English
Related papers

Related papers: Improving Transformers with Probabilistic Attentio…

200 papers

Transformer model with multi-head attention requires caching intermediate results for efficient inference in generation tasks. However, cache brings new memory-related costs and prevents leveraging larger batch size for faster speed. We…

Computation and Language · Computer Science 2021-06-15 Yu Yan , Jiusheng Chen , Weizhen Qi , Nikhil Bhendawade , Yeyun Gong , Nan Duan , Ruofei Zhang

The Transformer architecture has revolutionized deep learning through its Self-Attention mechanism, which effectively captures contextual information. However, the memory footprint of Self-Attention presents significant challenges for…

Computer Vision and Pattern Recognition · Computer Science 2024-08-29 Zohaib Khan , Muhammad Khaquan , Omer Tafveez , Burhanuddin Samiwala , Agha Ali Raza

While Transformer self-attention offers strong parallelism, the Key-Value (KV) cache grows linearly with sequence length and becomes a bottleneck for inference efficiency. Multi-head latent attention was recently developed to compress the…

Machine Learning · Computer Science 2025-11-04 Keqi Deng , Philip C. Woodland

Multi-head attention layers, as used in the Transformer neural sequence model, are a powerful alternative to RNNs for moving information across and between sequences. While training these layers is generally fast and simple, due to…

Neural and Evolutionary Computing · Computer Science 2019-11-07 Noam Shazeer

Transformers are widely used in natural language processing, where they consistently achieve state-of-the-art performance. This is mainly due to their attention-based architecture, which allows them to model rich linguistic relations…

Computation and Language · Computer Science 2022-11-29 Nikolaos Mylonas , Ioannis Mollas , Grigorios Tsoumakas

The advent of Transformers marked a significant breakthrough in sequence modelling, providing a highly performant architecture capable of leveraging GPU parallelism. However, Transformers are computationally expensive at inference time,…

Machine Learning · Computer Science 2024-05-29 Leo Feng , Frederick Tung , Hossein Hajimirsadeghi , Mohamed Osama Ahmed , Yoshua Bengio , Greg Mori

The training and generalization dynamics of the Transformer's core mechanism, namely the Attention mechanism, remain under-explored. Besides, existing analyses primarily focus on single-head attention. Inspired by the demonstrated benefits…

Machine Learning · Computer Science 2024-10-15 Puneesh Deora , Rouzbeh Ghaderi , Hossein Taheri , Christos Thrampoulidis

Transformer models face scalability challenges in causal language modeling (CLM) due to inefficient memory allocation for growing key-value (KV) caches, which strains compute and storage resources. Existing methods like Grouped Query…

Computation and Language · Computer Science 2025-06-17 Guanghui Song , Dongping Liao , Yiren Zhao , Kejiang Ye , Cheng-zhong Xu , Xitong Gao

Multi-head, key-value attention is the backbone of the widely successful Transformer model and its variants. This attention mechanism uses multiple parallel key-value attention blocks (called heads), each performing two fundamental…

Machine Learning · Computer Science 2022-02-15 Sarthak Mittal , Sharath Chandra Raparthy , Irina Rish , Yoshua Bengio , Guillaume Lajoie

The attention mechanism has been the core component in modern transformer architectures. However, the computation of standard full attention scales quadratically with the sequence length, serving as a major bottleneck in long-context…

Computation and Language · Computer Science 2026-04-28 Yusheng Zhao , Hourun Li , Bohan Wu , Yichun Yin , Lifeng Shang , Jingyang Yuan , Meng Zhang , Ming Zhang

Self-attention in Transformers is typically implemented as $\mathrm{softmax}(QK^\top/\sqrt{d})V$, where $Q=XW_Q$, $K=XW_K$, and $V=XW_V$ are learned linear projections of the input $X$. We ask whether these learned projections are…

Machine Learning · Computer Science 2026-05-05 Debarshi Kundu , Archisman Ghosh , Swaroop Ghosh , Vasant Honavar

Transformers have revolutionized deep learning in numerous fields, including natural language processing, computer vision, and audio processing. Their strength lies in their attention mechanism, which allows for the discovering of complex…

Machine Learning · Computer Science 2024-04-02 Uladzislau Yorsh , Martin Holeňa , Ondřej Bojar , David Herel

Multi-layer models with multiple attention heads per layer provide superior translation quality compared to simpler and shallower models, but determining what source context is most relevant to each target word is more challenging as a…

Computation and Language · Computer Science 2019-02-01 Thomas Zenkel , Joern Wuebker , John DeNero

Vision Transformers (ViTs) have been shown to enhance visual recognition through modeling long-range dependencies with multi-head self-attention (MHSA), which is typically formulated as Query-Key-Value computation. However, the attention…

Computer Vision and Pattern Recognition · Computer Science 2023-11-28 Chongjian Ge , Xiaohan Ding , Zhan Tong , Li Yuan , Jiangliu Wang , Yibing Song , Ping Luo

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

Key-value (KV) caching plays an essential role in accelerating decoding for transformer-based autoregressive large language models (LLMs). However, the amount of memory required to store the KV cache can become prohibitive at long sequence…

Machine Learning · Computer Science 2024-05-22 William Brandon , Mayank Mishra , Aniruddha Nrusimha , Rameswar Panda , Jonathan Ragan Kelly

Transformer-based models have brought a radical change to neural machine translation. A key feature of the Transformer architecture is the so-called multi-head attention mechanism, which allows the model to focus simultaneously on different…

Computation and Language · Computer Science 2020-10-06 Alessandro Raganato , Yves Scherrer , Jörg Tiedemann

Multi-head attention plays a crucial role in the recent success of Transformer models, which leads to consistent performance improvements over conventional attention in various applications. The popular belief is that this effectiveness…

Computation and Language · Computer Science 2021-06-18 Liyuan Liu , Jialu Liu , Jiawei Han

The attention mechanism is the primary component of the transformer architecture; it has led to significant advancements in deep learning spanning many domains and covering multiple tasks. In computer vision, the attention mechanism was…

Computer Vision and Pattern Recognition · Computer Science 2025-05-05 Abdullah Nazhat Abdullah , Tarkan Aydin

Central to the success of Transformers is the attention block, which effectively models global dependencies among input tokens associated to a dataset. However, we theoretically demonstrate that standard attention mechanisms in transformers…

Machine Learning · Computer Science 2026-03-31 Hemanth Saratchandran