeurIPS, ICLR, ICML, and IJCAI.
Li holds a Ph.D. in Computer Engineering from Northeastern University, and an M.S. in Information Security and B.S. in Computer Science from Nanjing University of Posts and Telecommunications.
Education
- Ph.D., Computer Engineering, Northeastern University
- M.S., Information Security, Nanjing University of Posts and Telecommunications
- B.S., Computer Science, Nanjing University of Posts and Telecommunications
Data Science Domains
Analytics, Data + Society
Areas of Practice
Artificial Intelligence and Machine Learning, Biomedical, Health, and Life Sciences, Human-Centered Design and Interaction, Theory, Foundations, and Advanced Methodologies, Data Ethics and Society
Methodologies
Data Mining, Machine Learning, Deep Learning
Selected Publications
Dongliang Guo, Mengxuan Hu, Zihan Guan, Thomas Hartvigsen, and Sheng Li. BalancEdit: Dynamically Balancing the Generality-Locality Trade-off in Multi-modal Model Editing. The Forty-Second International Conference on Machine Learning (ICML), 2025.
Daiqing Qi, Handong Zhao, Jing Shi, Simon Jenni, Yifei Fan, Franck
Dernoncourt, Scott Cohen, and Sheng Li. The Photographer's Eye: Teaching Multimodal Large Language Models to See, Think and Critique Like Photographers. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.
Ronghang Zhu, Mengxuan Hu, Weiming Zhuang, Lingjuan Lyu, Xiang Yu, and Sheng Li. Revisiting Source-Free Domain Adaptation: Insights into Representativeness, Generalization, and Diversity. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.
Guangya Wan, Yuqi Wu, Jie Chen, and Sheng Li. RASC: Reasoning-Aware Self-Consistency for Efficient and Faithful LLM Reasoning. The Annual Conference of the Nations of the Americas Chapter of the ACL (NAACL), 2025.
Mengxuan Hu, Zihan Guan, Yi Zeng, Junfeng Guo, Zhongliang Zhou, Jielu Zhang, Ruoxi Jia, Anil Kumar Vullikanti, and Sheng Li. Mind Control through Causal Inference: Predicting Clean Images from Poisoned Data. International Conference on Learning Representations (ICLR), 2025.
Mengxuan Hu, Zihan Guan, Junfeng Guo, Zhongliang Zhou, Jielu Zhang, and Sheng Li. BBCaL: Black-box Backdoor Detection under the Causality Lens. Transactions on Machine Learning Research (TMLR), 2025.
Daiqing Qi, Handong Zhao, and Sheng Li. Easy Regional Contrastive
Learning of Expressive Visual Fashion Representations. The Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS), 2024.
Daiqing Qi, Handong Zhao, Aidong Zhang, and Sheng Li. Generalizing to Unseen Domains via Text-guided Augmentation: A Training-free Approach, European Conference on Computer Vision (ECCV), 2024.
Yu Wang, Ronghang Zhu, Pengsheng Ji, and Sheng Li. Open-Set Graph Domain Adaptation via Separate Domain Alignment. The 38th Annual AAAI Conference on Artificial Intelligence (AAAI), 2024.
Weili Shi and Sheng Li. Dual-windowed Vision Transformer with Angular Self-Attention. Transactions on Machine Learning Research (TMLR), 2024.