English
Related papers

Related papers: Spark Transformer: Reactivating Sparsity in FFN an…

200 papers

The quadratic computational complexity of standard attention mechanisms presents a severe scalability bottleneck for LLMs in long-context scenarios. While hybrid attention mechanisms combining Full Attention (FA) and Sparse Attention (SA)…

Machine Learning · Computer Science 2026-04-10 Quantong Qiu , Zhiyi Hong , Yi Yang , Haitian Wang , Kebin Liu , Qingqing Dang , Juntao Li , Min Zhang

Transformers are state-of-the-art networks for most sequence processing tasks. However, the self-attention mechanism often used in Transformers requires large time windows for each computation step and thus makes them less suitable for…

Neural and Evolutionary Computing · Computer Science 2023-03-22 Nathan Leroux , Jan Finkbeiner , Emre Neftci

A recent empirical observation (Li et al., 2022b) of activation sparsity in MLP blocks offers an opportunity to drastically reduce computation costs for free. Although having attributed it to training dynamics, existing theoretical…

Machine Learning · Computer Science 2023-10-27 Ze Peng , Lei Qi , Yinghuan Shi , Yang Gao

Sparse neural networks have been widely applied to reduce the computational demands of training and deploying over-parameterized deep neural networks. For inference acceleration, methods that discover a sparse network from a pre-trained…

Machine Learning · Computer Science 2021-06-16 Shiwei Liu , Decebal Constantin Mocanu , Yulong Pei , Mykola Pechenizkiy

Spiking Neural Networks (SNNs) provide an energy-efficient deep learning option due to their unique spike-based event-driven (i.e., spike-driven) paradigm. In this paper, we incorporate the spike-driven paradigm into Transformer by the…

Neural and Evolutionary Computing · Computer Science 2023-07-06 Man Yao , Jiakui Hu , Zhaokun Zhou , Li Yuan , Yonghong Tian , Bo Xu , Guoqi Li

The attention mechanism is a fundamental component of the Transformer model, contributing to interactions among distinct tokens, in contrast to earlier feed-forward neural networks. In general, the attention scores are determined simply by…

Computation and Language · Computer Science 2024-10-11 Chuanyang Zheng , Yihang Gao , Han Shi , Jing Xiong , Jiankai Sun , Jingyao Li , Minbin Huang , Xiaozhe Ren , Michael Ng , Xin Jiang , Zhenguo Li , Yu Li

Architectural choices inside the Transformer feedforward network (FFN) block do not merely affect the block itself; they reshape the computations learned by the rest of the model. We study this effect in one-layer Transformers trained on…

Machine Learning · Computer Science 2026-05-18 Gabriel Smithline , Chris Mascioli

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

With the rise of Transformer models in NLP and CV domain, Multi-Head Attention has been proven to be a game-changer. However, its expensive computation poses challenges to the model throughput and efficiency, especially for the long…

Image and Video Processing · Electrical Eng. & Systems 2024-04-12 Jiing-Ping Wang , Ming-Guang Lin , An-Yeu , Wu

We present the Condensate Theorem: attention sparsity is a learned topological property, not an architectural constraint. Through empirical analysis of trained language models, we find that attention mass concentrates on a distinct…

Machine Learning · Computer Science 2026-02-11 Jorge L. Ruiz Williams

Spiking neural networks (SNNs) have garnered interest due to their energy efficiency and superior effectiveness on neuromorphic chips compared with traditional artificial neural networks (ANNs). One of the mainstream approaches to…

Neural and Evolutionary Computing · Computer Science 2024-04-29 Zhipeng Huang , Jianhao Ding , Zhiyu Pan , Haoran Li , Ying Fang , Zhaofei Yu , Jian K. Liu

Transformers have achieved remarkable successes across a wide range of applications, yet the theoretical foundation of their model efficiency remains underexplored. In this work, we investigate how the model parameters -- mainly attention…

Machine Learning · Computer Science 2025-10-07 Ruoxi Yu , Haotian Jiang , Jingpu Cheng , Penghao Yu , Qianxiao Li , Zhong Li

End-to-end model, especially Recurrent Neural Network Transducer (RNN-T), has achieved great success in speech recognition. However, transducer requires a great memory footprint and computing time when processing a long decoding sequence.…

Sound · Computer Science 2023-07-18 Xiaohui Zhang , Mangui Liang , Zhengkun Tian , Jiangyan Yi , Jianhua Tao

Sparse neural networks are becoming increasingly important as the field seeks to improve the performance of existing models by scaling them up, while simultaneously trying to reduce power consumption and computational footprint.…

Machine Learning · Computer Science 2021-06-08 Siddhant M. Jayakumar , Razvan Pascanu , Jack W. Rae , Simon Osindero , Erich Elsen

Self-attention serves as the core foundation of large-scale transformer pretraining, but its quadratic token interaction cost makes inference expensive. Replacing attention with simpler sequential modules is appealing, yet naive…

Machine Learning · Computer Science 2026-05-20 Yuxin Ren , Maxwell D Collins , Miao Hu , Huanrui Yang

We study two recurring phenomena in Transformer language models: massive activations, in which a small number of tokens exhibit extreme outliers in a few channels, and attention sinks, in which certain tokens attract disproportionate…

Artificial Intelligence · Computer Science 2026-03-06 Shangwen Sun , Alfredo Canziani , Yann LeCun , Jiachen Zhu

Transformers have achieved significant success across various domains, relying on self-attention to capture dependencies. However, the standard first-order attention mechanism is often limited by a low-rank bottleneck, struggling to capture…

Computation and Language · Computer Science 2025-12-05 Hanting Chen , Chong Zhu , Kai Han , Yuchuan Tian , Yuchen Liang , Tianyu Guo , Xinghao Chen , Dacheng Tao , Yunhe Wang

Sparse attention methods exploit the inherent sparsity in attention to speed up the prefilling phase of long-context inference, mitigating the quadratic complexity of full attention computation. While existing sparse attention methods rely…

Machine Learning · Computer Science 2025-05-27 Dan Peng , Zhihui Fu , Zewen Ye , Zhuoran Song , Jun Wang

The design of Large Language Models (LLMs) has long been hampered by a fundamental conflict within their core attention mechanism: its remarkable expressivity is built upon a computational complexity of O(H N^2) that grows quadratically…

Machine Learning · Computer Science 2025-12-01 Mingkuan Zhao , Wentao Hu , Jiayin Wang , Xin Lai , Tianchen Huang , Yuheng Min , Rui Yan , Xiaoyan Zhu

In the context of inverse problems $\bf y = Ax$, sparse recovery offers a powerful paradigm shift by enabling the stable solution of ill-posed or underdetermined systems through the exploitation of structure, particularly sparsity. Sparse…

Image and Video Processing · Electrical Eng. & Systems 2025-06-03 Di An , Dylan Poppert , Jiayue Li , Mark Foster , Trac D. Tran