SLICEChat: Progressive In-Encoder Token Pruning for Whole-Slide Pathology Language Models
SLICEChat prunes pathology slide tokens inside a hybrid Mamba-Transformer encoder before multimodal fusion.
SLICEChat is a slide-level multimodal model that progressively prunes tokens inside a hybrid Mamba-Transformer encoder for gigapixel whole-slide pathology images. Language-supervised, region-aware pruning removes spatially coherent low-utility regions on a keep-rate schedule before multimodal fusion. On SlideBench VQA it reaches 79.84% accuracy on TCGA and 59.09% on BCNB, outperforming prior slide-level pathology MLLMs, and leads overall WSI-Bench metrics with competitive memory use and latency.
- In-encoder pruning shortens slide tokens before multimodal fusion.
- Hybrid Mamba-Transformer encoder combines long-range and global layers.
- SlideBench VQA: 79.84% on TCGA and 59.09% on BCNB.
- Highest overall WSI-Bench metrics with competitive memory and latency.
From the original article
1 min read at arxiv.orgWhole-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 computationally expensive.
By Ali Kerem Bozkurt · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.