MedARC: Training-Free Adaptive Redundancy Compression of Visual Tokens for 3D Medical Vision-Language Models

• URL: http://arxiv.org/abs/2607.26554v1
• Date: Wed, 29 Jul 2026 07:27:09 GMT
• Title: MedARC: Training-Free Adaptive Redundancy Compression of Visual Tokens for 3D Medical Vision-Language Models
• Abstract summary: We propose MedARC, a framework for Adaptive Redundancy Compression of visual tokens in 3D medical vision-language models.<n>MedARC estimates token importance by integrating three complementary cues.<n>Experiments on CT-RATE and MR-RATE show that MedARC reduces visual-token overhead and inference time while preserving or improving diagnostic performance.
• Score: 3.8740159612186265
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Integrating 3D medical images with vision-language models (VLMs) holds substantial promise for computer-aided diagnosis. However, volumetric images generate prohibitively long visual-token sequences with considerable spatial and inter-slice redundancy. Existing token compression methods typically apply uniform reduction or rely on a single importance signal, increasing the risk of removing regions that are clinically relevant to the query or structurally distinctive. To address this limitation, we propose MedARC, a unified, training-free framework for Adaptive Redundancy Compression of visual tokens in 3D medical VLMs. MedARC estimates token importance by integrating three complementary cues: self-attention from the VLM vision encoder, which reflects the model's intrinsic visual focus; similarity between projected visual tokens and text embeddings, which identifies query-relevant regions; and deviations of local visual foundation model features from the volume-level feature center, which highlight structurally distinctive anatomy. The resulting importance distribution guides a saliency-aware merging strategy that preserves informative tokens while consolidating redundant ones rather than simply discarding them. Experiments on CT-RATE and MR-RATE show that MedARC reduces visual-token overhead and inference time while preserving or improving diagnostic performance. Its multi-cue scoring cost is outweighed by the savings from processing fewer tokens, with greater benefits expected for larger language models.

Related papers

• SCALPEL: Semantic Cross-modal Alignment via LLM-Powered Encoder Learning for Medical Vision-Language Representation [5.487826115955642]
  Vision-language pre-training serves as a cornerstone for medical multimodal representation learning.<n>We propose textbfSCALPEL, a textbfSemantic textbfCross-modal textbfAlignment framework via textbfLLM-textbfPowered textbfEncoder textbfLearning.
  arXiv  Detail & Related papers  (2026-07-29T13:12:32Z)
• Disease-Centric Vision-Language Pretraining with Hybrid Visual Encoding for 3D Computed Tomography [75.7789001619107]
  Vision-language pre-training holds great promise for general-purpose medical AI.<n>We propose a tailored framework featuring three key components.<n>A diagnosis-aware prompt strategy employs real clinical phrases and aggregated disease prototypes to bridge the pre-training-inference gap.
  arXiv  Detail & Related papers  (2026-06-24T08:24:45Z)
• Med-DisSeg: Dispersion-Driven Representation Learning for Fine-Grained Medical Image Segmentation [3.182068203318624]
  We propose Med DisSeg, a dispersion driven medical image segmentation framework.<n>Med DisSeg combines a lightweight Dispersive Loss with adaptive attention for fine grained structure segmentation.<n>We show that Med DisSeg achieves competitive results on multi organ CT segmentation, supporting its robustness and cross task applicability.
  arXiv  Detail & Related papers  (2026-05-14T08:49:36Z)
• MedPruner: Training-Free Hierarchical Token Pruning for Efficient 3D Medical Image Understanding in Vision-Language Models [59.180043227905294]
  We propose MedPruner, a training-free and model-agnostic hierarchical token pruning framework for efficient 3D medical image understanding.<n>We show that MedPruner enables models such as MedGemma to maintain or even exceed their original performance while retaining fewer than 5% of visual tokens.
  arXiv  Detail & Related papers  (2026-03-12T07:37:00Z)
• Look Carefully: Adaptive Visual Reinforcements in Multimodal Large Language Models for Hallucination Mitigation [51.743225614196774]
  Multimodal large language models (MLLMs) have achieved remarkable progress in vision-language reasoning.<n>They remain vulnerable to hallucination, where generated content deviates from visual evidence.<n>Recent vision enhancement methods attempt to address this issue by reinforcing visual tokens during decoding.<n>We propose Adaptive Visual Reinforcement (AIR), a training-free framework for MLLMs.
  arXiv  Detail & Related papers  (2026-02-27T14:18:51Z)
• Staged Voxel-Level Deep Reinforcement Learning for 3D Medical Image Segmentation with Noisy Annotations [4.581671524490035]
  We propose an end-to-end Staged Voxel-Level Deep Reinforcement Learning framework for robust medical image segmentation under noisy annotations.<n>This framework employs a dynamic iterative update strategy to automatically mitigate the impact of erroneous labels without requiring manual intervention.
  arXiv  Detail & Related papers  (2026-01-07T12:39:54Z)
• MIRNet: Integrating Constrained Graph-Based Reasoning with Pre-training for Diagnostic Medical Imaging [67.74482877175797]
  MIRNet is a novel framework that integrates self-supervised pre-training with constrained graph-based reasoning.<n>We introduce TongueAtlas-4K, a benchmark comprising 4,000 images annotated with 22 diagnostic labels.
  arXiv  Detail & Related papers  (2025-11-13T06:30:41Z)
• VELVET-Med: Vision and Efficient Language Pre-training for Volumetric Imaging Tasks in Medicine [11.993301266706139]
  We propose a vision-language pre-training framework, termed as textbfVELVET-Med, specifically designed for limited volumetric data such as 3D CT and associated radiology reports.<n>Our approach seeks to uncover rich spatial and semantic relationships embedded in volumetric medical images and corresponding clinical narratives.<n>The resulting encoders exhibit strong transferability, achieving state-of-the-art performance across a wide range of downstream tasks.
  arXiv  Detail & Related papers  (2025-08-16T17:08:43Z)
• Mitigating Hallucination for Large Vision Language Model by Inter-Modality Correlation Calibration Decoding [66.06337890279839]
  Large vision-language models (LVLMs) have shown remarkable capabilities in visual-language understanding for downstream multi-modal tasks.<n>LVLMs still suffer from generating hallucinations in complex generation tasks, leading to inconsistencies between visual inputs and generated content.<n>We propose an Inter-Modality Correlation Decoding (IMCCD) method to mitigate hallucinations in LVLMs in a training-free manner.
  arXiv  Detail & Related papers  (2025-01-03T17:56:28Z)
• Disruptive Autoencoders: Leveraging Low-level features for 3D Medical Image Pre-training [51.16994853817024]
  This work focuses on designing an effective pre-training framework for 3D radiology images. We introduce Disruptive Autoencoders, a pre-training framework that attempts to reconstruct the original image from disruptions created by a combination of local masking and low-level perturbations. The proposed pre-training framework is tested across multiple downstream tasks and achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-07-31T17:59:42Z)

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.