English
Related papers

Related papers: Hybrid Linear Attention Done Right: Efficient Dist…

200 papers

Non-hierarchical sparse attention Transformer-based models, such as Longformer and Big Bird, are popular approaches to working with long documents. There are clear benefits to these approaches compared to the original Transformer in terms…

Computation and Language · Computer Science 2022-10-12 Ilias Chalkidis , Xiang Dai , Manos Fergadiotis , Prodromos Malakasiotis , Desmond Elliott

Transformers have become the de facto architecture for a wide range of machine learning tasks, particularly in large language models (LLMs). Despite their remarkable performance, many challenges remain in training deep transformer networks,…

Computation and Language · Computer Science 2025-12-09 Zhijian Zhuo , Yutao Zeng , Ya Wang , Sijun Zhang , Jian Yang , Xiaoqing Li , Xun Zhou , Jinwen Ma

Linear RNN architectures, like Mamba, can be competitive with Transformer models in language modeling while having advantageous deployment characteristics. Given the focus on training large-scale Transformer models, we consider the…

Machine Learning · Computer Science 2025-06-30 Junxiong Wang , Daniele Paliotta , Avner May , Alexander M. Rush , Tri Dao

Converting a pretrained Transformer into a more efficient hybrid model through distillation offers a promising approach to reducing inference costs. However, achieving high-quality generation in distilled models requires careful joint…

Computation and Language · Computer Science 2026-03-30 Juan Gabriel Kostelec , Xiang Wang , Axel Laborieux , Christos Sourmpis , Qinghai Guo

Although transformer architectures have achieved state-of-the-art performance across diverse domains, their quadratic computational complexity with respect to sequence length remains a significant bottleneck, particularly for…

Computation and Language · Computer Science 2025-11-05 Zeyu Liu , Souvik Kundu , Lianghao Jiang , Anni Li , Srikanth Ronanki , Sravan Bodapati , Gourav Datta , Peter A. Beerel

The attention mechanism in Transformers is an important primitive for accurate and scalable sequence modeling. Its quadratic-compute and linear-memory complexity however remain significant bottlenecks. Linear attention and state-space…

Machine Learning · Computer Science 2026-03-03 Han Guo , Songlin Yang , Tarushii Goel , Eric P. Xing , Tri Dao , Yoon Kim

Transformer-based methods have demonstrated excellent performance on super-resolution visual tasks, surpassing conventional convolutional neural networks. However, existing work typically restricts self-attention computation to…

Computer Vision and Pattern Recognition · Computer Science 2024-05-09 Shu-Chuan Chu , Zhi-Chao Dou , Jeng-Shyang Pan , Shaowei Weng , Junbao Li

Standard Mixture-of-Experts (MoE) transformers route tokens to expert subnetworks within each layer, but the layer structure itself remains monolithic. We introduce Mixture of Layers (MoL), which replaces full-width transformer blocks…

Machine Learning · Computer Science 2026-05-12 Ivan Ternovtsii , Yurii Bilak

Hyperspectral image (HSI) denoising is critical for the effective analysis and interpretation of hyperspectral data. However, simultaneously modeling global and local features is rarely explored to enhance HSI denoising. In this letter, we…

Image and Video Processing · Electrical Eng. & Systems 2024-03-18 Shuai Hu , Feng Gao , Xiaowei Zhou , Junyu Dong , Qian Du

This work introduces Hybrid Sparse Attention (HySparse), a new architecture that interleaves each full attention layer with several sparse attention layers. While conceptually simple, HySparse strategically derives each sparse layer's token…

Computation and Language · Computer Science 2026-02-04 Yizhao Gao , Jianyu Wei , Qihao Zhang , Yu Cheng , Shimao Chen , Zhengju Tang , Zihan Jiang , Yifan Song , Hailin Zhang , Liang Zhao , Bo Yang , Gang Wang , Shijie Cao , Fuli Luo

Transformers have become the de facto standard for a wide range of tasks, from image classification to physics simulations. Despite their impressive performance, the quadratic complexity of standard Transformers in both memory and time with…

Computer Vision and Pattern Recognition · Computer Science 2025-07-04 Alex Colagrande , Paul Caillon , Eva Feillet , Alexandre Allauzen

Scaling sequence length has become a critical demand in the era of large language models. However, existing methods struggle with either computational complexity or model expressivity, rendering the maximum sequence length restricted. To…

Computation and Language · Computer Science 2023-07-20 Jiayu Ding , Shuming Ma , Li Dong , Xingxing Zhang , Shaohan Huang , Wenhui Wang , Nanning Zheng , Furu Wei

In Transformer-based architectures, the attention mechanism is inherently permutation-invariant with respect to the input sequence's tokens. To impose sequential order, token positions are typically encoded using a scheme with either fixed…

Machine Learning · Computer Science 2023-10-31 Giorgio Angelotti

Transformer-based models have emerged as one of the most widely used architectures for natural language processing, natural language generation, and image generation. The size of the state-of-the-art models has increased steadily reaching…

Hardware Architecture · Computer Science 2025-01-15 Rya Sanovar , Srikant Bharadwaj , Renee St. Amant , Victor Rühle , Saravan Rajmohan

Transformer architectures have achieved state-of-the-art performance across natural language tasks, yet they fundamentally misrepresent the hierarchical nature of human language by processing text as flat token sequences. This results in…

Computation and Language · Computer Science 2025-09-26 Ayan Sar , Sampurna Roy , Kanav Gupta , Anurag Kaushish , Tanupriya Choudhury , Abhijit Kumar

Since the introduction of the Transformer architecture for large language models, the softmax-based attention layer has faced increasing scrutinity due to its quadratic-time computational complexity. Attempts have been made to replace it…

Machine Learning · Computer Science 2026-02-02 Robert Forchheimer

Vision-Language Models (VLMs) are increasingly tasked with ultra-long multimodal understanding. While linear architectures offer constant computation and memory footprints, they often struggle with high-frequency visual perception compared…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Hongyuan Tao , Bencheng Liao , Shaoyu Chen , Haoran Yin , Qian Zhang , Wenyu Liu , Xinggang Wang

The encoder-decoder is the typical framework for Neural Machine Translation (NMT), and different structures have been developed for improving the translation performance. Transformer is one of the most promising structures, which can…

Computation and Language · Computer Science 2018-12-11 Kaitao Song , Xu Tan , Furong Peng , Jianfeng Lu

Human Activity Recognition (HAR) using wearable sensor data has become a central task in mobile computing, healthcare, and human-computer interaction. Despite the success of traditional deep learning models such as CNNs and RNNs, they often…

Machine Learning · Computer Science 2025-05-27 Yunbo Liu , Xukui Qin , Yifan Gao , Xiang Li , Chengwei Feng

The WuNeng architecture introduces a novel approach to enhancing the expressivity and power of large language models by integrating recurrent neural network (RNN)-based RWKV-7 with advanced attention mechanisms, prioritizing heightened…

Computation and Language · Computer Science 2025-04-29 Liu Xiao , Li Zhiyuan , Lin Yueyu