English
Related papers

Related papers: STAR: An Efficient Softmax Engine for Attention Mo…

200 papers

Transformers are slow and memory-hungry on long sequences, since the time and memory complexity of self-attention are quadratic in sequence length. Approximate attention methods have attempted to address this problem by trading off model…

Machine Learning · Computer Science 2022-06-24 Tri Dao , Daniel Y. Fu , Stefano Ermon , Atri Rudra , Christopher Ré

Attention with bias, which extends standard attention by introducing prior knowledge as an additive bias matrix to the query-key scores, has been widely deployed in vision, language, protein-folding and other advanced scientific models,…

Machine Learning · Computer Science 2025-10-27 Haixu Wu , Minghao Guo , Yuezhou Ma , Yuanxu Sun , Jianmin Wang , Wojciech Matusik , Mingsheng Long

Inspired by foveal vision, hard attention models promise interpretability and parameter economy. However, existing models like the Recurrent Model of Visual Attention (RAM) and Deep Recurrent Attention Model (DRAM) failed to model the…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Pengcheng Pan , Yonekura Shogo , Yasuo Kuniyoshi

The transformer's attention mechanism has revolutionized AI and machine learning, with its efficient computation being crucial to its performance. However, calculating attention involves matrix operations interspersed with softmax…

Machine Learning · Computer Science 2025-05-21 Kosmas Alexandridis , Vasileios Titopoulos , Giorgos Dimitrakopoulos

Transformers have emerged as a powerful tool for natural language processing (NLP) and computer vision. Through the attention mechanism, these models have exhibited remarkable performance gains when compared to conventional approaches like…

Hardware Architecture · Computer Science 2024-07-18 Salma Afifi , Ishan Thakkar , Sudeep Pasricha

Recently, attention-based encoder-decoder (AED) models have shown state-of-the-art performance in automatic speech recognition (ASR). As the original AED models with global attentions are not capable of online inference, various online…

Audio and Speech Processing · Electrical Eng. & Systems 2021-01-15 Hyeonseung Lee , Woo Hyun Kang , Sung Jun Cheon , Hyeongju Kim , Nam Soo Kim

The attention mechanism has been proven effective on various visual tasks in recent years. In the semantic segmentation task, the attention mechanism is applied in various methods, including the case of both Convolution Neural Networks…

Computer Vision and Pattern Recognition · Computer Science 2024-05-10 Zheng Yuan , Jie Zhang , Yude Wang , Shiguang Shan , Xilin Chen

The unprecedented growth in the field of machine learning has led to the development of deep neuromorphic networks trained on labelled dataset with capability to mimic or even exceed human capabilities. However, for applications involving…

Emerging Technologies · Computer Science 2024-07-12 Arjun Tyagi , Shubham Sahay

Transformers have transformed the field of natural language processing. This performance is largely attributed to the use of stacked self-attention layers, each of which consists of matrix multiplies as well as softmax operations. As a…

Hardware Architecture · Computer Science 2021-03-18 Jacob R. Stevens , Rangharajan Venkatesan , Steve Dai , Brucek Khailany , Anand Raghunathan

This paper presents a novel architecture utilizing a 10T SRAM cell for XNOR-based in-memory computing, aimed at mitigating the extensive routing challenges typically encountered in conventional in-memory computing systems. By integrating a…

Hardware Architecture · Computer Science 2026-05-18 Narendra Singh Dhakad , Santosh Kumar Vishvakarma

Model merging is an efficient way of obtaining a multi-task model from several pretrained models without further fine-tuning, and it has gained attention in various domains, including natural language processing (NLP). Despite the…

Computation and Language · Computer Science 2025-02-17 Yu-Ang Lee , Ching-Yun Ko , Tejaswini Pedapati , I-Hsin Chung , Mi-Yen Yeh , Pin-Yu Chen

Efficient inference on GPUs using large language models remains challenging due to memory bandwidth limitations, particularly during data transfers between High Bandwidth Memory (HBM) and SRAM in attention computations. Approximate…

Machine Learning · Computer Science 2025-06-06 Nirav Koley , Prajwal Singhania , Abhinav Bhatele

Visual AutoRegressive (VAR) modeling has garnered significant attention for its innovative next-scale prediction paradigm. However, mainstream VAR paradigms attend to all tokens across historical scales at each autoregressive step. As the…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Zekun Li , Ning Wang , Tongxin Bai , Changwang Mei , Peisong Wang , Shuang Qiu , Jian Cheng

The attention module is the key component in Transformers. While the global attention mechanism offers high expressiveness, its excessive computational cost restricts its applicability in various scenarios. In this paper, we propose a novel…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Dongchen Han , Tianzhu Ye , Yizeng Han , Zhuofan Xia , Siyuan Pan , Pengfei Wan , Shiji Song , Gao Huang

Softmax Attention has a quadratic time complexity in sequence length, which becomes prohibitive to run at long contexts, even with highly optimized GPU kernels. For example, FlashAttention-2/3 (exact, GPU-optimized implementations of…

Machine Learning · Computer Science 2026-04-21 Sahil Joshi , Agniva Chowdhury , Amar Kanakamedala , Ekam Singh , Evan Tu , Anshumali Shrivastava

Various forms of sparse attention have been explored to mitigate the quadratic computational and memory cost of the attention mechanism in transformers. We study sparse transformers not through a lens of efficiency but rather in terms of…

Machine Learning · Computer Science 2025-06-19 Parikshit Ram , Kenneth L. Clarkson , Tim Klinger , Shashanka Ubaru , Alexander G. Gray

Efficiently supporting long context length is crucial for Transformer models. The quadratic complexity of the self-attention computation plagues traditional Transformers. Sliding window-based static sparse attention mitigates the problem by…

Hardware Architecture · Computer Science 2024-05-28 Zhenyu Bai , Pranav Dangi , Huize Li , Tulika Mitra

While linear attention reduces the quadratic complexity of standard Transformers to linear time, it often lags behind in expressivity due to the removal of softmax normalization. This omission eliminates \emph{global competition}, a…

Machine Learning · Computer Science 2026-02-03 Mingwei Xu , Xuan Lin , Xinnan Guo , Wanqing Xu , Wanyun Cui

Auto-regressive (AR) models, initially successful in language generation, have recently shown promise in visual generation tasks due to their superior sampling efficiency. Unlike image generation, video generation requires a substantially…

Computer Vision and Pattern Recognition · Computer Science 2025-05-22 Xuan Shen , Weize Ma , Yufa Zhou , Enhao Tang , Yanyue Xie , Zhengang Li , Yifan Gong , Quanyi Wang , Henghui Ding , Yiwei Wang , Yanzhi Wang , Pu Zhao , Jun Lin , Jiuxiang Gu

Computational workloads are growing exponentially, driving power consumption to unsustainable levels. Efficiently distributing large-scale networks is an NP-Complete problem equivalent to Boolean satisfiability (SAT), making it one of the…

Systems and Control · Electrical Eng. & Systems 2026-03-16 Everest Bloomer , Irem Didin , Ching-Yi Lin , Sahil Shah
‹ Prev 1 4 5 6 7 8 10 Next ›