English
Related papers

Related papers: Adaptive Attention Span in Transformers

200 papers

Large Language Models (LLMs) face efficiency bottlenecks due to the quadratic complexity of the attention mechanism when processing long contexts. Sparse attention methods offer a promising solution, but existing approaches often suffer…

Computation and Language · Computer Science 2025-03-06 Lida Chen , Dong Xu , Chenxin An , Xintao Wang , Yikai Zhang , Jiangjie Chen , Zujie Liang , Feng Wei , Jiaqing Liang , Yanghua Xiao , Wei Wang

Transformers have had tremendous impact for several sequence related tasks, largely due to their ability to retrieve from any part of the sequence via softmax based dot-product attention. This mechanism plays a crucial role in Transformer's…

Machine Learning · Computer Science 2025-07-15 Sai Surya Duvvuri , Inderjit S. Dhillon

Pretrained transformer models have demonstrated remarkable performance across various natural language processing tasks. These models leverage the attention mechanism to capture long- and short-range dependencies in the sequence. However,…

Computation and Language · Computer Science 2023-10-20 Qingru Zhang , Dhananjay Ram , Cole Hawkins , Sheng Zha , Tuo Zhao

Transformers have demonstrated outstanding performance across a wide range of tasks, owing to their self-attention mechanism, but they are highly energy-consuming. Spiking Neural Networks have emerged as a promising energy-efficient…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Yufei Guo , Xiaode Liu , Yuanpei Chen , Weihang Peng , Yuhan Zhang , Zhe Ma

Transformers evaluated in a single, fixed-depth pass are provably limited in expressive power to the constant-depth circuit class TC0. Running a Transformer autoregressively removes that ceiling -- first in next-token prediction and, more…

Machine Learning · Computer Science 2025-07-21 Mrinal Mathur , Mike Doan , Barak Pearlmutter , Sergey Plis

Transformer-based pre-training techniques of text and layout have proven effective in a number of document understanding tasks. Despite this success, multimodal pre-training models suffer from very high computational and memory costs.…

Computation and Language · Computer Science 2021-09-03 Laura Nguyen , Thomas Scialom , Jacopo Staiano , Benjamin Piwowarski

Transformers have become central to natural language processing and large language models, but their deployment at scale faces three major challenges. First, the attention mechanism requires massive matrix multiplications and frequent…

Hardware Architecture · Computer Science 2026-01-22 Xiaoxuan Yang , Peilin Chen , Tergel Molom-Ochir , Yiran Chen

In the Transformer model, "self-attention" combines information from attended embeddings into the representation of the focal embedding in the next layer. Thus, across layers of the Transformer, information originating from different tokens…

Machine Learning · Computer Science 2020-06-02 Samira Abnar , Willem Zuidema

Transformers have recently revolutionized many domains in modern machine learning and one salient discovery is their remarkable in-context learning capability, where models can solve an unseen task by utilizing task-specific prompts without…

Machine Learning · Computer Science 2023-10-10 Yu Huang , Yuan Cheng , Yingbin Liang

Efficient attentions have greatly improved the computational efficiency of Transformers. However, most existing linear attention mechanisms suffer from an \emph{efficiency degradation} problem, leading to inefficiencies in causal language…

Computation and Language · Computer Science 2023-12-19 Jun Zhang , Shuyang Jiang , Jiangtao Feng , Lin Zheng , Lingpeng Kong

Can transformers learn to perform algorithmic tasks reliably across previously unseen input/output domains? While pre-trained language models show solid accuracy on benchmarks incorporating algorithmic reasoning, assessing the reliability…

Machine Learning · Computer Science 2025-07-22 Michal Spiegel , Michal Štefánik , Marek Kadlčík , Josef Kuchař

Transformers are powerful sequence models, but require time and memory that grows quadratically with the sequence length. In this paper we introduce sparse factorizations of the attention matrix which reduce this to $O(n \sqrt{n})$. We also…

Machine Learning · Computer Science 2019-04-25 Rewon Child , Scott Gray , Alec Radford , Ilya Sutskever

For real-time speech enhancement (SE) including noise suppression, dereverberation and acoustic echo cancellation, the time-variance of the audio signals becomes a severe challenge. The causality and memory usage limit that only the…

Audio and Speech Processing · Electrical Eng. & Systems 2023-02-22 Chengyu Zheng , Yuan Zhou , Xiulian Peng , Yuan Zhang , Yan Lu

In recent years, the popular Transformer architecture has achieved great success in many application areas, including natural language processing and computer vision. Many existing works aim to reduce the computational and memory complexity…

Machine Learning · Computer Science 2023-09-20 Zhe Chen

Transformer-based models, such as BERT and GPT, have been widely adopted in natural language processing (NLP) due to their exceptional performance. However, recent studies show their vulnerability to textual adversarial attacks where the…

Computation and Language · Computer Science 2023-12-01 Lujia Shen , Yuwen Pu , Shouling Ji , Changjiang Li , Xuhong Zhang , Chunpeng Ge , Ting Wang

The canonical $O(N^2)$ Transformer remains the empirical performance frontier in sequence modeling, and its training can be further optimized by addressing geometric inefficiency. We propose an optimization framework that leverages an…

Machine Learning · Computer Science 2025-12-16 Jongwook Kim , Sangheon Yun , Sukjin Yoon

The Transformer self-attention network has recently shown promising performance as an alternative to recurrent neural networks in end-to-end (E2E) automatic speech recognition (ASR) systems. However, Transformer has a drawback in that the…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-29 Emiru Tsunoo , Yosuke Kashiwagi , Toshiyuki Kumakura , Shinji Watanabe

The quadratic complexity of the attention module makes it gradually become the bulk of compute in Transformer-based LLMs during generation. Moreover, the excessive key-value cache that arises when dealing with long inputs also brings severe…

Computation and Language · Computer Science 2023-10-17 Siyu Ren , Qi Jia , Kenny Q. Zhu

Deep attention models have advanced the modelling of sequential data across many domains. For language modelling in particular, the Transformer-XL -- a Transformer augmented with a long-range memory of past activations -- has been shown to…

Machine Learning · Computer Science 2020-07-08 Jack W. Rae , Ali Razavi

While Transformer networks benefit from a global receptive field, their quadratic cost relative to sequence length restricts their application to long sequences and high-resolution inputs. We introduce Fast Multipole Attention (FMA), a…

Computation and Language · Computer Science 2025-09-19 Yanming Kang , Giang Tran , Hans De Sterck