English
Related papers

Related papers: Dynamic N:M Fine-grained Structured Sparse Attenti…

200 papers

Transformers are the mainstream of NLP applications and are becoming increasingly popular in other domains such as Computer Vision. Despite the improvements in model quality, the enormous computation costs make Transformers difficult at…

Machine Learning · Computer Science 2021-10-22 Liu Liu , Zheng Qu , Zhaodong Chen , Yufei Ding , Yuan Xie

Diffusion transformers have achieved remarkable success in high-quality video generation, yet their reliance on spatiotemporal 3D full attention incurs prohibitive computational cost due to the quadratic complexity of attention. Block…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Jie Hu , Zixiang Gao , Yutong He , Kun Yuan

Transformers are considered one of the most important deep learning models since 2018, in part because it establishes state-of-the-art (SOTA) records and could potentially replace existing Deep Neural Networks (DNNs). Despite the remarkable…

Machine Learning · Computer Science 2022-08-23 Hongwu Peng , Shaoyi Huang , Shiyang Chen , Bingbing Li , Tong Geng , Ang Li , Weiwen Jiang , Wujie Wen , Jinbo Bi , Hang Liu , Caiwen Ding

The demand for efficient processing of deep neural networks (DNNs) on embedded devices is a significant challenge limiting their deployment. Exploiting sparsity in the network's feature maps is one of the ways to reduce its inference…

Computer Vision and Pattern Recognition · Computer Science 2023-09-28 Matteo Grimaldi , Darshan C. Ganji , Ivan Lazarevich , Sudhakar Sah

While diffusion language models (DLMs) offer a promising alternative to autoregressive models (ARs), existing open-source DLMs suffer from high inference latency. This bottleneck is mainly due to the attention's quadratic complexity with…

Computation and Language · Computer Science 2025-09-30 Zeqing Wang , Gongfan Fang , Xinyin Ma , Xingyi Yang , Xinchao Wang

Deep learning demonstrates effectiveness across a wide range of tasks. However, the dense and over-parameterized nature of these models results in significant resource consumption during deployment. In response to this issue, weight…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-03-05 Cong Ma , Du Wu , Zhelang Deng , Jiang Chen , Xiaowen Huang , Jintao Meng , Wenxi Zhu , Bingqiang Wang , Amelie Chi Zhou , Peng Chen , Minwen Deng , Yanjie Wei , Shengzhong Feng , Yi Pan

Unstructured pruning reduces the memory footprint in deep neural networks (DNNs). Recently, researchers proposed different types of structural pruning intending to reduce also the computation complexity. In this work, we first suggest a new…

Artificial Intelligence · Computer Science 2021-10-22 Itay Hubara , Brian Chmiel , Moshe Island , Ron Banner , Seffi Naor , Daniel Soudry

Long-sequence processing is a critical capability for modern large language models. However, the self-attention mechanism in the standard Transformer architecture faces severe computational and memory bottlenecks when processing long…

Computation and Language · Computer Science 2025-09-30 Weilin Zhao , Zihan Zhou , Zhou Su , Chaojun Xiao , Yuxuan Li , Yanghao Li , Yudi Zhang , Weilun Zhao , Zhen Li , Yuxiang Huang , Ao Sun , Xu Han , Zhiyuan Liu

Sparse training is one of the promising techniques to reduce the computational cost of DNNs while retaining high accuracy. In particular, N:M fine-grained structured sparsity, where only N out of consecutive M elements can be nonzero, has…

Machine Learning · Computer Science 2023-09-25 Chao Fang , Wei Sun , Aojun Zhou , Zhongfeng Wang

Sparsity has become one of the promising methods to compress and accelerate Deep Neural Networks (DNNs). Among different categories of sparsity, structured sparsity has gained more attention due to its efficient execution on modern…

Machine Learning · Computer Science 2022-09-19 Sheng-Chun Kao , Amir Yazdanbakhsh , Suvinay Subramanian , Shivani Agrawal , Utku Evci , Tushar Krishna

In trained deep neural networks, unstructured pruning can reduce redundant weights to lower storage cost. However, it requires the customization of hardwares to speed up practical inference. Another trend accelerates sparse model inference…

Computer Vision and Pattern Recognition · Computer Science 2020-10-30 Zhuliang Yao , Shijie Cao , Wencong Xiao , Chen Zhang , Lanshun Nie

The increasing demand for long-context modeling in large language models (LLMs) is bottlenecked by the quadratic complexity of the standard self-attention mechanism. The community has proposed sparse attention to mitigate this issue.…

Artificial Intelligence · Computer Science 2025-11-18 Jingze Shi , Yifan Wu , Yiran Peng , Bingheng Wu , Liangdong Wang , Guang Liu , Yuyu Luo

Transformer-based language models have found many diverse applications requiring them to process sequences of increasing length. For these applications, the causal self-attention -- which is the only component scaling quadratically w.r.t.…

Machine Learning · Computer Science 2023-06-05 Matteo Pagliardini , Daniele Paliotta , Martin Jaggi , François Fleuret

Long-context understanding is crucial for many NLP applications, yet transformers struggle with efficiency due to the quadratic complexity of self-attention. Sparse attention methods alleviate this cost but often impose static, predefined…

Computation and Language · Computer Science 2025-06-16 Hanzhi Zhang , Heng Fan , Kewei Sha , Yan Huang , Yunhe Feng

The Transformer has been an indispensable staple in deep learning. However, for real-life applications, it is very challenging to deploy efficient Transformers due to immense parameters and operations of models. To relieve this burden,…

Hardware Architecture · Computer Science 2022-11-01 Chao Fang , Aojun Zhou , Zhongfeng Wang

Deep Learning (DL) has achieved unprecedented success in various application domains. Meanwhile, model pruning has emerged as a viable solution to reduce the footprint of DL models in mobile applications, without compromising their…

Hardware Architecture · Computer Science 2024-01-17 Christodoulos Peltekis , Vasileios Titopoulos , Chrysostomos Nicopoulos , Giorgos Dimitrakopoulos

Long-context modeling is crucial for next-generation language models, yet the high computational cost of standard attention mechanisms poses significant computational challenges. Sparse attention offers a promising direction for improving…

The success of DNN pruning has led to the development of energy-efficient inference accelerators that support pruned models with sparse weight and activation tensors. Because the memory layouts and dataflows in these architectures are…

Neural and Evolutionary Computing · Computer Science 2020-09-24 Dingqing Yang , Amin Ghasemazar , Xiaowei Ren , Maximilian Golub , Guy Lemieux , Mieszko Lis

Existing pruning methods utilize the importance of each weight based on specified criteria only when searching for a sparse structure but do not utilize it during training. In this work, we propose a novel approach - \textbf{M}agnitude…

Computer Vision and Pattern Recognition · Computer Science 2023-06-09 Jihye Back , Namhyuk Ahn , Jangho Kim

The rise of Deep Neural Networks (DNNs) has led to an increase in model size and complexity, straining the memory capacity of GPUs. Sparsity in DNNs, characterized as structural or ephemeral, has gained attention as a solution. This work…

Machine Learning · Computer Science 2023-11-30 Daniel Barley , Holger Fröning
‹ Prev 1 2 3 10 Next ›