arXiv Computer Vision
MedSTP: Preserving Subspace and Transition Evidence for Medical VQA Token Pruning
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
Hugging Face Trending Papers
Oct 15
MedSTP: Preserving Subspace and Transition Evidence for Medical VQA Token Pruning
Medical vision-language models (VLMs) for visual question answering (VQA) often pass long visual-token sequences to the language model, making visual-token pruning attractive but risky for medical ima...
arXiv AI
Jun 26
MedPruner: Training-Free Hierarchical Token Pruning for Efficient 3D Medical Image Understanding in Vision-Language Models
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.
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.
arXiv AI
Aug 25
E2S-Pruner: Progressive Two-Stage Evidence Fusion for Visual Token Pruning in Vision-Language Models
arXiv:2608.23253v1 Announce Type: cross Abstract: Vision-language models typically encode an image into hundreds of visual tokens, incurring substantial inference latency and GPU memory overhead. Exi...
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.
arXiv Computer Vision
Aug 28
Multi-Image Visual Token Pruning in Large Visual Language Models
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.