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.
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:2608. 04515v1 Announce Type: cross Abstract: Slice-based MLLMs leverage mature 2D encoders by representing 3D volumes as sequences of 2D slices.
arXiv:2607.12896v3 Announce Type: replace Abstract: Medical image segmentation foundation models are expected to generalize across diverse clinical scenarios, yet existing universal methods remain fr...
The paper introduces Adaptive Visual Token Pruning (AVTP), a training‑free framework that dynamically selects pruning layers and ratios for large vision‑language models (LVLMs) when processing multiple image sequences. By analyzing visual attention distributions across different LVLM architectures, AVTP adapts token retention to image importance, enabling efficient inference without relying on attention‑based computations incompatible with FlashAttention. Experiments show significant speedups—up to 2× for Qwen3VL‑8B—while preserving or even improving accuracy on multi‑image benchmarks.
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.
arXiv:2608. 08713v1 Announce Type: cross Abstract: Vision-language models offer a promising path toward automating radiology report generation, but applying them to full 3D CT volumes poses substantial computational challenges.
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.
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:2606. 08156v1 Announce Type: cross Abstract: Vision Transformers (ViTs) achieve strong performance but suffer from high computational costs due to quadratic self-attention complexity.
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...
MTMed3D is a multi-task Transformer-based model that jointly performs 3D detection, segmentation, and classification in medical imaging. It uses a shared Transformer encoder to produce multi-scale features, with separate CNN decoders for each task. Evaluated on BraTS 2018 and 2019, it achieves strong results, especially in detection, while reducing computational cost and inference time compared to single-task models.
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.