English
Related papers

Related papers: Residual Stream Duality in Modern Transformer Arch…

200 papers

Transformer networks have achieved remarkable success across diverse domains, leveraging a variety of architectural innovations, including residual connections. However, traditional residual connections, which simply sum the outputs of…

Machine Learning · Computer Science 2025-07-25 Mike Heddes , Adel Javanmard , Kyriakos Axiotis , Gang Fu , MohammadHossein Bateni , Vahab Mirrokni

Transformer residual streams evolve by additive accumulation: each layer appends a feature update to a shared hidden state, but has no direct mechanism for replacing content that has become obsolete or conflicting. We introduce Deep Delta…

Machine Learning · Computer Science 2026-05-14 Yifan Zhang , Yifeng Liu , Mengdi Wang , Quanquan Gu

Attention Residuals replace standard additive residual connections with learned softmax attention over previous layer outputs, enabling selective cross-layer routing. However, standard Attention Residuals still attend over cumulative hidden…

Machine Learning · Computer Science 2026-05-20 Cheng Luo , Zefan Cai , Junjie Hu

Standard transformers entangle all computation in a single residual stream, obscuring which components perform which functions. We introduce the Dual-Stream Transformer, which decomposes the residual stream into two functionally distinct…

Computation and Language · Computer Science 2026-03-10 J. Clayton Kerce , Alexis Fox

When examined through the lens of their residual streams, a puzzling property emerges in transformer networks: residual contributions (e.g., attention heads) sometimes specialize in specific tasks or input attributes. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2025-04-15 Lorenzo Basile , Valentino Maiorca , Luca Bortolussi , Emanuele Rodolà , Francesco Locatello

Attention mechanisms have become a core component of deep learning models, with Channel Attention and Spatial Attention being the two most representative architectures. Current research on their fusion strategies primarily bifurcates into…

Computer Vision and Pattern Recognition · Computer Science 2026-01-26 Zhongming Liu , Bingbing Jiang

Linear attention offers a linear-time alternative to self-attention but often struggles to capture long-range patterns. We revisit linear attention through a prediction-correction lens and show that prevalent variants can be written as a…

Machine Learning · Computer Science 2025-10-01 Xunhao Lai , Jialiang Kang , Jianqiao Lu , Tong Lin , Pengyu Zhao

Many studies have been conducted to improve the efficiency of Transformer from quadric to linear. Among them, the low-rank-based methods aim to learn the projection matrices to compress the sequence length. However, the projection matrices…

Machine Learning · Computer Science 2022-11-30 Bosheng Qin , Juncheng Li , Siliang Tang , Yueting Zhuang

Transformer models have emerged as fundamental tools across various scientific and engineering disciplines, owing to their outstanding performance in diverse applications. Despite this empirical success, the theoretical foundations of…

Machine Learning · Computer Science 2026-04-14 Zhen Qin , Jinxin Zhou , Jiachen Jiang , Zhihui Zhu

Recently, Transformer-based architecture has been introduced into single image deraining task due to its advantage in modeling non-local information. However, existing approaches tend to integrate global features based on a dense…

Computer Vision and Pattern Recognition · Computer Science 2023-08-16 Zhentao Fan , Hongming Chen , Yufeng Li

Transformer is a ubiquitous model for natural language processing and has attracted wide attentions in computer vision. The attention maps are indispensable for a transformer model to encode the dependencies among input tokens. However,…

Machine Learning · Computer Science 2021-02-26 Yujing Wang , Yaming Yang , Jiangang Bai , Mingliang Zhang , Jing Bai , Jing Yu , Ce Zhang , Gao Huang , Yunhai Tong

The Transformer architecture has significantly advanced deep learning, particularly in natural language processing, by effectively managing long-range dependencies. However, as the demand for understanding complex relationships grows,…

Computation and Language · Computer Science 2024-06-18 Qian Chen , Wen Wang , Qinglin Zhang , Siqi Zheng , Shiliang Zhang , Chong Deng , Hai Yu , Jiaqing Liu , Yukun Ma , Chong Zhang

Transformers are built upon multi-head scaled dot-product attention and positional encoding, which aim to learn the feature representations and token dependencies. In this work, we focus on enhancing the distinctive representation by…

Computer Vision and Pattern Recognition · Computer Science 2022-07-12 Litao Yu , Jian Zhang

We propose a dual-stream multi-scale vision transformer (DS-MSHViT) architecture that processes RGB and optical flow inputs for efficient sewer defect classification. Unlike existing methods that combine the predictions of two separate…

Computer Vision and Pattern Recognition · Computer Science 2023-11-29 Abdullah Al Redwan Newaz , Mahdi Abdeldguerfi , Kendall N. Niles , Joe Tom

Transformer-based models have emerged as a leading architecture for natural language processing, natural language generation, and image generation tasks. A fundamental element of the transformer architecture is self-attention, which allows…

Machine Learning · Computer Science 2025-07-01 Venmugil Elango

Transformer-based object detectors often struggle with occlusions, fine-grained localization, and computational inefficiency caused by fixed queries and dense attention. We propose DAMM, Dual-stream Attention with Multi-Modal queries, a…

Computer Vision and Pattern Recognition · Computer Science 2025-08-08 Noreen Anwar , Guillaume-Alexandre Bilodeau , Wassim Bouachir

Transformer architectures are now central to sequence modeling tasks. At its heart is the attention mechanism, which enables effective modeling of long-term dependencies in a sequence. Recently, transformers have been successfully applied…

Computer Vision and Pattern Recognition · Computer Science 2022-06-16 Lin Zheng , Huijie Pan , Lingpeng Kong

Despite the remarkable progresses made in deep-learning based depth map super-resolution (DSR), how to tackle real-world degradation in low-resolution (LR) depth maps remains a major challenge. Existing DSR model is generally trained and…

Computer Vision and Pattern Recognition · Computer Science 2020-06-03 Xibin Song , Yuchao Dai , Dingfu Zhou , Liu Liu , Wei Li , Hongdng Li , Ruigang Yang

Neural sequence-to-sequence networks with attention have achieved remarkable performance for machine translation. One of the reasons for their effectiveness is their ability to capture relevant source-side contextual information at each…

Computation and Language · Computer Science 2018-10-02 Lesly Miculicich Werlen , Nikolaos Pappas , Dhananjay Ram , Andrei Popescu-Belis

Transformer networks have become the preferred architecture for many tasks due to their state-of-the-art performance. However, the optimal way to implement residual connections in Transformer, which are essential for effective training, is…

Computation and Language · Computer Science 2023-05-01 Shufang Xie , Huishuai Zhang , Junliang Guo , Xu Tan , Jiang Bian , Hany Hassan Awadalla , Arul Menezes , Tao Qin , Rui Yan
‹ Prev 1 2 3 10 Next ›