← Back to all news
arXiv Computer Vision By Rongyang Zhang, Chengqiang Lu, Cong Li, Hongchao Gu, Tingjia Shen, Xuyang Zhi, Qimeng Wang, Yan Gao, Yi Wu, Yao Hu, Hao Wang, Enhong Chen

Multi-Image Visual Token Pruning in Large Visual Language Models

Read the original on arXiv Computer Vision →

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.

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 Computer Vision.

Related stories

arXiv AI
Sep 10

STAR-Pro: Stage-Wise Token Adaptive Reduction with Progressive Refinement for Efficient Large Vision-Language Models

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...

By Yichen Guo, Tinghao Wang, Qizhe Zhang, Lingbei Meng, Yuan Zhang, Jiajun Cao, Hao Jiang, Chenwei Wu, Jixian Wu, Sixiang Chen, Tao Luo, Hongyang Cheng, Kai Tang, Chenxi Li, Renyuan Li, Xiande Huang, Wenya Wang, Shanghang Zhang
llmsefficiencymultimodalbenchmarks
More like this →
arXiv Computer Vision
Aug 27

Not All Attention Heads Contribute to Critical Visual Token Selection: Head-Aware Pruning Matters More

The paper shows that only a small subset of attention heads in vision-language models is responsible for selecting critical visual tokens. By pruning tokens based on similarity before LLM reasoning and then applying head‑aware pruning during reasoning, the proposed ProViP framework achieves high task performance with significant speedups. Experiments on LLaVA‑1.5‑7B demonstrate 95.9% performance retention and a 1.62× inference speedup at an 88.9% pruning ratio.

By Chaofang Ma, Lin Jiang, Carol Jingyi Li, Xingyu Liu, Zeyu Li, Jiang Xu, Wei Zhang
llmsragefficiencymultimodal
More like this →
arXiv Machine Learning
4d ago

V-CoLA: Vision Token Compression with Linear Attention

The paper introduces V-CoLA, a training‑free token compression framework tailored for vision-language models that use linear attention. V-CoLA employs a uniqueness‑aware importance criterion to select critical vision tokens and an adaptive token merging strategy to compress them, all optimized to fit the chunk‑wise parallelism of linear attention. Experiments show that V‑CoLA retains 99.5% of the original performance with only half the vision tokens and achieves significant speedups during prefill.

By Hao Jiang, Yiru Mao, Tianpeng Bu, Hao Zhou, Hongtao Duan, Wang Jing, Bowen Xu, Xin Chen, Lulu Hu, Bin Yang, Yongliang Tao, Minying Zhang
llmsmultimodalbenchmarks
More like this →
arXiv AI
Aug 5

Adaptive Two-Stage Visual Token Pruning for Efficient Inference in Video-Language Models

arXiv:2608. 03112v1 Announce Type: cross Abstract: Vision-language models excel at image and video understanding but suffer from high inference latency due to the need to process thousands of tokens per image, limiting their deployment on resource-constrained edge devices and in real-time surveillance applications.

By Paribesh Regmi, Qingshuang Chen, Chi Zhang, Heba Aly, Yelin Kim, Hongda Mao
llmsragfine-tuningefficiencymultimodalbenchmarks
More like this →