Shawn Im

According to our database, Shawn Im authored at least 11 papers between 2023 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

How Do Transformers Learn to Associate Tokens: Gradient Leading Terms Bring Mechanistic Interpretability.

Shawn Im, Changdae Oh, Zhen Fang, Sharon Li

CoRR, January, 2026

How Well Can Preference Optimization Generalize Under Noisy Feedback?

Shawn Im, Yixuan Li

Trans. Mach. Learn. Res., 2026

2025

How Well Can Preference Optimization Generalize Under Noisy Feedback?

Shawn Im, Sharon Li

CoRR, October, 2025

Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders.

James Oldfield, Shawn Im, Yixuan Li, Mihalis A. Nicolaou, Ioannis Patras, Grigorios G. Chrysos

CoRR, May, 2025

Visual Instruction Bottleneck Tuning.

Changdae Oh, Jiatong Li, Shawn Im, Yixuan Li

CoRR, May, 2025

A Unified Understanding and Evaluation of Steering Methods.

Shawn Im, Yixuan Li

CoRR, February, 2025

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

Proceedings of the Forty-second International Conference on Machine Learning, 2025

Understanding Multimodal LLMs Under Distribution Shifts: An Information-Theoretic Approach.

Changdae Oh, Zhen Fang, Shawn Im, Xuefeng Du, Yixuan Li

Proceedings of the Forty-second International Conference on Machine Learning, 2025

2024

On the Generalization of Preference Learning with DPO.

Shawn Im, Yixuan Li

CoRR, 2024

Understanding the Learning Dynamics of Alignment with Human Feedback.

Shawn Im, Yixuan Li

Proceedings of the Forty-first International Conference on Machine Learning, 2024

2023

Evaluating the Utility of Model Explanations for Model Development.

Shawn Im, Jacob Andreas, Yilun Zhou

CoRR, 2023