Simple Token-Efficient Vision-Language Model for Case-level Pathology Synoptic Report Generation

• URL: http://arxiv.org/abs/2605.30716v1
• Date: Fri, 29 May 2026 01:15:13 GMT
• Title: Simple Token-Efficient Vision-Language Model for Case-level Pathology Synoptic Report Generation
• Abstract summary: We present a simple token-efficient vision-language model for case-level synoptic report generation.<n>Our architecture follows a minimal three-component design: a frozen pathology patch, a lightweight two-layer vision-language aligner, and a large language model decoder.<n>Our approach achieves high ROUGE-L/METEOR/BLEU-4 scores while being substantially more efficient in memory and runtime.
• Score: 9.268049949671958
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Generating clinically useful pathology reports for pathology cases from whole-slide images (WSIs) is challenging due to gigapixel resolution, long visual-token sequences, and the complexity of case-level reasoning, where a single case may contain multiple WSIs with heterogeneous tissues and ambiguous findings. We present a simple token-efficient vision--language model for case-level synoptic report generation that remains practical under constrained GPU memory. Our architecture follows a minimal three-component design: a frozen pathology patch encoder, a lightweight two-layer MLP vision-language aligner, and a large language model decoder, with an explicit WSI marker token to separate slides within a case. Training proceeds in two supervised stages: (1) aligner-only WSI captioning using heterogeneous WSI-text pairs, and (2) case-level supervised fine-tuning on case-report pairs for structured report generation. To reduce sequence length, we represent each slide using $512 \times 512$ patches at $5\times$ magnification, which reduces the average sequence length by up to $64\times$ times compared to the commonly used $20\times$ patches. Combined with efficient training techniques, we enable practical training with only half a NVIDIA H100 GPU. Across both training stages, our approach achieves high ROUGE-L/METEOR/BLEU-4 scores while being substantially more efficient in memory and runtime. In AI-based evaluations, our model is consistently preferred over strong baselines. Extensive ablations characterize performance-efficiency trade-offs and identify simple choices that improve robustness in multi-WSI settings. Overall, this work provides a strong, reproducible baseline for efficient pathology report generation, lowering the barrier to multi-WSI VLM research under limited compute.

