English
Related papers

Related papers: Hierarchical Shift Mixing -- Beyond Dense Attentio…

200 papers

Transformer-based models have been achieving state-of-the-art results in several fields of Natural Language Processing. However, its direct application to speech tasks is not trivial. The nature of this sequences carries problems such as…

Computation and Language · Computer Science 2022-05-17 Gerard Sant , Gerard I. Gállego , Belen Alastruey , Marta R. Costa-Jussà

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

Since its introduction, the transformers architecture has seen great adoption in NLP applications, but it also has limitations. Although the self-attention mechanism allows for generating very rich representations of the input text, its…

Computation and Language · Computer Science 2023-11-10 Daniele Giofré , Sneha Ghantasala

In the world of deep learning, Transformer models have become very significant, leading to improvements in many areas from understanding language to recognizing images, covering a wide range of applications. Despite their success, the…

Machine Learning · Computer Science 2024-07-19 Ghadeer Jaradat , Mohammed Tolba , Ghada Alsuhli , Hani Saleh , Mahmoud Al-Qutayri , Thanos Stouraitis , Baker Mohammad

Transformer-based LLMs achieve strong results on many language tasks; however, long inputs remain challenging because context windows are finite, and prefill latency and memory grow rapidly with prompt length. Flat token-stream processing…

Computation and Language · Computer Science 2026-05-26 Maryam Haghifam , Zifan He , Jason Cong , Yizhou Sun

Variable count is among the main scalability bottlenecks for transformer modeling in multivariate time series (MTS) data. On top of this, a growing consensus in the field points to indiscriminate inter-variable mixing as a potential source…

Machine Learning · Computer Science 2025-09-25 Hunjae Lee , Corey Clark

Large language models produce powerful text embeddings, but their causal attention mechanism restricts the flow of information from later to earlier tokens, degrading representation quality. While recent methods attempt to solve this by…

Computation and Language · Computer Science 2025-11-20 Xueying Ding , Xingyue Huang , Mingxuan Ju , Liam Collins , Yozen Liu , Leman Akoglu , Neil Shah , Tong Zhao

Transformers have demonstrated remarkable success across vision, language, and video. Yet, increasing task complexity has led to larger models and more tokens, raising the quadratic cost of self-attention and the overhead of GPU memory…

Computer Vision and Pattern Recognition · Computer Science 2025-08-04 Joonmyung Choi , Sanghyeok Lee , Byungoh Ko , Eunseo Kim , Jihyung Kil , Hyunwoo J. Kim

Softmax attention is the principle backbone of foundation models for various artificial intelligence applications, yet its quadratic complexity in sequence length can limit its inference throughput in long-context settings. To address this…

Machine Learning · Computer Science 2024-12-10 Jerome Sieber , Carmen Amo Alonso , Alexandre Didier , Melanie N. Zeilinger , Antonio Orvieto

Is it always necessary to compute tokens from shallow to deep layers in Transformers? The continued success of vanilla Transformers and their variants suggests an undoubted "yes". In this work, however, we attempt to break the depth-ordered…

Computation and Language · Computer Science 2024-07-10 Zhuocheng Gong , Ang Lv , Jian Guan , Junxi Yan , Wei Wu , Huishuai Zhang , Minlie Huang , Dongyan Zhao , Rui Yan

Linearizing pretrained large language models (LLMs) primarily relies on intra-layer hybrid attention mechanisms to alleviate the quadratic complexity of standard softmax attention. Existing methods perform token routing based on…

Machine Learning · Computer Science 2026-02-03 Weikang Meng , Liangyu Huo , Yadan Luo , Jiawen Guan , Jingyi Zhang , Yingjian Li , Zheng Zhang

Transformer-based large language models (LLMs) exhibit impressive performance in generative tasks but also introduce significant challenges in real-world serving due to inefficient use of the expensive, computation-optimized accelerators.…

Machine Learning · Computer Science 2025-04-11 Shaoyuan Chen , Wencong Xiao , Yutong Lin , Mingxing Zhang , Yingdi Shan , Jinlei Jiang , Kang Chen , Yongwei Wu

Recent advances in deep learning have relied heavily on the use of large Transformers due to their ability to learn at scale. However, the core building block of Transformers, the attention operator, exhibits quadratic cost in sequence…

A natural question arising in Music Source Separation (MSS) is whether long range contextual information is useful, or whether local acoustic features are sufficient. In other fields, attention based Transformers have shown their ability to…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-17 Simon Rouard , Francisco Massa , Alexandre Défossez

Since its inception in "Attention Is All You Need", transformer architecture has led to revolutionary advancements in NLP. The attention layer within the transformer admits a sequence of input tokens $X$ and makes them interact through…

Machine Learning · Computer Science 2024-02-23 Davoud Ataee Tarzanagh , Yingcong Li , Christos Thrampoulidis , Samet Oymak

The three existing dominant network families, i.e., CNNs, Transformers, and MLPs, differ from each other mainly in the ways of fusing spatial contextual information, leaving designing more effective token-mixing mechanisms at the core of…

Computer Vision and Pattern Recognition · Computer Science 2022-12-26 Guoqiang Wei , Zhizheng Zhang , Cuiling Lan , Yan Lu , Zhibo Chen

Transformers are the cornerstone of modern large language models, but their quadratic computational complexity limits efficiency in long-sequence processing. Recent advancements in Mamba, a state space model (SSM) with linear complexity,…

Machine Learning · Computer Science 2026-01-08 Yixing Li , Ruobing Xie , Zhen Yang , Xingwu Sun , Shuaipeng Li , Weidong Han , Zhanhui Kang , Yu Cheng , Chengzhong Xu , Di Wang , Jie Jiang

Transformer requires a fixed number of layers and heads which makes them inflexible to the complexity of individual samples and expensive in training and inference. To address this, we propose a sample-based Dynamic Hierarchical Transformer…

Machine Learning · Computer Science 2024-01-11 Fanfei Meng , Lele Zhang , Yu Chen , Yuxin Wang

We present an empirical study of whether hierarchically structured, shared-weight recurrence can match the representational quality of independent-layer stacking in a Transformer-based language model. HRM-LM replaces L independent…

Computation and Language · Computer Science 2026-04-17 Sang-Il Han

To mitigate the computational complexity in the self-attention mechanism on long sequences, linear attention utilizes computation tricks to achieve linear complexity, while state space models (SSMs) popularize a favorable practice of using…

Machine Learning · Computer Science 2024-06-17 Zicheng Liu , Siyuan Li , Li Wang , Zedong Wang , Yunfan Liu , Stan Z. Li