arXiv AI September 28, 2026 By Zhexiang Li

MedTokenBudget: Lesion-Preserving Token Routing for Dermoscopic Image Classification

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Aug 21

Clustering and Token Denoising for Faster and More Robust VLMs

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.

By Baptiste Rossigneux, Inna Kucher, Vincent Lorrain, Emmanuel Casseau

llms efficiency multimodal benchmarks

arXiv Computer Vision

5d ago

Subtoken Vision Transformer for Fine-grained Recognition

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...

By Jie Zhu, Ivy Zhang, Minchul Kim, Xiaoming Liu

llms computer-vision nlp

Hugging Face Trending Papers

Jul 26

PathSelect: Sequential Token Selection for Whole Slide Pathology

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.

llms efficiency multimodal

arXiv AI

Jun 9

RAPID: Layer-Wise Redundancy-Aware Pruning and Importance-Driven Token Merging for Efficient ViT

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.

By Kyumin Choi, Ikbeom Jang

llms efficiency

Hugging Face Trending Papers

Jul 29

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

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.

llms rag multimodal

arXiv AI

Sep 2

SinkPruner: Sink-Free Visual Token Pruning for Multimodal Large Language Models

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.

By Shiyu Li, Zi-Yuan Hu, Shijia Huang, Yanyang Li, Yiwu Zhong, Liwei Wang