Related papers

• Unified Spatio-Temporal Token Scoring for Efficient Video VLMs [61.08183446817756]
  Token pruning is essential for enhancing the computational efficiency of vision-language models.<n>We introduce Spatio-Temporal Token Scoring (STTS), a simple and lightweight module that prunes vision tokens across both the ViT and the LLM.<n>STTS prunes 50% of vision tokens throughout the entire architecture, resulting in a 62% improvement in efficiency during both training and inference.
  arXiv  Detail & Related papers  (2026-03-18T17:59:56Z)
• LoC-Path: Learning to Compress for Pathology Multimodal Large Language Models [19.89635786218384]
  Whole Slide Image (WSI) understanding is fundamentally challenging due to its gigapixel scale and the extreme sparsity of diagnostically relevant regions.<n>Existing slide-level multimodal large language models (MLLMs) for pathology rely on heavy slide-level encoders.<n>We introduce an efficient MLLM framework, called LoC-Path, that replaces the expensive slide-level encoder with redundancy-reducing modules.
  arXiv  Detail & Related papers  (2025-12-05T03:16:46Z)
• VesSAM: Efficient Multi-Prompting for Segmenting Complex Vessel [68.24765319399286]
  We present VesSAM, a powerful and efficient framework tailored for 2D vessel segmentation.<n>VesSAM integrates (1) a convolutional adapter to enhance local texture features, (2) a multi-prompt encoder that fuses anatomical prompts, and (3) a lightweight mask decoder to reduce jagged artifacts.<n>VesSAM consistently outperforms state-of-the-art PEFT-based SAM variants by over 10% Dice and 13% IoU.
  arXiv  Detail & Related papers  (2025-11-02T15:47:05Z)
• Learning Hyperspectral Images with Curated Text Prompts for Efficient Multimodal Alignment [1.7188280334580195]
  We make an attempt to optimize a Vision-Language Model (VLM) for hyperspectral scene understanding by exploiting a CLIP-style contrastive training framework.<n>Our framework maps voxel-level embeddings from a vision backbone onto the latent space of a frozen large embedding model.<n>It is seen that the proposed method updates only 0.07 percent of the total parameters, yet yields state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-09-20T23:23:04Z)
• AHDMIL: Asymmetric Hierarchical Distillation Multi-Instance Learning for Fast and Accurate Whole-Slide Image Classification [51.525891360380285]
  AHDMIL is an Asymmetric Hierarchical Distillation Multi-Instance Learning framework.<n>It eliminates irrelevant patches through a two-step training process.<n>It consistently outperforms previous state-of-the-art methods in both classification performance and inference speed.
  arXiv  Detail & Related papers  (2025-08-07T07:47:16Z)
• Minimal High-Resolution Patches Are Sufficient for Whole Slide Image Representation via Cascaded Dual-Scale Reconstruction [13.897013242536849]
  Whole-slide image (WSI) analysis remains challenging due to gigapixel scale and sparsely distributed diagnostic regions.<n>We propose a Cascaded Dual-Scale Reconstruction framework, demonstrating that only an average of 9 high-resolution patches per WSI are sufficient for robust slide-level representation.
  arXiv  Detail & Related papers  (2025-08-03T08:01:30Z)
• HiLa: Hierarchical Vision-Language Collaboration for Cancer Survival Prediction [55.00788339683146]
  We propose a novel Hierarchical vision-Language collaboration framework for improved survival prediction.<n> Specifically, HiLa employs pretrained feature extractors to generate hierarchical visual features from WSIs at both patch and region levels.<n>This ap-proach enables the comprehensive learning of discriminative visual features cor-responding to different survival-related attributes from prompts.
  arXiv  Detail & Related papers  (2025-07-07T02:06:25Z)
• Accelerating Multimodal Large Language Models by Searching Optimal Vision Token Reduction [62.8375542401319]
  Multimodal Large Language Models (MLLMs) encode the input image(s) as vision tokens and feed them into the language backbone.<n>The number of vision tokens increases quadratically as the image resolutions, leading to huge computational costs.<n>We propose a greedy search algorithm (G-Search) to find the least number of vision tokens to keep at each layer from the shallow to the deep.
  arXiv  Detail & Related papers  (2024-11-30T18:54:32Z)
• A self-supervised framework for learning whole slide representations [52.774822784847565]
  We present Slide Pre-trained Transformers (SPT) for gigapixel-scale self-supervision of whole slide images. We benchmark SPT visual representations on five diagnostic tasks across three biomedical microscopy datasets.
  arXiv  Detail & Related papers  (2024-02-09T05:05:28Z)
• Hierarchical Transformer for Survival Prediction Using Multimodality Whole Slide Images and Genomics [63.76637479503006]
  Learning good representation of giga-pixel level whole slide pathology images (WSI) for downstream tasks is critical. This paper proposes a hierarchical-based multimodal transformer framework that learns a hierarchical mapping between pathology images and corresponding genes. Our architecture requires fewer GPU resources compared with benchmark methods while maintaining better WSI representation ability.
  arXiv  Detail & Related papers  (2022-11-29T23:47:56Z)
• An Efficient Cervical Whole Slide Image Analysis Framework Based on Multi-scale Semantic and Spatial Features using Deep Learning [2.7218168309244652]
  This study designs a novel inline connection network (InCNet) by enriching the multi-scale connectivity to build the lightweight model named You Only Look Cytopathology Once (YOLCO) The proposed model allows the input size enlarged to megapixel that can stitch the WSI without any overlap by the average repeats. Based on Transformer for classifying the integrated multi-scale multi-task features, the experimental results appear $0.872$ AUC score better and $2.51times$ faster than the best conventional method in WSI classification.
  arXiv  Detail & Related papers  (2021-06-29T06:24:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.