English
Related papers

Related papers: Beyond Linearity in Attention Projections: The Cas…

200 papers

We argue that Transformers are essentially graph-to-graph models, with sequences just being a special case. Attention weights are functionally equivalent to graph edges. Our Graph-to-Graph Transformer architecture makes this ability…

Computation and Language · Computer Science 2023-10-30 James Henderson , Alireza Mohammadshahi , Andrei C. Coman , Lesly Miculicich

With parallelizable attention networks, the neural Transformer is very fast to train. However, due to the auto-regressive architecture and self-attention in the decoder, the decoding procedure becomes slow. To alleviate this issue, we…

Computation and Language · Computer Science 2018-05-08 Biao Zhang , Deyi Xiong , Jinsong Su

Multi-query attention (MQA), which only uses a single key-value head, drastically speeds up decoder inference. However, MQA can lead to quality degradation, and moreover it may not be desirable to train a separate model just for faster…

Computation and Language · Computer Science 2023-12-27 Joshua Ainslie , James Lee-Thorp , Michiel de Jong , Yury Zemlyanskiy , Federico Lebrón , Sumit Sanghai

Widely adopted in modern Vision Transformer designs, Softmax attention can effectively capture long-range visual information; however, it incurs excessive computational cost when dealing with high-resolution inputs. In contrast, linear…

Computer Vision and Pattern Recognition · Computer Science 2024-12-10 Dongchen Han , Yifan Pu , Zhuofan Xia , Yizeng Han , Xuran Pan , Xiu Li , Jiwen Lu , Shiji Song , Gao Huang

Transformers have revolutionized deep learning in numerous fields, including natural language processing, computer vision, and audio processing. Their strength lies in their attention mechanism, which allows for the discovering of complex…

Machine Learning · Computer Science 2024-04-02 Uladzislau Yorsh , Martin Holeňa , Ondřej Bojar , David Herel

The Transformer architecture has revolutionized deep learning through its Self-Attention mechanism, which effectively captures contextual information. However, the memory footprint of Self-Attention presents significant challenges for…

Computer Vision and Pattern Recognition · Computer Science 2024-08-29 Zohaib Khan , Muhammad Khaquan , Omer Tafveez , Burhanuddin Samiwala , Agha Ali Raza

Transformer is the backbone of modern NLP models. In this paper, we propose RealFormer, a simple and generic technique to create Residual Attention Layer Transformer networks that significantly outperform the canonical Transformer and its…

Machine Learning · Computer Science 2021-09-14 Ruining He , Anirudh Ravula , Bhargav Kanagal , Joshua Ainslie

This paper investigates the limitations of transformers for entity-tracking tasks in large language models. We identify a theoretical constraint, showing that transformers require at least $\log_2 (n+1)$ layers to handle entity tracking…

Machine Learning · Computer Science 2024-12-12 Erwan Fagnou , Paul Caillon , Blaise Delattre , Alexandre Allauzen

In decoder-only (causal) transformers, the computation graph created by causal masking routes information through both direct-path attention and indirect paths formed by intermediate tokens. We denote these indirect paths between token…

Machine Learning · Computer Science 2026-01-22 Hunjae Lee , Corey Clark

Transformers in their common form are inherently limited to operate on whole token sequences rather than on one token at a time. Consequently, their use during online inference on time-series data entails considerable redundancy due to the…

Artificial Intelligence · Computer Science 2023-06-28 Lukas Hedegaard , Arian Bakhtiarnia , Alexandros Iosifidis

Query-based methods have garnered significant attention in object detection since the advent of DETR, the pioneering query-based detector. However, these methods face challenges like slow convergence and suboptimal performance. Notably,…

Computer Vision and Pattern Recognition · Computer Science 2023-12-15 Hongbin Xu , Yamei Xia , Shuai Zhao , Bo Cheng

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

Recent studies have revealed various manifestations of position bias in transformer architectures, from the "lost-in-the-middle" phenomenon to attention sinks, yet a comprehensive theoretical understanding of how attention masks and…

Machine Learning · Computer Science 2025-08-12 Xinyi Wu , Yifei Wang , Stefanie Jegelka , Ali Jadbabaie

The Transformer architecture has gained growing attention in graph representation learning recently, as it naturally overcomes several limitations of graph neural networks (GNNs) by avoiding their strict structural inductive biases and…

Machine Learning · Statistics 2022-06-14 Dexiong Chen , Leslie O'Bray , Karsten Borgwardt

Existing sequence to sequence models for structured language tasks rely heavily on the dot product self attention mechanism, which incurs quadratic complexity in both computation and memory for input length N. We introduce the Graph Wavelet…

Computation and Language · Computer Science 2025-05-14 Andrew Kiruluta , Eric Lundy , Priscilla Burity

Token representation strategies within large-scale neural architectures often rely on contextually refined embeddings, yet conventional approaches seldom encode structured relationships explicitly within token interactions. Self-attention…

Computation and Language · Computer Science 2025-03-27 James Blades , Frederick Somerfield , William Langley , Susan Everingham , Maurice Witherington

This work examines whether decoder-only Transformers such as LLaMA, which were originally designed for large language models (LLMs), can be adapted to the computer vision field. We first "LLaMAfy" a standard ViT step-by-step to align with…

Computer Vision and Pattern Recognition · Computer Science 2024-05-28 Jiahao Wang , Wenqi Shao , Mengzhao Chen , Chengyue Wu , Yong Liu , Taiqiang Wu , Kaipeng Zhang , Songyang Zhang , Kai Chen , Ping Luo

We present SegNeXt, a simple convolutional network architecture for semantic segmentation. Recent transformer-based models have dominated the field of semantic segmentation due to the efficiency of self-attention in encoding spatial…

Computer Vision and Pattern Recognition · Computer Science 2022-09-20 Meng-Hao Guo , Cheng-Ze Lu , Qibin Hou , Zhengning Liu , Ming-Ming Cheng , Shi-Min Hu

The success of self-attention lies in its ability to capture long-range dependencies and enhance context understanding, but it is limited by its computational complexity and challenges in handling sequential data with inherent…

Computation and Language · Computer Science 2025-05-05 Md Kowsher , Nusrat Jahan Prottasha , Chun-Nam Yu , Ozlem Ozmen Garibay , Niloofar Yousefi

In deep learning theory, the covariance matrix of the representations serves as a proxy to examine the network's trainability. Motivated by the success of Transformers, we study the covariance matrix of a modified Softmax-based attention…

Machine Learning · Statistics 2023-12-12 Lorenzo Noci , Chuning Li , Mufan Bill Li , Bobby He , Thomas Hofmann , Chris Maddison , Daniel M. Roy