arXiv Machine Learning July 14, 2026 By Christopher Buratti, Michele Marchetti, Federica Parlapiano, Davide Traini, Domenico Ursino, Luca Virgili

Gradient-Skipping Relevance Propagation for Efficient Explainability of Vision Transformers

Read the original on arXiv Machine Learning →

arXiv:2607. 10365v1 Announce Type: cross Abstract: Vision Transformers (ViTs) are difficult to interpret because current methods of relevance propagation and attention flow do not fully consider some key architectural features, such as the uneven importance of attention heads and residual connections.

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

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 AI

Jun 24

Listening makes Vision Clear for VLMs

arXiv:2606. 23763v1 Announce Type: cross Abstract: Recent work typically assesses vision--language consistency using attention distributions of answer-side tokens.

By Yiyang Chen, Yixin Tan, Binrui Shen

safety

arXiv Machine Learning

Jun 16

Enhancing Visual Feature Attribution via Weighted Integrated Gradients

arXiv:2505. 03201v4 Announce Type: replace-cross Abstract: Integrated Gradients (IG) is a widely used attribution method in explainable AI, particularly in computer vision applications where reliable feature attribution is essential.

By Kien Tran Duc Tuan, Tam Nguyen Trong, Son Nguyen Hoang, Khoat Than, Anh Nguyen Duc

llms computer-vision

arXiv Machine Learning

Jun 16

Spatial Priors via Space Filling Curves for Small and Limited Data Vision Transformers

arXiv:2606. 14757v1 Announce Type: cross Abstract: Though Vision Transformers (ViTs) have become the dominant backbone in many computer vision tasks, due to permutation equivariance, their attention mechanism lacks explicit spatial inductive biases.

By Leyla Naz Candogan, Arshia Afzal, Pol Puigdemont, Volkan Cevher

llms computer-vision fine-tuning safety

arXiv AI

Jun 6

Mechanistic Insights into Functional Sparsity in Multimodal LLMs via CoRe Heads

arXiv:2606. 05843v1 Announce Type: cross Abstract: While Multimodal Large Language Models (MLLMs) demonstrate remarkable proficiency on complex vision-language tasks, the mechanisms by which they extract query-relevant visual features from complex, noisy contexts remain opaque.

By Ruoxi Sun, Quantong Qiu, Juntao Li, Zecheng Tang, Yihang Lou, Min Zhang

llms efficiency multimodal safety

arXiv Machine Learning

Jun 8

Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation

arXiv:2604. 10098v2 Announce Type: replace Abstract: As the foundational architecture of modern machine learning, Transformers have driven remarkable progress across diverse AI domains.

By Zunhai Su, Hengyuan Zhang, Wei Wu, Yifan Zhang, Yaxiu Liu, He Xiao, Qingyao Yang, Yuxuan Sun, Rui Yang, Chao Zhang, Jing Xiong, Hui Shen, Keyu Fan, Weihao Ye, Chaofan Tao, Taiqiang Wu, Zhongwei Wan, Tiantian Zhang, Bowen Yan, Zhen Li, Yiming Zhang, Congkai Xie, Yulei Qian, Yuchen Xie, Yik-Chung Wu, Hongxia Yang, Ngai Wong

llms safety

Related stories

Exact Linear Attention

Listening makes Vision Clear for VLMs

Enhancing Visual Feature Attribution via Weighted Integrated Gradients

Spatial Priors via Space Filling Curves for Small and Limited Data Vision Transformers

Mechanistic Insights into Functional Sparsity in Multimodal LLMs via CoRe Heads

Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation