# Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation

arXiv: https://arxiv.org/abs/2608.00279 · HTML: https://mlsanity.com/paper/2608.00279/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 43 of its 63 references that are in the map.
- First posted on arXiv 31 Jul 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Medical vision-language models](https://mlsanity.com/mllm/medical-vision-language-models/)

## Builds on (most cited first, 30 of 43)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [Show and Tell: A Neural Image Caption Generator](https://mlsanity.com/paper/1411.4555/) (2014)
- [MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs](https://mlsanity.com/paper/1901.07042/) (2019)
- [Meshed-Memory Transformer for Image Captioning](https://mlsanity.com/paper/1912.08226/) (2019)
- [Making the Most of Text Semantics to Improve Biomedical Vision--Language Processing](https://mlsanity.com/paper/2204.09817/) (2022)
- [RadGraph: Extracting Clinical Entities and Relations from Radiology Reports](https://mlsanity.com/paper/2106.14463/) (2021)
- [Image Captioning with Semantic Attention](https://mlsanity.com/paper/1603.03925/) (2016)
- [On the Automatic Generation of Medical Imaging Reports](https://mlsanity.com/paper/1711.08195/) (2017)
- [Cross-modal Memory Networks for Radiology Report Generation](https://mlsanity.com/paper/2204.13258/) (2022)
- [Exploring and Distilling Posterior and Prior Knowledge for Radiology Report Generation](https://mlsanity.com/paper/2106.06963/) (2021)
- [Multi-Granularity Cross-modal Alignment for Generalized Medical Visual Representation Learning](https://mlsanity.com/paper/2210.06044/) (2022)
- [When Radiology Report Generation Meets Knowledge Graph](https://mlsanity.com/paper/2002.08277/) (2020)
- [Hybrid Retrieval-Generation Reinforced Agent for Medical Image Report Generation](https://mlsanity.com/paper/1805.08298/) (2018)
- [Improving Factual Completeness and Consistency of Image-to-Text Radiology Report Generation](https://mlsanity.com/paper/2010.10042/) (2020)
- [Interactive and Explainable Region-guided Radiology Report Generation](https://mlsanity.com/paper/2304.08295/) (2023)
- [TieNet: Text-Image Embedding Network for Common Thorax Disease Classification and Reporting in Chest X-rays](https://mlsanity.com/paper/1801.04334/) (2018)
- [Knowledge-enhanced Visual-Language Pre-training on Chest Radiology Images](https://mlsanity.com/paper/2302.14042/) (2023)
- [Dynamic Graph Enhanced Contrastive Learning for Chest X-ray Report Generation](https://mlsanity.com/paper/2303.10323/) (2023)
- [METransformer: Radiology Report Generation by Transformer with Multiple Learnable Expert Tokens](https://mlsanity.com/paper/2304.02211/) (2023)
- [Improving Chest X-Ray Report Generation by Leveraging Warm Starting](https://mlsanity.com/paper/2201.09405/) (2022)
- [Chest ImaGenome Dataset for Clinical Reasoning](https://mlsanity.com/paper/2108.00316/) (2021)
- [Competence-based Multimodal Curriculum Learning for Medical Report Generation](https://mlsanity.com/paper/2206.14579/) (2022)
- [Contrastive Attention for Automatic Chest X-ray Report Generation](https://mlsanity.com/paper/2106.06965/) (2021)
- [AlignTransformer: Hierarchical Alignment of Visual Regions and Disease Tags for Medical Report Generation](https://mlsanity.com/paper/2203.10095/) (2022)

## Abstract (arXiv)

Recent radiology-adapted vision-language models have achieved strong performance on standard report generation benchmarks, yet their robustness and generalization remain constrained by imperfect alignment and correlation between visual and textual features. Existing methods connect image and text either implicitly through autoregressive report supervision or explicitly through contrastive learning. However, autoregressive supervision alone is insufficient to establish reliable image-text alignment, while contrastive learning can push apart unpaired reports that describe related pathologies simply because they are not paired with the same image. This is problematic in radiology, where different reports may share compatible pathology semantics rather than being true negatives. As a result, the learned representation may fail to organize images and reports around shared pathology concepts, causing the decoder to rely on pretrained language priors and generate clinically plausible reports that are not fully supported by radiographic evidence. To address this issue, we propose PALM, a pathology-aware alignment framework for radiology report generation. Instead of directly matching each image-report pair while separating all others, PALM aligns visual and textual features through shared pathology prototypes. These prototypes provide a clinically meaningful bridge between radiographic evidence and textual findings, allowing cases with similar pathology semantics to move toward common concepts without separating compatible cases. In addition, we introduce Masked Evidence Modeling to strengthen the image encoder sensitivity to local radiographic evidence by learning semantic changes caused by masked image regions. Experiments on MIMIC-CXR, IU X-Ray, and MIMIC-ABN show that PALM consistently improves both report generation and abnormality-focused robustness.