English
Related papers

Related papers: Smart Bird: Learnable Sparse Attention for Efficie…

200 papers

Transformer-based models excel in speech recognition. Existing efforts to optimize Transformer inference, typically for long-context applications, center on simplifying attention score calculations. However, streaming speech recognition…

Machine Learning · Computer Science 2024-01-22 Yang Li , Liangzhen Lai , Yuan Shangguan , Forrest N. Iandola , Zhaoheng Ni , Ernie Chang , Yangyang Shi , Vikas Chandra

Transformer has been widely-used in many Natural Language Processing (NLP) tasks and the scaled dot-product attention between tokens is a core module of Transformer. This attention is a token-wise design and its complexity is quadratic to…

Computation and Language · Computer Science 2020-08-13 Shuai Zhang , Peng Zhang , Xindian Ma , Junqiu Wei , Ningning Wang , Qun Liu

Transformer has achieved great success in the NLP field by composing various advanced models like BERT and GPT. However, Transformer and its existing variants may not be optimal in capturing token distances because the position or distance…

Computation and Language · Computer Science 2021-04-13 Chuhan Wu , Fangzhao Wu , Yongfeng Huang

Speculative decoding (SD) is a widely adopted approach for accelerating inference in large language models (LLMs), particularly when the draft and target models are well aligned. However, state-of-the-art SD methods typically rely on…

Computation and Language · Computer Science 2026-02-12 Wei Zhong , Manasa Bharadwaj , Yixiao Wang , Yipeng Ji , Chul Lee

Transformer networks are able to capture patterns in data coming from many domains (text, images, videos, proteins, etc.) with little or no change to architecture components. We perform a theoretical analysis of the core component…

Machine Learning · Computer Science 2021-06-09 Valerii Likhosherstov , Krzysztof Choromanski , Adrian Weller

Pretrained language models based on the transformer architecture have shown great success in NLP. Textual training data often comes from the web and is thus tagged with time-specific information, but most language models ignore this…

Computation and Language · Computer Science 2022-05-05 Guy D. Rosin , Kira Radinsky

We present the Condensate Theorem: attention sparsity is a learned topological property, not an architectural constraint. Through empirical analysis of trained language models, we find that attention mass concentrates on a distinct…

Machine Learning · Computer Science 2026-02-11 Jorge L. Ruiz Williams

Following the success of dot-product attention in Transformers, numerous approximations have been recently proposed to address its quadratic complexity with respect to the input length. While these variants are memory and compute efficient,…

Computation and Language · Computer Science 2021-06-15 Ankit Gupta , Guy Dar , Shaya Goodman , David Ciprut , Jonathan Berant

Large transformer models have shown extraordinary success in achieving state-of-the-art results in many natural language processing applications. However, training and deploying these models can be prohibitively costly for long sequences,…

Machine Learning · Computer Science 2020-06-16 Sinong Wang , Belinda Z. Li , Madian Khabsa , Han Fang , Hao Ma

Long-sequence processing is a critical capability for modern large language models. However, the self-attention mechanism in the standard Transformer architecture faces severe computational and memory bottlenecks when processing long…

Computation and Language · Computer Science 2025-09-30 Weilin Zhao , Zihan Zhou , Zhou Su , Chaojun Xiao , Yuxuan Li , Yanghao Li , Yudi Zhang , Weilun Zhao , Zhen Li , Yuxiang Huang , Ao Sun , Xu Han , Zhiyuan Liu

Looped Transformers (LT) have emerged as a powerful architecture by iterating their layers multiple times before decoding the final token. However, pairing them with full attention retains quadratic complexity, making them computationally…

Machine Learning · Computer Science 2026-05-26 Chunyuan Deng , Yizhe Zhang , Rui-Jie Zhu , Yuanyuan Xu , Jiarui Liu , T. S. Eugene Ng , Hanjie Chen

As the context window expands, self-attention increasingly dominates the transformer's inference time. Therefore, accelerating attention computation while minimizing performance degradation is essential for the efficient deployment of Large…

Computation and Language · Computer Science 2025-03-14 Eli Sason , Darya Frolova , Boris Nazarov , Felix Goldberd

Recently, Transformer based models have shown competitive automatic speech recognition (ASR) performance. One key factor in the success of these models is the multi-head attention mechanism. However, for trained models, we have previously…

Computation and Language · Computer Science 2021-04-07 Shucong Zhang , Erfan Loweimi , Peter Bell , Steve Renals

The attention module, which is a crucial component in Transformer, cannot scale efficiently to long sequences due to its quadratic complexity. Many works focus on approximating the dot-then-exponentiate softmax function in the original…

Machine Learning · Computer Science 2021-11-04 Shengjie Luo , Shanda Li , Tianle Cai , Di He , Dinglan Peng , Shuxin Zheng , Guolin Ke , Liwei Wang , Tie-Yan Liu

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

The inference process for large language models is slow and memory-intensive, with one of the most critical bottlenecks being excessive Key-Value (KV) cache accesses. This paper introduces "Double Sparsity," a novel post-training sparse…

Machine Learning · Computer Science 2024-08-20 Shuo Yang , Ying Sheng , Joseph E. Gonzalez , Ion Stoica , Lianmin Zheng

Transformer-based models have achieved state-of-the-art performance in jet tagging at the CERN Large Hadron Collider (LHC), with the Particle Transformer (ParT) representing a leading example of such models. A striking feature of ParT is…

Gating mechanisms have been widely utilized, from early models like LSTMs and Highway Networks to recent state space models, linear attention, and also softmax attention. Yet, existing literature rarely examines the specific effects of…

Computation and Language · Computer Science 2025-05-13 Zihan Qiu , Zekun Wang , Bo Zheng , Zeyu Huang , Kaiyue Wen , Songlin Yang , Rui Men , Le Yu , Fei Huang , Suozhi Huang , Dayiheng Liu , Jingren Zhou , Junyang Lin

To address the high resolution of image pixels, the Swin Transformer introduces window attention. This mechanism divides an image into non-overlapping windows and restricts attention computation to within each window, significantly…

Computer Vision and Pattern Recognition · Computer Science 2025-01-15 Zhendong Zhang

In this paper, we show that a simple self-supervised pre-trained audio model can achieve comparable inference efficiency to more complicated pre-trained models with speech transformer encoders. These speech transformers rely on mixing…

Sound · Computer Science 2024-02-09 Sungho Jeon , Ching-Feng Yeh , Hakan Inan , Wei-Ning Hsu , Rashi Rungta , Yashar Mehdad , Daniel Bikel