Im, Shawn

8 publications

TMLR 2026 How Well Can Preference Optimization Generalize Under Noisy Feedback? Shawn Im, Yixuan Li

NeurIPS 2025 Can DPO Learn Diverse Human Values? a Theoretical Scaling Law Shawn Im, Sharon Li

ICML 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

NeurIPS 2025 Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders James Oldfield, Shawn Im, Sharon Li, Mihalis Nicolaou, Ioannis Patras, Grigorios Chrysos

ICML 2025 Understanding Multimodal LLMs Under Distribution Shifts: An Information-Theoretic Approach Changdae Oh, Zhen Fang, Shawn Im, Xuefeng Du, Yixuan Li

ICLRW 2025 Understanding Multimodal LLMs Under Distribution Shifts: An Information-Theoretic Approach Changdae Oh, Zhen Fang, Shawn Im, Xuefeng Du, Yixuan Li

NeurIPS 2025 Visual Instruction Bottleneck Tuning Changdae Oh, Jiatong Li, Shawn Im, Sharon Li

ICML 2024 Understanding the Learning Dynamics of Alignment with Human Feedback Shawn Im, Yixuan Li