3 accepted papers
While Multimodal Large Language Models (MLLMs) excel at single-image understanding, they exhibit significantly degraded performance in multi-image reasoning scenarios. Multi-image reasoning presents fundamental challenges including complex inter-relationships between images and scattered critical in
Prompt tuning enables Vision-Language Models (VLMs) to efficiently adapt to new tasks through learnable prompt vectors. This naturally raises a question: do these prompts leak private information about their training data? While Membership Inference Attacks (MIAs) can quantify this risk, current met
2D-3D cross-dimensional registration for spinal surgery navigation, which aims to achieve real-time visual navigation of preoperative 3D vertebrae based on intraoperative 2D fluoroscopy images, faces significant challenges due to semantic and dimensional gaps. Traditional 2D-3D registration methods…