Profiles2024-2026
Shawn Im
University of Wisconsin-Madison
3Papers
0Last author
2Unique co-authors
3First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers3
- How Do Transformers Learn to Associate Tokens: Gradient Leading Terms Bring Mechanistic InterpretabilityAuthor 1 of 4ICLR 2026 · 4 citations
- Can DPO Learn Diverse Human Values? A Theoretical Scaling LawAuthor 1 of 2NeurIPS 2025 · 8 citations
- Understanding the Learning Dynamics of Alignment with Human FeedbackAuthor 1 of 2ICML 2024 · 18 citations
