arXiv Computation and Language August 28, 2026 By Zizhong Ding, Junxian Li, Kai Liu, Shaoqiu Zhang, Xiao Xiao, Linghe Kong, Yulun Zhang

ET-Prune: Evidence-Aware Dynamic Budgeting for Visual Token Pruning in Text-Rich MLLMs

Read the original on arXiv Computation and Language →

ET‑Prune is a training‑free framework that dynamically allocates visual token budgets in multimodal large language models based on question‑conditioned evidence. It protects text‑like spatial regions, converts evidence uncertainty into a token floor, and progressively prunes concentrated evidence while retaining diffuse or text‑dense tokens. In six backbone‑benchmark comparisons, ET‑Prune matches or outperforms other pruned methods while keeping roughly half the visual tokens, achieving notable gains on OCRBench‑v2 and MMBench v1.1.

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 Computation and Language.

arXiv AI

Sep 30

TReVS: Integrating Textual Relevance and Visual Saliency for Efficient Vision-Language Model Token Pruning

arXiv:2609.37581v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) excel at visual understanding and reasoning but often incur substantial inference costs due to the large number of visu...

By Jing Wang, Zhiping Wu, Dongdong Ren, Youfang Han, Wei Zhao, Wenbin Li

llms efficiency multimodal benchmarks

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

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

llms efficiency multimodal benchmarks

arXiv Machine Learning

Aug 6

DIVE: Dynamic Iterative Visual Evidence Construction for Efficient Vision-Language Models

arXiv:2608. 04496v1 Announce Type: cross Abstract: Visual inputs in vision-language models (VLMs) are often encoded into substantially longer token sequences than text, making visual tokens a major bottleneck for efficient inference.

By Chen Zhong, Xiao An, Zijie Wang, Jiepan Li, Guangyi Yang, Wei He

llms efficiency multimodal benchmarks

Hugging Face Trending Papers

Aug 24

Buried in Textual Debt: Context Pruning with Visual Evidence Preservation for MLLM Agents

Multimodal Large Language Models (MLLMs) are increasingly deployed as multi-step agents, where explicit reasoning supports task decomposition and tool coordination but also accumulates self-generated...

llms agents fine-tuning efficiency multimodal benchmarks

arXiv AI

Aug 25

Buried in Textual Debt: Context Pruning with Visual Evidence Preservation for MLLM Agents

arXiv:2608.22963v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) are increasingly deployed as multi-step agents, where explicit reasoning supports task decomposition and tool...

By Yuchen Huang, Sijia Li, Jun Zhang, Yi R. Fung

llms agents fine-tuning efficiency multimodal benchmarks

One email a morning, machine-written

Related stories

TReVS: Integrating Textual Relevance and Visual Saliency for Efficient Vision-Language Model Token Pruning

AnchorPrune: Relevance-Anchored Contextual Expansion for Visual Token Pruning

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

DIVE: Dynamic Iterative Visual Evidence Construction for Efficient Vision-Language Models

Buried in Textual Debt: Context Pruning with Visual Evidence Preservation for MLLM Agents

Buried in Textual Debt: Context Pruning with Visual Evidence Preservation for MLLM Agents