arXiv Computer Vision September 18, 2026 By Shengli He (Guizhou University), Yongchao Liang (Guizhou University), Roumeng He (Shanghai Ocean University), Junjie Zeng (Guizhou University), Jiyuan He (Guizhou University), Can Wu (Guizhou University), Li Zheng (Guizhou University)

QCPruner: Query-Conditioned Population Coverage for Visual Token Pruning

Read the original on arXiv Computer Vision →

QCPruner is a training‑free visual token pruning method that conditions both token selection and representation on the query via bilateral utility weighting. It fuses keyword‑matched query anchors with cross‑modal cues to compute a nonnegative facility‑location objective that is monotone and submodular, guaranteeing a (1‑1/e) greedy approximation. Across multiple multimodal large language models, QCPruner consistently outperforms existing pruning methods, achieving over 96% of unpruned performance even with very few tokens retained.

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.

arXiv AI

Jul 9

AnchorPrune: Relevance-Anchored Contextual Expansion for Visual Token Pruning

arXiv:2607. 07033v1 Announce Type: cross Abstract: Large vision-language models incur substantial inference costs because high-resolution inputs introduce thousands of visual tokens, many of which are redundant for a given query.

By Kyuan Oh, Bumsoo Kim

llms efficiency multimodal benchmarks

arXiv AI

Jul 28

GOTS: Greedy Orthogonal Token Selection for High-Resolution Vision-Language Models

arXiv:2607. 23913v1 Announce Type: new Abstract: Modern vision-language models (VLMs) increasingly rely on dynamic or high-resolution visual encoding, producing thousands of visual tokens that substantially increase downstream language-model inference cost.

By Jun Ling, Tao Huang, Junzhuo Liu, Bowen Tang, Peng Wang

llms multimodal benchmarks

arXiv Computer Vision

Sep 15

StepPrune: Adaptive Sequential Visual Token Selection across Multimodal Large Language Models

arXiv:2609.13804v1 Announce Type: new Abstract: Visual prefixes account for a major portion of the per-layer computation in multimodal large language models (MLLMs), making visual-token pruning a dir...

By Hansen Zhang, Landi He, Mingde Yao, Lijian Xu

llms efficiency multimodal

arXiv AI

Aug 10

RoRA: Role-Oriented Regional Allocation for Visual Token Pruning in MLLMs

arXiv:2608. 07088v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) encode images as long visual token sequences, making prefilling and KV-cache storage expensive.

By Qiyanhui Lu, Han Wu, Rongjian Xu, Tingzhang Luo, Cheng Fan, Xinghao Chen, Minjing Dong, Jufeng Yang, Jianyuan Guo

llms efficiency multimodal

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...

By Taoyu Qian, Qi Wang, Daqian Shi, Yuanhao Jiang, Shang Gao, Hualong Yu

llms fine-tuning efficiency multimodal

arXiv AI

Sep 16

StackTok: Accelerating VLMs Inference with Budget-Adaptive Visual Token Selection

arXiv:2609.16841v1 Announce Type: cross Abstract: Increasing image resolution produces ever-longer visual-token sequences in vision-language models (VLMs), substantially raising their inference cost....

By Zhenbin Wang, Lei Zhang, Lituan Wang, Wei Huang, Yan Wang, Zhenwei Zhang

llms multimodal benchmarks

One email a morning, machine-written

Related stories

AnchorPrune: Relevance-Anchored Contextual Expansion for Visual Token Pruning

GOTS: Greedy Orthogonal Token Selection for High-Resolution Vision-Language Models

StepPrune: Adaptive Sequential Visual Token Selection across Multimodal Large Language Models

RoRA: Role-Oriented Regional Allocation for Visual Token Pruning in MLLMs

E2S-Pruner: Progressive Two-Stage Evidence Fusion for Visual Token Pruning in Vision-Language Models

StackTok: Accelerating VLMs Inference with Budget-Adaptive Visual Token Selection