# Efficient Whole Slide Pathology VQA via Token Compression

arXiv: https://arxiv.org/abs/2507.14497 · HTML: https://mlsanity.com/paper/2507.14497/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 23 of its 31 references that are in the map.
- First posted on arXiv 19 Jul 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Medical vision-language models](https://mlsanity.com/mllm/medical-vision-language-models/)
- Efficient LLM inference and serving / [Visual token pruning in multimodal models](https://mlsanity.com/inference/visual-token-pruning-in-multimodal-models/)

## Builds on (most cited first, 23 of 23)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Images](https://mlsanity.com/paper/2004.09666/) (2020)
- [An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models](https://mlsanity.com/paper/2403.06764/) (2024)
- [DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models](https://mlsanity.com/paper/2503.02175/) (2025)
- [Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization](https://mlsanity.com/paper/2303.15810/) (2023)
- [Quilt-LLaVA: Visual Instruction Tuning by Extracting Localized Narratives from Open-Source Histopathology Videos](https://mlsanity.com/paper/2312.04746/) (2023)
- [Attention-Challenging Multiple Instance Learning for Whole Slide Image Classification](https://mlsanity.com/paper/2311.07125/) (2023)
- [A Policy-Guided Imitation Approach for Offline Reinforcement Learning](https://mlsanity.com/paper/2210.08323/) (2022)
- [Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsification](https://mlsanity.com/paper/2412.00876/) (2024)
- [SlideChat: A Large Vision-Language Assistant for Whole-Slide Pathology Image Understanding](https://mlsanity.com/paper/2410.11761/) (2024)
- [WSI-VQA: Interpreting Whole Slide Images by Generative Visual Question Answering](https://mlsanity.com/paper/2407.05603/) (2024)
- [CPath-Omni: A Unified Multimodal Foundation Model for Patch and Whole Slide Image Analysis in Computational Pathology](https://mlsanity.com/paper/2412.12077/) (2024)
- [PathGen-1.6M: 1.6 Million Pathology Image-text Pairs Generation through Multi-agent Collaboration](https://mlsanity.com/paper/2407.00203/) (2024)
- [ViLa-MIL: Dual-scale Vision-Language Multiple Instance Learning for Whole Slide Image Classification](https://mlsanity.com/paper/2502.08391/) (2025)
- [FOCUS: Knowledge-enhanced Adaptive Visual Compression for Few-shot Whole Slide Image Classification](https://mlsanity.com/paper/2411.14743/) (2024)
- [Look Beneath the Surface: Exploiting Fundamental Symmetry for Sample-Efficient Offline RL](https://mlsanity.com/paper/2306.04220/) (2023)
- [Hummer: Towards Limited Competitive Preference Dataset](https://mlsanity.com/paper/2405.11647/) (2024)
- [Automatic Report Generation for Histopathology images using pre-trained Vision Transformers](https://mlsanity.com/paper/2311.06176/) (2023)
- [Comparative Analysis of CPU and GPU Profiling for Deep Learning Models](https://mlsanity.com/paper/2309.02521/) (2023)

## Built on by (most cited first, 6 of 6)

- [A Survey of Token Compression for Efficient Multimodal Large Language Models](https://mlsanity.com/paper/2507.20198/) (2025)
- [LoC-Path: Learning to Compress for Pathology Multimodal Large Language Models](https://mlsanity.com/paper/2512.05391/) (2025)
- [Act Like a Pathologist: Tissue-Aware Whole Slide Image Reasoning](https://mlsanity.com/paper/2603.00667/) (2026)
- [Backdoor Learning in Language Models and Vision-Language Models](https://mlsanity.com/paper/2608.18095/) (2026)
- [SLICEChat: Progressive In-Encoder Token Pruning for Whole-Slide Pathology Language Models](https://mlsanity.com/paper/2609.24894/) (2026)
- [Question-Specific Knowledge Graphs for Efficient Visual Reasoning](https://mlsanity.com/paper/2609.35942/) (2026)

## Abstract (arXiv)

Whole-slide images (WSIs) in pathology can reach up to 10,000 x 10,000 pixels, posing significant challenges for multimodal large language model (MLLM) due to long context length and high computational demands. Previous methods typically focus on patch-level analysis or slide-level classification using CLIP-based models with multi-instance learning, but they lack the generative capabilities needed for visual question answering (VQA). More recent MLLM-based approaches address VQA by feeding thousands of patch tokens directly into the language model, which leads to excessive resource consumption. To address these limitations, we propose Token Compression Pathology LLaVA (TCP-LLaVA), the first MLLM architecture to perform WSI VQA via token compression. TCP-LLaVA introduces a set of trainable compression tokens that aggregate visual and textual information through a modality compression module, inspired by the [CLS] token mechanism in BERT. Only the compressed tokens are forwarded to the LLM for answer generation, significantly reducing input length and computational cost. Experiments on ten TCGA tumor subtypes show that TCP-LLaVA outperforms existing MLLM baselines in VQA accuracy while reducing training resource consumption by a substantial margin.