Hugging Face Trending Papers June 2, 2026

When Attention Collapses: Stage-Aware Visual Token Pruning from Structure to Semantics

Read the original on Hugging Face Trending Papers →

Vision-Language Models (VLMs) have demonstrated remarkable capabilities but suffer from significant computational overhead during inference. While visual token pruning offers a promising solution, existing methods predominantly rely on initial attention scores.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI

Jun 3

When Attention Collapses: Stage-Aware Visual Token Pruning from Structure to Semantics

arXiv:2606. 03569v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have demonstrated remarkable capabilities but suffer from significant computational overhead during inference.

By Jiahui Wang, Kai Zhang, Mai Han, Huanghe Zhang

llms efficiency multimodal safety

arXiv AI

Jul 28

Disentangling Semantic Attention from Structural Bias in the Attention Manifold

arXiv:2607. 24017v1 Announce Type: cross Abstract: The empirical success of attention mechanism in Multimodal Large Language Models (MLLMs) often obscures its inherent, subtle flaws.

By Pengkun Jiao, Bin Zhu, Jingjing Chen, Yu-gang Jiang

llms multimodal benchmarks safety

arXiv AI

Aug 10

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin

arXiv:2608. 06411v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) achieve strong performance across diverse vision-language tasks, but their efficiency is limited by the cost of processing numerous visual tokens.

By Yuyao Sun, Tao Deng, Shuang Li, Deqing Wang, Hao Geng, Minjun Yu

llms efficiency multimodal benchmarks

arXiv AI

Jul 10

Beyond Attention Scores: SVD-Based Vision Token Pruning for Efficient Vision-Language Models

arXiv:2604. 11530v3 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) have revolutionized multi-modal learning by jointly processing visual and textual information.

By Yvon Apedo, Martyna Poreba, Michal Szczepanski, Samia Bouchafa

llms efficiency multimodal safety

arXiv AI

Jun 29

IWP: Token Pruning as Implicit Weight Pruning in Large Vision Language Models

arXiv:2604. 00757v2 Announce Type: replace-cross Abstract: Large Vision Language Models show impressive performance across image and video understanding tasks, yet their computational cost grows rapidly with the number of visual tokens.

By Dong-Jae Lee, Sunghyun Baek, Junmo Kim

llms efficiency

arXiv AI

Jun 26

TOPS: First-Principles Visual Token Pruning via Constructing Token Optimal Preservation Sets for Efficient MLLM Inference

arXiv:2606. 27161v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have achieved strong multimodal reasoning capabilities, but their efficiency is limited by the large number of visual tokens, which introduces substantial computational overhead.

By Tinghao Wang, Yichen Guo, Rui Huang, Zheng Lu, Qizhe Zhang, Chenxi Li, Yuan Zhang, Jiajun Cao, Zhirong Shen, Yaosong Du, Guangyan Gan, Wenya Wang, Lin William Cong, Shanghang Zhang

llms efficiency multimodal benchmarks safety

Related stories

When Attention Collapses: Stage-Aware Visual Token Pruning from Structure to Semantics

Disentangling Semantic Attention from Structural Bias in the Attention Manifold

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin

Beyond Attention Scores: SVD-Based Vision Token Pruning for Efficient Vision-Language Models

IWP: Token Pruning as Implicit Weight Pruning in Large Vision Language Models

TOPS: First-Principles Visual Token Pruning via Constructing Token Optimal Preservation Sets for Efficient MLLM Inference