# Discovering Pathology Rationale and Token Allocation for Efficient Multimodal Pathology Reasoning

arXiv: https://arxiv.org/abs/2505.15687 · HTML: https://mlsanity.com/paper/2505.15687/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 43 references that are in the map.
- First posted on arXiv 21 May 2025.

## Builds on (most cited first, 28 of 28)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs](https://mlsanity.com/paper/2406.16860/) (2024)
- [Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs](https://mlsanity.com/paper/2401.06209/) (2024)
- [Visual-RFT: Visual Reinforcement Fine-Tuning](https://mlsanity.com/paper/2503.01785/) (2025)
- [PathVQA: 30000+ Questions for Medical Visual Question Answering](https://mlsanity.com/paper/2003.10286/) (2020)
- [Deep Learning for Generic Object Detection: A Survey](https://mlsanity.com/paper/1809.02165/) (2018)
- [Quilt-1M: One Million Image-Text Pairs for Histopathology](https://mlsanity.com/paper/2306.11207/) (2023)
- [Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Models](https://mlsanity.com/paper/2503.13939/) (2025)
- [BiomedParse: a biomedical foundation model for image parsing of everything everywhere all at once](https://mlsanity.com/paper/2405.12971/) (2024)
- [MambaMIL: Enhancing Long Sequence Modeling with Sequence Reordering in Computational Pathology](https://mlsanity.com/paper/2403.06800/) (2024)
- [MILD-Net: Minimal Information Loss Dilated Network for Gland Instance Segmentation in Colon Histology Images](https://mlsanity.com/paper/1806.01963/) (2018)
- [Quilt-LLaVA: Visual Instruction Tuning by Extracting Localized Narratives from Open-Source Histopathology Videos](https://mlsanity.com/paper/2312.04746/) (2023)
- [DCAN: Deep Contour-Aware Networks for Accurate Gland Segmentation](https://mlsanity.com/paper/1604.02677/) (2016)
- [Foundation Model for Advancing Healthcare: Challenges, Opportunities, and Future Directions](https://mlsanity.com/paper/2404.03264/) (2024)
- [A Multimodal Knowledge-enhanced Whole-slide Pathology Foundation Model](https://mlsanity.com/paper/2407.15362/) (2024)
- [PathAsst: A Generative Foundation AI Assistant Towards Artificial General Intelligence of Pathology](https://mlsanity.com/paper/2305.15072/) (2023)
- [PathMMU: A Massive Multimodal Expert-Level Benchmark for Understanding and Reasoning in Pathology](https://mlsanity.com/paper/2401.16355/) (2024)
- [In-context learning enables multimodal large language models to classify cancer pathology images](https://mlsanity.com/paper/2403.07407/) (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)
- [UniToPatho, a labeled histopathological dataset for colorectal polyps classification and adenoma dysplasia grading](https://mlsanity.com/paper/2101.09991/) (2021)
- [Towards A Generalizable Pathology Foundation Model via Unified Knowledge Distillation](https://mlsanity.com/paper/2407.18449/) (2024)
- [Vim4Path: Self-Supervised Vision Mamba for Histopathology Images](https://mlsanity.com/paper/2404.13222/) (2024)

## Built on by (most cited first, 4 of 4)

- [Patho-AgenticRAG: Towards Multimodal Agentic Retrieval-Augmented Generation for Pathology VLMs via Reinforcement Learning](https://mlsanity.com/paper/2508.02258/) (2025)
- [TeamPath: Building MultiModal Pathology Experts with Reasoning AI Copilots](https://mlsanity.com/paper/2511.17652/) (2025)
- [Computational Pathology in the Era of Emerging Foundation and Agentic AI -- International Expert Perspectives on Clinical Integration and Translational Readiness](https://mlsanity.com/paper/2603.05884/) (2026)
- [A Multimodal Agentic Pathology Co-pilot via Evidence Grounded Reasoning](https://mlsanity.com/paper/2606.08093/) (2026)

## Abstract (arXiv)

Multimodal pathological image understanding has garnered widespread interest due to its potential to improve diagnostic accuracy and enable personalized treatment through integrated visual and textual data. However, existing methods exhibit limited reasoning capabilities, which hamper their ability to handle complex diagnostic scenarios. Additionally, the enormous size of pathological images leads to severe computational burdens, further restricting their practical deployment. To address these limitations, we introduce a novel bilateral reinforcement learning framework comprising two synergistic branches. One reinforcement branch enhances the reasoning capability by enabling the model to learn task-specific decision processes, i.e., pathology rationales, directly from labels without explicit reasoning supervision. While the other branch dynamically allocates a tailored number of tokens to different images based on both their visual content and task context, thereby optimizing computational efficiency. We apply our method to various pathological tasks such as visual question answering, cancer subtyping, and lesion detection. Extensive experiments show an average +41.7 absolute performance improvement with 70.3% lower inference costs over the base models, achieving both reasoning accuracy and computational efficiency.