English
Related papers

Related papers: Why Is Attention Sparse In Particle Transformer?

200 papers

Transformer models have achieved state-of-the-art results in a wide range of NLP tasks including summarization. Training and inference using large transformer models can be computationally expensive. Previous work has focused on one…

Computation and Language · Computer Science 2021-09-10 Potsawee Manakul , Mark J. F. Gales

Learning sparse parity functions has become a theoretical testbed for studying feature learning in neural networks. However, existing analyses primarily focus on Feed-Forward Neural Networks (FFNNs). Meanwhile, theoretical understanding of…

Machine Learning · Computer Science 2026-05-12 Yaomengxi Han , Debarghya Ghoshdastidar

Transformer architecture has been very successful long runner in the field of Deep Learning (DL) and Large Language Models (LLM) because of its powerful attention-based learning and parallel-natured architecture. As the models grow gigantic…

Machine Learning · Computer Science 2026-01-21 Phani Kumar , Nyshadham , Jyothendra Varma , Polisetty V R K , Aditya Rathore

The Transformer architecture model, based on self-attention and multi-head attention, has achieved remarkable success in offline end-to-end Automatic Speech Recognition (ASR). However, self-attention and multi-head attention cannot be…

Computation and Language · Computer Science 2022-10-03 Chendong Zhao , Jianzong Wang , Wen qi Wei , Xiaoyang Qu , Haoqian Wang , Jing Xiao

Transformers-based models, such as BERT, have been one of the most successful deep learning models for NLP. Unfortunately, one of their core limitations is the quadratic dependency (mainly in terms of memory) on the sequence length due to…

The favorable performance of Vision Transformers (ViTs) is often attributed to the multi-head self-attention (MSA). The MSA enables global interactions at each layer of a ViT model, which is a contrasting feature against Convolutional…

Computer Vision and Pattern Recognition · Computer Science 2024-12-30 Nam Hyeon-Woo , Kim Yu-Ji , Byeongho Heo , Dongyoon Han , Seong Joon Oh , Tae-Hyun Oh

This paper investigates fake news detection as a downstream evaluation of Transformer representations, benchmarking encoder-only and decoder-only pre-trained models (BERT, GPT-2, Transformer-XL) as frozen embedders paired with lightweight…

Computation and Language · Computer Science 2025-12-01 Sumit Mamtani , Abhijeet Bhure

In Diffusion Transformer (DiT) models, particularly for video generation, attention latency is a major bottleneck due to the long sequence length and the quadratic complexity. We find that attention weights can be separated into two parts:…

We revisit the problem of training attention-based sparse image matching models for various local features. We first identify one critical design choice that has been previously overlooked, which significantly impacts the performance of the…

Computer Vision and Pattern Recognition · Computer Science 2026-03-13 Qiang Wang

The attention mechanism is considered the backbone of the widely-used Transformer architecture. It contextualizes the input by computing input-specific attention matrices. We find that this mechanism, while powerful and elegant, is not as…

Computation and Language · Computer Science 2022-11-08 Michael Hassid , Hao Peng , Daniel Rotem , Jungo Kasai , Ivan Montero , Noah A. Smith , Roy Schwartz

Can a transformer learn which attention entries matter during training? In principle, yes: attention distributions are highly concentrated, and a small gate network can identify the important entries post-hoc with near-perfect accuracy. In…

Machine Learning · Computer Science 2026-03-04 Keston Aquino-Michaels

Recent research on the multi-head attention mechanism, especially that in pre-trained models such as BERT, has shown us heuristics and clues in analyzing various aspects of the mechanism. As most of the research focus on probing tasks or…

Computation and Language · Computer Science 2020-11-04 Yue Guan , Jingwen Leng , Chao Li , Quan Chen , Minyi Guo

State-of-the-art transformer models use pairwise dot-product based self-attention, which comes at a computational cost quadratic in the input sequence length. In this paper, we investigate the global structure of attention scores computed…

Machine Learning · Computer Science 2021-06-17 Srinadh Bhojanapalli , Ayan Chakrabarti , Himanshu Jain , Sanjiv Kumar , Michal Lukasik , Andreas Veit

With the advent of large models based on the Transformer architecture, researchers have observed an anomalous phenomenon in the Attention mechanism--there is a very high attention on the first element, which is prevalent across…

Machine Learning · Computer Science 2024-07-04 Ruiqing Yan , Xingbo Du , Haoyu Deng , Linghan Zheng , Qiuzhuang Sun , Jifang Hu , Yuhang Shao , Penghao Jiang , Jinrong Jiang , Lian Zhao

Transformers have recently shown superior performances on various vision tasks. The large, sometimes even global, receptive field endows Transformer models with higher representation power over their CNN counterparts. Nevertheless, simply…

Computer Vision and Pattern Recognition · Computer Science 2022-05-25 Zhuofan Xia , Xuran Pan , Shiji Song , Li Erran Li , Gao Huang

The highly popular Transformer architecture, based on self-attention, is the foundation of large pretrained models such as BERT, that have become an enduring paradigm in NLP. While powerful, the computational resources and time required to…

Computation and Language · Computer Science 2021-08-31 Ran Tian , Joshua Maynez , Ankur P. Parikh

Transformers have proven highly effective across modalities, but standard softmax attention scales quadratically with sequence length, limiting long context modeling. Linear attention mitigates this by approximating attention with kernel…

Machine Learning · Computer Science 2026-02-10 Ashkan Shahbazi , Chayne Thrash , Yikun Bai , Keaton Hamm , Navid NaderiAlizadeh , Soheil Kolouri

Large transformer models have achieved state-of-the-art results in numerous natural language processing tasks. Among the pivotal components of the transformer architecture, the attention mechanism plays a crucial role in capturing token…

Computation and Language · Computer Science 2026-03-16 Yichuan Deng , Zhao Song , Kaijun Yuan , Tianyi Zhou

Transformers have revolutionized natural language processing, but their quadratic complexity with respect to sequence length remains a fundamental bottleneck for long-range modeling. While sparse attention mechanisms like RingAttention…

Computation and Language · Computer Science 2026-03-31 Dong Liu , Yanxuan Yu

We present a novel attention mechanism: Causal Attention (CATT), to remove the ever-elusive confounding effect in existing attention-based vision-language models. This effect causes harmful bias that misleads the attention module to focus…

Computer Vision and Pattern Recognition · Computer Science 2021-03-08 Xu Yang , Hanwang Zhang , Guojun Qi , Jianfei Cai