Dasol Choi

Venues

Papers

1. Better Safe Than Sorry? Overreaction Problem of Vision Language Models in Visual Emergency Recognition
   WACV 2026 · Dasol Choi
2. COMPASS: A Framework for Evaluating Organization-Specific Policy Alignment in LLMs
   ACL 2026 · Dasol Choi
3. What Users Leave Unsaid: Under-Specified Queries Limit Vision-Language Models
   ACL 2026 · Dasol Choi
4. Distribution-Level Feature Distancing for Machine Unlearning: Towards a Better Trade-off Between Model Utility and Forgetting
   AAAI 2025 · Dasol Choi
5. DMR: Disentangling Marginal Representations for Out-of-Distribution Detection
   CVPR 2024 · Dasol Choi
6. Towards Efficient Machine Unlearning with Data Augmentation: Guided Loss-Increasing (GLI) to Prevent the Catastrophic Model Utility Drop
   CVPR 2024 · Dasol Choi