大模型
arxiv.org ·
SLICEChat：面向全切片病理语言模型的渐进式编码器内令牌剪枝
该论文提出 SLICEChat，一种切片级多模态大语言模型，在混合 Mamba-Transformer 切片编码器内部集成渐进式 token 剪枝：Mamba 层负责高效长程传播，Transformer 层在序列逐步缩短时保留全局交互，阶段间以语言监督、区域感知的剪枝按受控 keep-rate 移除空间连贯的低效用区域，从而在多模态融合前得到紧凑切片表示。作者报告在 SlideBench VQA 上 TCGA 准确率 79.84%、BCNB 59.09%，优于此前切片级病理 MLLM，并在 WSI-Bench 取得最高综合指标，同时内存占用与推理延迟具竞争力。结果均为作者自报，尚待同行评审与复现验证。
AI推荐理由 arXiv 预印本，作者与摘要信息完整，事实明确。核心新信息是 SLICEChat 将渐进式 token 剪枝嵌入混合 Mamba-Transformer 切片编码器内部，在语言监督下按 keep-rate 计划移除空间连贯的低效用区域，从而在多模态融合前压缩全切片病理表示。摘要给出 SlideBench VQA 上 TCGA 79.84%、BCNB 59.09% 的准确率，并称在 WSI-Bench 取得最高综合指标、内存与推理延迟具竞争力。局限：均为作者自报结果，尚无同行评审或第三方复现，且未提供与基线差距的具体数值。对病理多模态大模型与长序列算力优化方向有参考价值。
72
正文
Computer Science > Computer Vision and Pattern Recognition
arXiv:2609.24894 (cs)
[Submitted on 21 Sep 2026]
Title:SLICEChat: Progressive In-Encoder Token Pruning for Whole-Slide Pathology Language Models
Authors:Ali Kerem Bozkurt, Baris Cem Bakay, Ibrahim Kulac, Cigdem Gunduz-Demir, Erkut Erdem, Aykut Erdem
View a PDF of the paper titled SLICEChat: Progressive In-Encoder Token Pruning for Whole-Slide Pathology Language Models, by Ali Kerem Bozkurt and 5 other authors
View PDF
HTML (experimental)
Abstract: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 computationally expensive. We introduce SLICEChat, a slide-level MLLM that integrates progressive token pruning within a hybrid Mamba--Transformer slide encoder. Mamba layers enable efficient long-range propagation, while Transformer layers preserve global interactions as the sequence is progressively shortened. Between stages, language-supervised, region-aware pruning removes spatially coherent low-utility regions under a controlled keep-rate schedule, producing compact slide representations before multimodal fusion. On SlideBench VQA, SLICEChat achieves 79.84% accuracy on TCGA and 59.09% on BCNB cohorts, outperforming prior slide-level pathology MLLMs, and achieves the highest overall WSI-Bench metrics. It also provides competitive memory usage and the inference latency among the evaluated models. These results demonstrate accurate and computationally efficient multimodal reasoning over gigapixel WSIs.
Comments:
Subjects:
Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL)
Cite as:
arXiv:2609.24894 [cs.CV]
(or
arXiv:2609.24894v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2609.24894
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Ali Kerem Bozkurt [view email]
[v1]
Mon, 21 Sep 2026 16:59:06 UTC (20,022 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled SLICEChat: Progressive In-Encoder Token Pruning for Whole-Slide Pathology Language Models, by Ali Kerem Bozkurt and 5 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CV
new
|
recent
| 2026-09
Change to browse by:
cs
cs.CL
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)