arXiv AI June 2, 2026 By Guoqiang Zhang

Improved Belief-Attention in Vision Task

arXiv:2606. 00077v1 Announce Type: cross Abstract: Recently, Belief-Attention \cite{Guoqiang25BeliefAttention} has been proposed by first performing an orthogonal projection of the softmax-based weighted summation of $V$ vectors with respect to the original $V$ vectors and then taking the perpendicular component as the residual signal in Transformer for performance improvement.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

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

Jul 17

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging

arXiv:2506. 08297v2 Announce Type: replace-cross Abstract: Attention is the critical component of a transformer.

By Nhat Thanh Tran, Fanghui Xue, Shuai Zhang, Jiancheng Lyu, Yunling Zheng, Yingyong Qi, Jack Xin

llms computer-vision

arXiv Machine Learning

Jun 5

Exact Linear Attention

arXiv:2605. 18848v3 Announce Type: replace Abstract: This paper introduces Exact Linear Attention (ELA), a mechanism that achieves linear computational complexity for Transformer attention by exploiting the exact decomposition property of kernel functions, thereby eliminating approximation error.

By Weinuo Ou

llms computer-vision reinforcement-learning efficiency safety

arXiv Machine Learning

Aug 4

LAYA: Layer-wise Attention Aggregation for Interpretable Depth-Aware Neural Networks

arXiv:2511. 12723v2 Announce Type: replace Abstract: Deep neural networks typically rely on the representation produced by their final hidden layer to make predictions, implicitly assuming that this single vector fully captures the semantics encoded across all preceding transformations.

By Gennaro Vessio

rag computer-vision 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

Hugging Face Trending Papers

Jul 21

Norm or Direction? Decoding Vision Mambas for High-Resolution Vision

Vision Mamba models replace quadratic self-attention with linear complexity selective state space models (SSMs), emerging as efficient visual backbones. However, MambaOut demonstrates that a Gated CNN block can match or exceed VMamba on image classification, questioning the necessity of SSMs for vision.

computer-vision fine-tuning safety

Related stories

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

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging

Exact Linear Attention

LAYA: Layer-wise Attention Aggregation for Interpretable Depth-Aware Neural Networks

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

Norm or Direction? Decoding Vision Mambas for High-Resolution Vision