English
Related papers

Related papers: No Clustering, No Routing: How Transformers Actual…

200 papers

Recent work has questioned the importance of the Transformer's multi-headed attention for achieving high translation quality. We push further in this direction by developing a "hard-coded" attention variant without any learned parameters.…

Computation and Language · Computer Science 2020-05-05 Weiqiu You , Simeng Sun , Mohit Iyyer

The transformer is the most popular neural architecture for language modeling. The cornerstone of the transformer is its global attention mechanism, which lets the model aggregate information from all preceding tokens before generating the…

Computation and Language · Computer Science 2026-05-20 Jiaoda Li , Ryan Cotterell

Transformer has achieved great success in NLP. However, the quadratic complexity of the self-attention mechanism in Transformer makes it inefficient in handling long sequences. Many existing works explore to accelerate Transformers by…

Computation and Language · Computer Science 2021-09-03 Chuhan Wu , Fangzhao Wu , Tao Qi , Binxing Jiao , Daxin Jiang , Yongfeng Huang , Xing Xie

Rare words remain a critical bottleneck for speech-to-text systems. While direct fine-tuning improves recognition of target words, it often incurs high cost, catastrophic forgetting, and limited scalability. To address these challenges, we…

Audio and Speech Processing · Electrical Eng. & Systems 2025-12-29 Ruihao Jing , Cheng Gong , Yu Jiang , Boyu Zhu , Shansong Liu , Chi Zhang , Xiao-Lei Zhang , Xuelong Li

Multi-head attention advances neural machine translation by working out multiple versions of attention in different subspaces, but the neglect of semantic overlapping between subspaces increases the difficulty of translation and…

Computation and Language · Computer Science 2019-09-04 Shuhao Gu , Yang Feng

The transformer architecture is central to the success of modern Large Language Models (LLMs), in part due to its surprising ability to perform a wide range of tasks - including mathematical reasoning, memorization, and retrieval - using…

Machine Learning · Computer Science 2025-09-05 Yihe Dong , Lorenzo Noci , Mikhail Khodak , Mufan Li

Standard transformer architectures apply the same number of layers to every token regardless of contextual difficulty. We present Token-Selective Attention (TSA), a learned per-token gate on residual updates between consecutive transformer…

Machine Learning · Computer Science 2026-05-08 Ahmed Abdelmuniem Abdalla Mohammed

The quadratic computation complexity of self-attention has been a persistent challenge when applying Transformer models to vision tasks. Linear attention, on the other hand, offers a much more efficient alternative with its linear…

Computer Vision and Pattern Recognition · Computer Science 2023-09-04 Dongchen Han , Xuran Pan , Yizeng Han , Shiji Song , Gao Huang

Many common character-level, string-to string transduction tasks, e.g., grapheme-tophoneme conversion and morphological inflection, consist almost exclusively of monotonic transductions. However, neural sequence-to sequence models that use…

Computation and Language · Computer Science 2024-02-21 Shijie Wu , Ryan Cotterell

Mixture-of-Experts (MoE) networks have been proposed as an efficient way to scale up model capacity and implement conditional computing. However, the study of MoE components mostly focused on the feedforward layer in Transformer…

Computation and Language · Computer Science 2022-10-12 Xiaofeng Zhang , Yikang Shen , Zeyu Huang , Jie Zhou , Wenge Rong , Zhang Xiong

Recent work has shown that training loss scales as a power law with both model size and the number of tokens, and that achieving compute-optimal models requires scaling model size and token count together. However, these scaling laws assume…

Machine Learning · Computer Science 2025-07-04 Aurko Roy , Timothy Chou , Sai Surya Duvvuri , Sijia Chen , Jiecao Yu , Xiaodong Wang , Manzil Zaheer , Rohan Anil

Message Passing Neural Networks have recently become the most popular approach to graph machine learning tasks; however, their receptive field is limited by the number of message passing layers. To increase the receptive field, Graph…

Machine Learning · Computer Science 2026-04-10 Oleg Platonov , Liudmila Prokhorenkova

This paper investigates the limitations of the normalization in attention mechanisms. We begin with a theoretical framework that enables the identification of the model's selective ability and the geometric separation involved in token…

Machine Learning · Computer Science 2025-10-21 Timur Mudarisov , Mikhail Burtsev , Tatiana Petrova , Radu State

Transformer-based approaches have been successfully used to obtain state-of-the-art accuracy on natural language processing (NLP) tasks with semi-structured tables. These model architectures are typically deep, resulting in slow training…

Computation and Language · Computer Science 2021-06-02 Syrine Krichene , Thomas Müller , Julian Martin Eisenschlos

Transformer-based models, even though achieving super-human performance on several downstream tasks, are often regarded as a black box and used as a whole. It is still unclear what mechanisms they have learned, especially their core module:…

Computation and Language · Computer Science 2023-10-17 Chong Li , Shaonan Wang , Yunhao Zhang , Jiajun Zhang , Chengqing Zong

Training a unified multilingual model promotes knowledge transfer but inevitably introduces negative interference. Language-specific modeling methods show promise in reducing interference. However, they often rely on heuristics to…

Computation and Language · Computer Science 2024-04-18 Shaomu Tan , Di Wu , Christof Monz

The rapid progress seen in terms of large-scale generative AI is largely based on the attention mechanism. It is conversely non-trivial to conceive small-scale applications for which attention-based architectures outperform traditional…

Machine Learning · Computer Science 2025-08-07 Claudius Gros

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

The goal of this paper is to report certain scientific discoveries about a Seq2Seq model. It is known that analyzing the behavior of RNN-based models at the neuron level is considered a more challenging task than analyzing a DNN or CNN…

Neural and Evolutionary Computing · Computer Science 2023-03-28 Yi-Ting Lee , Da-Yi Wu , Chih-Chun Yang , Shou-De Lin

The Transformer is a fully attention-based alternative to recurrent networks that has achieved state-of-the-art results across a range of NLP tasks. In this paper, we analyze the structure of attention in a Transformer language model, the…

Computation and Language · Computer Science 2019-06-20 Jesse Vig , Yonatan Belinkov