English
Related papers

Related papers: Multi-Mixer Models: Flexible Sequence Modeling wit…

200 papers

Transformers have achieved success in both language and vision domains. However, it is prohibitively expensive to scale them to long sequences such as long documents or high-resolution images, because self-attention mechanism has quadratic…

Computer Vision and Pattern Recognition · Computer Science 2021-12-08 Chen Zhu , Wei Ping , Chaowei Xiao , Mohammad Shoeybi , Tom Goldstein , Anima Anandkumar , Bryan Catanzaro

The Transformer is a sequence model that forgoes traditional recurrent architectures in favor of a fully attention-based approach. Besides improving performance, an advantage of using attention is that it can also help to interpret a model…

Human-Computer Interaction · Computer Science 2019-06-14 Jesse Vig

Token embeddings play a crucial role in language modeling but, despite this practical relevance, their theoretical understanding remains limited. Our paper addresses the gap by characterizing the structure of embeddings obtained via…

Machine Learning · Computer Science 2025-06-26 Diyuan Wu , Aleksandr Shevchenko , Samet Oymak , Marco Mondelli

To improve the robustness of transformer neural networks used for temporal-dynamics prediction of chaotic systems, we propose a novel attention mechanism called easy attention which we demonstrate in time-series reconstruction and…

Machine Learning · Computer Science 2025-06-05 Marcial Sanchis-Agudo , Yuning Wang , Roger Arnau , Luca Guastoni , Jasmin Lim , Karthik Duraisamy , Ricardo Vinuesa

Scaling language models to handle longer contexts introduces substantial memory challenges due to the growing cost of key-value (KV) caches. Motivated by the efficiency gains of hybrid models and the broad availability of pretrained large…

Computation and Language · Computer Science 2026-05-19 Xuan Zhang , Fengzhuo Zhang , Cunxiao Du , Chao Du , Tianyu Pang , Wei Gao , Min Lin

Transformers and deep state space models (SSMs) sit at opposite ends of a basic design choice: attention routes each query through a growing key-value (KV) cache by content-based matching at quadratic cost, while deep SSMs compress context…

Machine Learning · Computer Science 2026-05-26 Naoki Kiyohara , Harrison Bo Hua Zhu , Riccardo El Hassanin , Zhuo Sun , Wenlong Chen , Samir Bhatt , Yingzhen Li

Transformers' quadratic computational complexity limits their scalability despite remarkable performance. While linear attention reduces this to linear complexity, pre-training such models from scratch remains, in most cases, prohibitively…

Machine Learning · Computer Science 2025-10-13 Martin Benfeghoul , Teresa Delgado , Adnan Oomerjee , Haitham Bou Ammar , Jun Wang , Zafeirios Fountas

Lattices are an efficient and effective method to encode ambiguity of upstream systems in natural language processing tasks, for example to compactly capture multiple speech recognition hypotheses, or to represent multiple linguistic…

Computation and Language · Computer Science 2019-06-05 Matthias Sperber , Graham Neubig , Ngoc-Quan Pham , Alex Waibel

While Transformers have shown remarkable success in natural language processing, their attention mechanism's large memory requirements have limited their ability to handle longer contexts. Prior approaches, such as recurrent memory or…

Computation and Language · Computer Science 2023-11-21 Amirkeivan Mohtashami , Martin Jaggi

Transformer architectures have achieved state-of-the-art results on a variety of sequence modeling tasks. However, their attention mechanism comes with a quadratic complexity in sequence lengths, making the computational overhead…

Computation and Language · Computer Science 2022-06-03 Hao Peng , Jungo Kasai , Nikolaos Pappas , Dani Yogatama , Zhaofeng Wu , Lingpeng Kong , Roy Schwartz , Noah A. Smith

Recent advances in deep learning have mainly relied on Transformers due to their data dependency and ability to learn at scale. The attention module in these architectures, however, exhibits quadratic time and space in input size, limiting…

Machine Learning · Computer Science 2024-07-25 Ali Behrouz , Michele Santacatterina , Ramin Zabih

Large language models (LLMs) have emerged due to their capability to generate high-quality content across diverse contexts. To reduce their explosively increasing demands for computing resources, a mixture of experts (MoE) has emerged. The…

Hardware Architecture · Computer Science 2025-11-04 Sungmin Yun , Kwanhee Kyung , Juhwan Cho , Jaewan Choi , Jongmin Kim , Byeongho Kim , Sukhan Lee , Kyomin Sohn , Jung Ho Ahn

Time-series data in real-world settings typically exhibit long-range dependencies and are observed at non-uniform intervals. In these settings, traditional sequence-based recurrent models struggle. To overcome this, researchers often…

Machine Learning · Statistics 2025-01-14 Fernando Moreno-Pino , Álvaro Arroyo , Harrison Waldon , Xiaowen Dong , Álvaro Cartea

Attention based Transformer architecture has enabled significant advances in the field of natural language processing. In addition to new pre-training techniques, recent improvements crucially rely on working with a relatively larger…

Machine Learning · Computer Science 2020-02-18 Srinadh Bhojanapalli , Chulhee Yun , Ankit Singh Rawat , Sashank J. Reddi , Sanjiv Kumar

Multimodal learning has been lacking principled ways of combining information from different modalities and learning a low-dimensional manifold of meaningful representations. We study multimodal learning and sensor fusion from a latent…

Machine Learning · Computer Science 2019-04-24 Lijiang Guo

Large Language Models (LLMs) based on autoregressive, decoder-only Transformers generate text one token at a time, where a token represents a discrete unit of text. As each newly produced token is appended to the partial output sequence,…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-05-06 Dimitrios Kafetzis , Ramin Khalili , Iordanis Koutsopoulos

The self-attention mechanism traditionally relies on the softmax operator, necessitating positional embeddings like RoPE, or position biases to account for token order. But current methods using still face length generalisation challenges.…

Machine Learning · Computer Science 2025-05-21 Shawn Tan , Songlin Yang , Aaron Courville , Rameswar Panda , Yikang Shen

In-context learning is a remarkable property of transformers and has been the focus of recent research. An attention mechanism is a key component in transformers, in which an attention matrix encodes relationships between words in a…

Machine Learning · Computer Science 2025-04-01 Katsuyuki Hagiwara

Data mixing decides how to combine different sources or types of data and is a consequential problem throughout language model training. In pretraining, data composition is a key determinant of model quality; in continual learning and…

Computation and Language · Computer Science 2026-05-18 Michael Y. Hu , Apurva Gandhi , Kyunghyun Cho , Tal Linzen , Pratyusha Sharma

We introduce "talking-heads attention" - a variation on multi-head attention which includes linearprojections across the attention-heads dimension, immediately before and after the softmax operation.While inserting only a small number of…

Machine Learning · Computer Science 2020-03-06 Noam Shazeer , Zhenzhong Lan , Youlong Cheng , Nan Ding , Le Hou