AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

Act Like a Pathologist: Tissue-Aware Whole Slide Image Reasoning

Wentao Huang, Weimin Lyu, Peiliang Lou, Qingqiao Hu, Xiaoling Hu, Shahira Abousamra, Wenchao Han, Ruifeng Guo, Jiawei Zhou, Chao Chen, Chen Wang

CVPR 2026 · Vision-language and multimodal › Visual question answering · approach: Vision-language model VQA evaluation · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
select patches with learned question-guided selection instead of random sampling (ablation)HistoSelect · WSI-Bench Close Diagnosisaccuracy: 78.02 -> 85.79Improved
select question-relevant patches instead of diversity-based (DivPrune) (ablation)HistoSelect · WSI-Bench Close Diagnosisaccuracy: 80.99 -> 85.79Improved
use learned selectors with IB regularization instead of non-learnable similarity (ablation)HistoSelect · WSI-Bench Close Diagnosisaccuracy: 81.98 -> 85.79Improved
add group sampler (coarse-to-fine) (ablation)HistoSelect · WSI-Bench Close Diagnosisaccuracy: 81.82 -> 85.79Improved
add patch selector (ablation)HistoSelect · WSI-Bench Close Diagnosisaccuracy: 81.32 -> 85.79Improved
increase token budget from 1k to 5k (ablation)HistoSelect · WSI-Bench Close Diagnosisaccuracy: 82.15 -> 85.79Improved
increase token budget from 5k to 10k (ablation)HistoSelect · WSI-Bench Close Diagnosisaccuracy: 85.79 -> 85.12No clear effect
select 30% of patches (5k tokens) instead of allHistoSelect · WSI-Bench Closetoken computation: 70% reductionImproved
use HistoSelect instead of SlideChatHistoSelect · Close-ended VQA averageaccuracy: 80.88 -> 83.80Improved
use HistoSelect instead of Quilt-LLaVA on treatment questions (open-ended)HistoSelect · WSI-Bench VQA TreatmentWSI-R: 0.807 -> 0.801Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy