English
Related papers

Related papers: ReduceFormer: Attention with Tensor Reduction by S…

200 papers

Transformer based models are increasingly being used in various domains including recommender systems (RS). Pretrained transformer models such as BERT have shown good performance at language modelling. With the greater ability to model…

Information Retrieval · Computer Science 2025-01-03 Uzma Mushtaque

Transformers are state-of-the-art models for a variety of sequence modeling tasks. At their core is an attention function which models pairwise interactions between the inputs at every timestep. While attention is powerful, it does not…

Computation and Language · Computer Science 2021-03-23 Hao Peng , Nikolaos Pappas , Dani Yogatama , Roy Schwartz , Noah A. Smith , Lingpeng Kong

While Transformer architectures have demonstrated impressive scalability across domains, they continue to face challenges in long-context reasoning, computational efficiency, and structural generalization - largely due to rigid layer…

Computation and Language · Computer Science 2025-10-03 Haochen You , Baojing Liu

This paper presents CLUSTERFORMER, a universal vision model that is based on the CLUSTERing paradigm with TransFORMER. It comprises two novel designs: 1. recurrent cross-attention clustering, which reformulates the cross-attention mechanism…

Computer Vision and Pattern Recognition · Computer Science 2023-10-09 James C. Liang , Yiming Cui , Qifan Wang , Tong Geng , Wenguan Wang , Dongfang Liu

Transformers have become central to natural language processing and large language models, but their deployment at scale faces three major challenges. First, the attention mechanism requires massive matrix multiplications and frequent…

Hardware Architecture · Computer Science 2026-01-22 Xiaoxuan Yang , Peilin Chen , Tergel Molom-Ochir , Yiran Chen

Accommodating long sequences efficiently in autoregressive Transformers, especially within an extended context window, poses significant challenges due to the quadratic computational complexity and substantial KV memory requirements…

Computation and Language · Computer Science 2024-06-25 Chao Lou , Zixia Jia , Zilong Zheng , Kewei Tu

To enhance the computational efficiency of quantized Transformers, we replace the dot-product and Softmax-based attention with an alternative mechanism involving addition and ReLU activation only. This side-steps the expansion to double…

Machine Learning · Computer Science 2025-10-02 Rickard Brännvall , Andrei Stoian

Transformer models have achieved remarkable success in sequential recommender systems (SRSs). However, computing the attention matrix in traditional dot-product attention mechanisms results in a quadratic complexity with sequence lengths,…

Information Retrieval · Computer Science 2024-11-05 Langming Liu , Xiangyu Zhao , Chi Zhang , Jingtong Gao , Wanyu Wang , Wenqi Fan , Yiqi Wang , Ming He , Zitao Liu , Qing Li

In recent years, the popular Transformer architecture has achieved great success in many application areas, including natural language processing and computer vision. Many existing works aim to reduce the computational and memory complexity…

Machine Learning · Computer Science 2023-09-20 Zhe Chen

Pairwise dot product-based attention allows Transformers to exchange information between tokens in an input-dependent way, and is key to their success across diverse applications in language and vision. However, a typical Transformer model…

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

We analyse the computational power of transformer encoders as sequence-to-sequence functions on vectors. We show that average hard attention can be used to simulate arithmetic circuits if they are given as an input to an encoder. The…

Computational Complexity · Computer Science 2026-05-07 Lena Ehrmuth , Laura Strieker

We propose a novel framework for producing a class of parameter and compute efficient models called AttentionLitesuitable for resource-constrained applications. Prior work has primarily focused on optimizing models either via knowledge…

Computer Vision and Pattern Recognition · Computer Science 2021-01-14 Souvik Kundu , Sairam Sundaresan

Attention based models such as Transformers involve pairwise interactions between data points, modeled with a learnable attention matrix. Importantly, this attention matrix is normalized with the SoftMax operator, which makes it row-wise…

Machine Learning · Computer Science 2022-01-25 Michael E. Sander , Pierre Ablin , Mathieu Blondel , Gabriel Peyré

Vision Transformers with various attention modules have demonstrated superior performance on vision tasks. While using sparsity-adaptive attention, such as in DAT, has yielded strong results in image classification, the key-value pairs…

Computer Vision and Pattern Recognition · Computer Science 2024-10-14 Nguyen Huu Bao Long , Chenyu Zhang , Yuzhi Shi , Tsubasa Hirakawa , Takayoshi Yamashita , Tohgoroh Matsui , Hironobu Fujiyoshi

The transformer architecture predominates across various models. As the heart of the transformer, attention has a computational complexity of $O(N^2)$, compared to $O(N)$ for linear transformations. When handling large sequence lengths,…

Machine Learning · Computer Science 2025-10-02 Jintao Zhang , Jia Wei , Haofeng Huang , Pengle Zhang , Jun Zhu , Jianfei Chen

The design choices in Transformer feed-forward neural networks have resulted in significant computational and parameter overhead. In this work, we emphasize the importance of hidden dimensions in designing lightweight FFNs, a factor often…

Computation and Language · Computer Science 2024-06-06 Tong Zheng , Bei Li , Huiwen Bao , Jiale Wang , Weiqiao Shan , Tong Xiao , Jingbo Zhu

Transformers excel across domains, yet their quadratic attention complexity poses a barrier to scaling. Random-feature attention, as in Performers, can reduce this cost to linear in the sequence length by approximating the softmax kernel…

Machine Learning · Computer Science 2026-03-05 Amirhossein Farzam , Hossein Mobahi , Nolan Andrew Miller , Luke Sernau

Linearization of attention using various kernel approximation and kernel learning techniques has shown promise. Past methods used a subset of combinations of component functions and weight matrices within the random feature paradigm. We…

Machine Learning · Computer Science 2025-09-24 Duke Nguyen , Du Yin , Aditya Joshi , Flora Salim

While transformers have begun to dominate many tasks in vision, applying them to large images is still computationally difficult. A large reason for this is that self-attention scales quadratically with the number of tokens, which in turn,…

Computer Vision and Pattern Recognition · Computer Science 2022-09-16 Daniel Bolya , Cheng-Yang Fu , Xiaoliang Dai , Peizhao Zhang , Judy Hoffman
‹ Prev 1 8 9 10 Next ›