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.
arXiv:2603. 11625v2 Announce Type: replace-cross Abstract: While specialized Medical Vision-Language Models (VLMs) have achieved remarkable success in interpreting 2D and 3D medical modalities, their deployment for 3D volumetric data remains constrained by significant computational inefficiencies.
arXiv:2608. 10635v1 Announce Type: cross Abstract: Medical Vision-Language Models (Med-VLMs) excel at verbalizing visual content, yet precise visual perception, segmentation, and grounding remain challenging.
Vision-language pre-training (VLP) holds great promise for general-purpose medical AI by leveraging radiology reports as rich textual supervision, yet existing methods struggle with 3D CT imaging due to inefficient visual backbones and coarse semantic alignment. To address these issues, we propose a tailored VLP framework featuring three key components: (1) a CNN-ViT hybrid encoder that replaces ViT's patch embedding with a 3D CNN backbone to efficiently capture local anatomical details while preserving global attention and compatibility with pre-trained cross-modal priors; (2) a disease-level contrastive learning mechanism using learnable query tokens to dynamically extract disease-specific semantics from full reports and align them with corresponding visual features, thereby disentangling distinct diseases within the same anatomical region; and (3) a diagnosis-aware prompt strategy that employs real clinical phrases and aggregated disease prototypes to bridge the pre-training-inference gap and enhance zero-shot diagnostic reliability.
arXiv:2608. 04515v1 Announce Type: cross Abstract: Slice-based MLLMs leverage mature 2D encoders by representing 3D volumes as sequences of 2D slices.
Textual descriptions can reduce ambiguity in medical image segmentation by specifying the finding and location to be delineated. Existing text-guided methods mainly improve where image and language fe...
Multimodal Routing and Region Refinement for Language-Guided Medical Image Segmentation (MRSeg) is a parameter‑efficient framework that uses frozen ConvNeXt‑Tiny and PubMedBERT encoders to extract multiscale visual features and clinical text tokens. A joint router predicts a sparse mixture over low‑rank adapter bases, enabling separate adaptation for two visual scales and text while keeping feature‑specific parameters distinct. Region Bridge aggregates dense visual tokens into latent regions using text‑derived queries, refines them via self‑attention and text cross‑attention, and redistributes the refined information back to the feature maps, culminating in a multiscale decoder that combines refined semantic features with shallow image evidence. MRSeg achieves state‑of‑the‑art Dice/mIoU scores on QaTa‑COV19 and MosMedData+ with only 7.11 M trainable parameters and 7.60 GFLOPs.
arXiv:2510. 15042v3 Announce Type: replace-cross Abstract: In the 3D medical image domain, vision-language pre-training is used to create vision-language encoders (VLEs) that can support radiologists by retrieving patients with similar abnormalities, predicting likelihoods of abnormality, or, with downstream adaptation, generating radiological reports.
arXiv:2608. 13690v1 Announce Type: cross Abstract: Medical image segmentation is still largely treated as a vision-only problem, although clinical interpretation often relies on textual knowledge of anatomy, location, appearance, and surrounding context.
arXiv:2609.36916v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) incur high inference latency from long visual token sequences. Existing pruning methods commonly use attention...
arXiv:2609.37581v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) excel at visual understanding and reasoning but often incur substantial inference costs due to the large number of visu...
SinkPruner is a training‑free framework that prunes visual tokens for multimodal large language models by first removing high‑norm redundant tokens with a visual sanitizer and then selectively keeping tokens that align with the text query using a text‑guided pruner. The coarse‑to‑fine design reduces attention sink and dispersion, enabling an 89% token reduction while preserving 96.5% of LLaVA‑1.5’s performance and 91.8% of Qwen2.5‑VL’s performance across twelve image‑language and four video‑language benchmarks. The visual sanitizer also improves existing pruning methods, showing strong transferability.
arXiv:2609.05916v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) achieve strong multimodal understanding, but the hundreds to thousands of visual tokens they process impose subs...