English
Related papers

Related papers: Attention Link: An Efficient Attention-Based Low R…

200 papers

Attentional sequence-to-sequence models have become the new standard for machine translation, but one challenge of such models is a significant increase in training and decoding cost compared to phrase-based systems. Here, we focus on…

Computation and Language · Computer Science 2017-05-08 Jacob Devlin

Key-Value (KV) cache memory and bandwidth increasingly dominate large language model inference cost in long-context and long-generation regimes. Architectures such as multi-head latent attention (MLA) and hybrid sliding-window attention…

Computation and Language · Computer Science 2026-04-08 Zhen Cheng , Hao-Bo Yang , Wan-Yi Huang , Jin-Long Li

Large Language Models (LLMs) have emerged as a pivotal research area, yet the attention module remains a critical bottleneck in LLM inference, even with techniques like KVCache to mitigate redundant computations. While various top-$k$…

This work presents an analysis of the effectiveness of using standard shallow feed-forward networks to mimic the behavior of the attention mechanism in the original Transformer model, a state-of-the-art architecture for sequence-to-sequence…

Computation and Language · Computer Science 2024-02-06 Vukasin Bozic , Danilo Dordevic , Daniele Coppola , Joseph Thommes , Sidak Pal Singh

Transformer-based deep learning models have achieved state-of-the-art performance across numerous language and vision tasks. While the self-attention mechanism, a core component of transformers, has proven capable of handling complex data…

Machine Learning · Computer Science 2025-08-05 Laziz Abdullaev , Tan M. Nguyen

The Transformer, with its scaled dot-product attention mechanism, has become a foundational architecture in modern AI. However, this mechanism is computationally intensive and incurs substantial energy costs. We propose a new Transformer…

Machine Learning · Computer Science 2025-08-07 Xin Gao , Xingming Xu , Shirin Amiraslani , Hong Xu

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

In this paper, we extend an attention-based neural machine translation (NMT) model by allowing it to access an entire training set of parallel sentence pairs even after training. The proposed approach consists of two stages. In the first…

Computation and Language · Computer Science 2018-03-09 Jiatao Gu , Yong Wang , Kyunghyun Cho , Victor O. K. Li

With parallelizable attention networks, the neural Transformer is very fast to train. However, due to the auto-regressive architecture and self-attention in the decoder, the decoding procedure becomes slow. To alleviate this issue, we…

Computation and Language · Computer Science 2018-05-08 Biao Zhang , Deyi Xiong , Jinsong Su

Identifying words that impact a task's performance more than others is a challenge in natural language processing. Transformers models have recently addressed this issue by incorporating an attention mechanism that assigns greater attention…

Computation and Language · Computer Science 2023-03-15 Neşet Özkan Tan , Alex Yuxuan Peng , Joshua Bensemann , Qiming Bao , Tim Hartill , Mark Gahegan , Michael Witbrock

Consistency is a key requirement of high-quality translation. It is especially important to adhere to pre-approved terminology and adapt to corrected translations in domain-specific projects. Machine translation (MT) has achieved…

Computation and Language · Computer Science 2023-05-10 Yasmin Moslem , Rejwanul Haque , John D. Kelleher , Andy Way

GPT-2 and BERT demonstrate the effectiveness of using pre-trained language models (LMs) on various natural language processing tasks. However, LM fine-tuning often suffers from catastrophic forgetting when applied to resource-rich tasks. In…

Computation and Language · Computer Science 2022-06-22 Jiacheng Yang , Mingxuan Wang , Hao Zhou , Chengqi Zhao , Yong Yu , Weinan Zhang , Lei Li

Large language models (LLMs) now support extremely long context windows, but the quadratic complexity of vanilla attention results in significantly long Time-to-First-Token (TTFT) latency. Existing approaches to address this complexity…

Computation and Language · Computer Science 2025-09-04 Qianchao Zhu , Jiangfei Duan , Chang Chen , Siran Liu , Guanyu Feng , Xin Lv , Xiao Chuanfu , Dahua Lin , Chao Yang

Transformer models typically calculate attention matrices using dot products, which have limitations when capturing nonlinear relationships between embedding vectors. We propose Neural Attention, a technique that replaces dot products with…

Machine Learning · Computer Science 2025-11-10 Andrew DiGiugno , Ausif Mahmood

Scarcity of parallel sentence-pairs poses a significant hurdle for training high-quality Neural Machine Translation (NMT) models in bilingually low-resource scenarios. A standard approach is transfer learning, which involves taking a model…

Computation and Language · Computer Science 2020-10-13 Fahimeh Saleh , Wray Buntine , Gholamreza Haffari

Very recently, a variety of vision transformer architectures for dense prediction tasks have been proposed and they show that the design of spatial attention is critical to their success in these tasks. In this work, we revisit the design…

Computer Vision and Pattern Recognition · Computer Science 2021-10-01 Xiangxiang Chu , Zhi Tian , Yuqing Wang , Bo Zhang , Haibing Ren , Xiaolin Wei , Huaxia Xia , Chunhua Shen

As training billion-scale transformers becomes increasingly common, employing multiple distributed GPUs along with parallel training methods has become a standard practice. However, existing transformer designs suffer from significant…

Machine Learning · Computer Science 2025-12-09 Gyudong Kim , Hyukju Na , Jin Hyeon Kim , Hyunsung Jang , Jaemin Park , Jaegi Hwang , Namkoo Ha , Seungryong Kim , Young Geun Kim

Transformer architectures are the backbone of the modern AI revolution. However, they are based on simply stacking the same blocks in dozens of layers and processing information sequentially from one block to another. In this paper, we…

Computation and Language · Computer Science 2024-12-24 Prateek Verma , Mert Pilanci

Many document-level neural machine translation (NMT) systems have explored the utility of context-aware architecture, usually requiring an increasing number of parameters and computational complexity. However, few attention is paid to the…

Computation and Language · Computer Science 2020-09-22 Pei Zhang , Boxing Chen , Niyu Ge , Kai Fan

Designing a single neural network architecture that performs competitively across a range of molecule property prediction tasks remains largely an open challenge, and its solution may unlock a widespread use of deep learning in the drug…

Machine Learning · Computer Science 2021-02-10 Łukasz Maziarka , Tomasz Danel , Sławomir Mucha , Krzysztof Rataj , Jacek Tabor , Stanisław Jastrzębski