English
Related papers

Related papers: Attention Sink in Transformers: A Survey on Utiliz…

200 papers

Attention sink (AS) is a consistent pattern in transformer attention maps where certain tokens (often special tokens or positional anchors) disproportionately attract attention from other tokens. We show that in transformers, AS is not an…

Machine Learning · Computer Science 2025-08-05 Valeria Ruscio , Umberto Nanni , Fabrizio Silvestri

Attention sinks -- tokens that receive disproportionate attention mass -- are assumed to be functionally important in autoregressive language models, but their role in diffusion transformers remains unclear. We present a causal analysis in…

Computer Vision and Pattern Recognition · Computer Science 2026-05-13 Fangzheng Wu , Brian Summa

Transformers commonly exhibit an attention sink: disproportionately high attention to the first position. We study this behavior in GPT-2-style models with learned query biases and absolute positional embeddings. Combining structural…

Machine Learning · Computer Science 2026-04-17 Yuval Ran-Milo , Hila Ofek , Shahar Mendel

We study two recurring phenomena in Transformer language models: massive activations, in which a small number of tokens exhibit extreme outliers in a few channels, and attention sinks, in which certain tokens attract disproportionate…

Artificial Intelligence · Computer Science 2026-03-06 Shangwen Sun , Alfredo Canziani , Yann LeCun , Jiachen Zhu

Transformers have dominated sequence processing tasks for the past seven years -- most notably language modeling. However, the inherent quadratic complexity of their attention mechanism remains a significant bottleneck as context length…

Computation and Language · Computer Science 2025-10-08 Alexander M. Fichtl , Jeremias Bohn , Josefin Kelber , Edoardo Mosca , Georg Groh

Vision transformers have emerged as a powerful tool across a wide range of applications, yet their inner workings remain only partially understood. In this work, we examine the phenomenon of massive tokens - tokens with exceptionally high…

Computer Vision and Pattern Recognition · Computer Science 2025-07-23 Andrew Lu , Wentinn Liao , Liuhui Wang , Huzheng Yang , Jianbo Shi

Since its introduction in 2017, Transformer has emerged as the leading neural network architecture, catalyzing revolutionary advancements in many AI disciplines. The key innovation in Transformer is a Self-Attention (SA) mechanism designed…

Machine Learning · Computer Science 2024-02-05 Yueyao Yu , Yin Zhang

Language Models (LMs) assign significant attention to the first token, even if it is not semantically important, which is known as attention sink. This phenomenon has been widely adopted in applications such as streaming/long context…

Computation and Language · Computer Science 2025-03-04 Xiangming Gu , Tianyu Pang , Chao Du , Qian Liu , Fengzhuo Zhang , Cunxiao Du , Ye Wang , Min Lin

Recent Vision Transformer~(ViT) models have demonstrated encouraging results across various computer vision tasks, thanks to their competence in modeling long-range dependencies of image patches or tokens via self-attention. These models,…

Computer Vision and Pattern Recognition · Computer Science 2022-04-14 Sucheng Ren , Daquan Zhou , Shengfeng He , Jiashi Feng , Xinchao Wang

Large Language Models (LLMs) often allocate disproportionate attention to specific tokens, a phenomenon commonly referred to as the attention sink. While such sinks are generally considered detrimental, prior studies have identified a…

Machine Learning · Computer Science 2026-03-10 Runyu Peng , Ruixiao Li , Mingshu Chen , Yunhua Zhou , Qipeng Guo , Xipeng Qiu

Despite the prevalence of the attention sink phenomenon in Large Language Models (LLMs), where initial tokens disproportionately monopolize attention scores, its structural origins remain elusive. This work provides a \textit{mechanistic…

Machine Learning · Computer Science 2026-05-08 Siquan Li , Kaiqi Jiang , Jiacheng Sun , Tianyang Hu

Vision Transformers (ViTs) face severe computational bottlenecks due to the quadratic complexity of self-attention at high resolutions. Existing token reduction methods rely on local metrics - such as single-layer attention scores - that…

Machine Learning · Computer Science 2026-05-22 Jaehyuk Lee , Hanyoung Kim , Yanggee Kim , Donghun Lee

The attention mechanism is a core component of the Transformer architecture. Various methods have been developed to compute attention scores, including multi-head attention (MHA), multi-query attention, group-query attention and so on. We…

This paper studies interpretable and fair artificial intelligence architectures for understanding English reading. Introduced transformer-based models, integrating advanced attention mechanisms and gradient-based feature attribution. The…

Computation and Language · Computer Science 2026-04-28 Ping Li

Attention mechanisms have become integral in AI, significantly enhancing model performance and scalability by drawing inspiration from human cognition. Concurrently, the Attention Schema Theory (AST) in cognitive science posits that…

Artificial Intelligence · Computer Science 2025-09-22 Krati Saxena , Federico Jurado Ruiz , Guido Manzi , Dianbo Liu , Alex Lamb

Transformers often display an attention sink: probability mass concentrates on a fixed, content-agnostic position. Are sinks a byproduct of the optimization/training regime? Or are they sometimes functionally necessary in softmax…

Machine Learning · Computer Science 2026-04-20 Yuval Ran-Milo

In this paper, we propose EDIT (Encoder-Decoder Image Transformer), a novel architecture designed to mitigate the attention sink phenomenon observed in Vision Transformer models. Attention sink occurs when an excessive amount of attention…

Computer Vision and Pattern Recognition · Computer Science 2025-10-17 Wenfeng Feng , Hongxiang Wang , Jianlong Wang , Xin Zhang , Jingjing Zhao , Yueyue Liang , Xiang Chen , Duokui Han

The self-attention mechanism, a cornerstone of Transformer-based state-of-the-art deep learning architectures, is largely heuristic-driven and fundamentally challenging to interpret. Establishing a robust theoretical foundation to explain…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Laziz U. Abdullaev , Maksim Tkachenko , Tan M. Nguyen

Attention is a cornerstone of human cognition that facilitates the efficient extraction of information in everyday life. Recent developments in artificial intelligence like the Transformer architecture also incorporate the idea of attention…

Other Quantitative Biology · Quantitative Biology 2024-07-03 Minglu Zhao , Dehong Xu , Tao Gao

Transformers are crucial across many AI fields, such as large language models, computer vision, and reinforcement learning. This prominence stems from the architecture's perceived universality and scalability compared to alternatives. This…

Machine Learning · Computer Science 2025-12-23 Amirreza Abbasi , Mohsen Hooshmand
‹ Prev 1 2 3 10 Next ›