 DefMamba: Deformable Visual State Space ModelComputer 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 |
 VMamba: Visual State Space ModelNeural Information Processing Systems (NeurIPS), 2024 |
 Spatial-Mamba: Effective Visual State Space Models via Structure-aware State FusionInternational Conference on Learning Representations (ICLR), 2024 |
