 Your other Left! Vision-Language Models Fail to Identify Relative Positions in Medical ImagesInternational Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2025 |
 BadToken: Token-level Backdoor Attacks to Multi-modal Large Language ModelsComputer Vision and Pattern Recognition (CVPR), 2025 |
 MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement LearningInternational Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2025 |
 A Survey of Large Language Models for Healthcare: from Data, Technology, and Applications to Accountability and EthicsInformation Fusion (Inf. Fusion), 2023 |
