MedTokenBudget introduces a supervised token routing framework for Vision Transformers applied to dermoscopic image classification. Its Lesion-Aware Token Scoring (LATS) module combines attention entropy, feature norm, and local feature contrast to select the top‑K patches under a target budget, trained with curriculum learning, diversity regularization, attention distillation, and lesion‑mask supervision. On the ISIC 2019 dataset, mask‑supervised LATS outperforms Random and ToMe at headline budgets while retaining more lesion patches.
arXiv:2608. 19285v1 Announce Type: cross Abstract: Recent Visual-Language Models (VLMs) have enhanced the capabilities of pre-trained LLMs by adding vision tokens alongside text, with approaches like LLaVA showing impressive results.
arXiv:2607.09086v2 Announce Type: replace Abstract: We present Subtoken Vision Transformer (SubViT), a selective image tokenization method for fine-grained visual recognition. Standard Vision Transfo...
Gigapixel Whole-Slide Images (WSIs) present a fundamental computational bottleneck for vision-language models (VLMs) due to extreme sequence lengths. Existing approaches predominantly rely on spatial sampling or training-free pruning, which risk diluting weak but informative signals, leading to the loss of critical diagnostic evidence due to the spatially diffuse nature of pathological cues.
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.
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.
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:2609.36916v1 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:2512. 08240v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) rely on hundreds of visual tokens, leading to high computational and memory costs.
arXiv:2511. 20956v2 Announce Type: replace-cross Abstract: Breast ultrasound (BUS) reporting relies on clinically meaningful lesion descriptors, including BI-RADS category, lesion shape, margin, echogenicity, posterior features, pathology, and histology.
arXiv:2605. 30716v2 Announce Type: replace-cross 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.
MDSkin-Net is a multi‑task skin lesion analysis framework that integrates Pattern Analysis priors into a hybrid CNN‑Transformer architecture. It introduces a Pattern Analysis‑Guided Attention Module (PAGAM) with improved Efficient Channel Attention, Multi‑Scale Spatial Attention, and Biased Asymmetry Attention, along with a multi‑scale spatial alignment regularization that uses segmentation masks as soft supervision. Trained only on the ISIC 2017 training split, the model achieves high segmentation and classification performance on multiple datasets, demonstrating strong zero‑shot generalization across different cohorts.
arXiv:2605.12491v2 Announce Type: replace Abstract: Vision Transformers (ViTs) learn rich visual-semantic representations through all-to-all self-attention among patch tokens. However, this design im...