Shawn Im
Hello! I am a PhD student at UW-Madison working with Prof. Sharon Li. I am thankful to be supported by the NSF GRFP. I also had the chance to intern at Apple MLR this summer. Previously, I was an undergraduate at MIT in mathematics and computer science. My interest is in developing a reliable understanding of the behavior of machine learning models primarily to ensure they are beneficial. Not only is this understanding crucial for safe and beneficial models, but also, as models grow to understand more about the world and human values or preferences, a strong understanding of their behavior has the potential to lead to new insights of the world and ourselves. Currently, I am working on
- Interpretability
- Theory of ML
- AI Safety
Recent Work
Visual Instruction Bottleneck Tuning
Changdae Oh, Jiatong Li, Shawn Im, Yixuan Li
Neural Information Processing Systems (NeurIPS), 2025
[Paper]
Research
Position: Challenges and Future Directions of Data-Centric AI Alignment
Min-Hsuan Yeh, Jeffrey Wang, Xuefeng Du, Seongheon Park, Leitian Tao, Shawn Im, Yixuan Li
In Proceedings of International Conference on Machine Learning (ICML), 2025
[Paper]
Understanding Multimodal LLMs Under Distribution Shifts: An Information-Theoretic Approach
Changdae Oh, Zhen Fang, Shawn Im, Xuefeng Du, Yixuan Li
In Proceedings of International Conference on Machine Learning (ICML), 2025
[Paper]
A Unified Understanding and Evaluation of Steering Methods
Shawn Im, Yixuan Li
Preprint, 2025
[Paper]
Evaluating the Utility of Model Explanations for Model Development
Shawn Im, Jacob Andreas, Yilun Zhou
NeurIPS Workshop on Attributing Model Behavior at Scale (ATTRIB), 2023
[Paper]
Other