SLICEChat: Progressive In-Encoder Token Pruning for Whole-Slide Pathology Language Models
Whole-slide pathology images (WSIs) contain gigapixel-scale visual content, creating a major scalability challenge for slide-level multimodal large language models (MLLMs). Existing approaches process thousands of patch tokens and typically apply compression only after slide encoding, leaving multimodal attention compu...
Ali Kerem Bozkurt, Baris Cem Bakay, Ibrahim Kulac et al.
· 0 citations