English
Related papers

Related papers: LazyFormer: Self Attention with Lazy Update

200 papers

Attention layers are widely used in natural language processing (NLP) and are beginning to influence computer vision architectures. Training very large transformer models allowed significant improvement in both fields, but once trained,…

Machine Learning · Computer Science 2021-05-21 Jean-Baptiste Cordonnier , Andreas Loukas , Martin Jaggi

Group equivariant neural networks are used as building blocks of group invariant neural networks, which have been shown to improve generalisation performance and data efficiency through principled parameter sharing. Such works have mostly…

Machine Learning · Computer Science 2021-06-17 Michael Hutchinson , Charline Le Lan , Sheheryar Zaidi , Emilien Dupont , Yee Whye Teh , Hyunjik Kim

While the transformer architecture has achieved state-of-the-art performance on natural language processing tasks, these models impose substantial memory and computational overhead. Recent research has identified significant architectural…

Computation and Language · Computer Science 2026-04-01 Shivanshu Kumar , Gopalakrishnan Srinivasan

Pretrained language models based on the transformer architecture have shown great success in NLP. Textual training data often comes from the web and is thus tagged with time-specific information, but most language models ignore this…

Computation and Language · Computer Science 2022-05-05 Guy D. Rosin , Kira Radinsky

To capture user preference, transformer models have been widely applied to model sequential user behavior data. The core of transformer architecture lies in the self-attention mechanism, which computes the pairwise attention scores in a…

Information Retrieval · Computer Science 2024-04-05 Zhen Tian , Wayne Xin Zhao , Changwang Zhang , Xin Zhao , Zhongrui Ma , Ji-Rong Wen

We revisit the design choices in Transformers, and propose methods to address their weaknesses in handling long sequences. First, we propose a simple layer named gated attention unit, which allows the use of a weaker single-head attention…

Machine Learning · Computer Science 2022-06-28 Weizhe Hua , Zihang Dai , Hanxiao Liu , Quoc V. Le

This research endeavors to offer insights into unlocking the further potential of transformer-based architectures. One of the primary motivations is to offer a geometric interpretation for the attention mechanism in transformers. In our…

Machine Learning · Computer Science 2025-12-16 Zhongping Ji

Transformer architectures deliver state-of-the-art accuracy via dense full-attention, but their quadratic time and memory complexity with respect to sequence length limits practical deployment. Linear attention mechanisms offer linear or…

Machine Learning · Computer Science 2026-01-21 Xiaojie Xia , Huigang Zhang , Chaoliang Zhong , Jun Sun , Yusuke Oishi

We propose Joint MLP/Attention (JoMA) dynamics, a novel mathematical framework to understand the training procedure of multilayer Transformer architectures. This is achieved by integrating out the self-attention layer in Transformers,…

Machine Learning · Computer Science 2024-03-18 Yuandong Tian , Yiping Wang , Zhenyu Zhang , Beidi Chen , Simon Du

Multi-head attention layers, as used in the Transformer neural sequence model, are a powerful alternative to RNNs for moving information across and between sequences. While training these layers is generally fast and simple, due to…

Neural and Evolutionary Computing · Computer Science 2019-11-07 Noam Shazeer

While Transformers have revolutionized deep learning, their quadratic attention complexity hinders their ability to process infinitely long inputs. We propose Feedback Attention Memory (FAM), a novel Transformer architecture that leverages…

Machine Learning · Computer Science 2024-05-08 Dongseong Hwang , Weiran Wang , Zhuoyuan Huo , Khe Chai Sim , Pedro Moreno Mengibar

Transformer-based models have been widely adopted for sentiment analysis tasks due to their exceptional ability to capture contextual information. However, these methods often exhibit suboptimal accuracy in certain scenarios. By analyzing…

Artificial Intelligence · Computer Science 2025-12-25 Yawei Liu

Transformers have had tremendous impact for several sequence related tasks, largely due to their ability to retrieve from any part of the sequence via softmax based dot-product attention. This mechanism plays a crucial role in Transformer's…

Machine Learning · Computer Science 2025-07-15 Sai Surya Duvvuri , Inderjit S. Dhillon

In the Transformer model, "self-attention" combines information from attended embeddings into the representation of the focal embedding in the next layer. Thus, across layers of the Transformer, information originating from different tokens…

Machine Learning · Computer Science 2020-06-02 Samira Abnar , Willem Zuidema

Diffusion Transformers have emerged as the preeminent models for a wide array of generative tasks, demonstrating superior performance and efficacy across various applications. The promising results come at the cost of slow inference, as…

Machine Learning · Computer Science 2025-03-24 Xuan Shen , Zhao Song , Yufa Zhou , Bo Chen , Yanyu Li , Yifan Gong , Kai Zhang , Hao Tan , Jason Kuen , Henghui Ding , Zhihao Shu , Wei Niu , Pu Zhao , Yanzhi Wang , Jiuxiang Gu

Transformer architectures have transformed AI applications but remain complex to customize for domain experts lacking low-level implementation expertise. We introduce AttentionSmithy, a modular software package that simplifies transformer…

Machine Learning · Computer Science 2025-02-18 Caleb Cranney , Jesse G. Meyer

Transformer-based architectures achieve state-of-the-art performance across a wide range of tasks in natural language processing, computer vision, and speech processing. However, their immense capacity often leads to overfitting, especially…

Computer Vision and Pattern Recognition · Computer Science 2025-09-22 Mirza Samad Ahmed Baig , Syeda Anshrah Gillani , Abdul Akbar Khan , Shahid Munir Shah , Muhammad Omer Khan

Modern foundation models such as large language models (LLMs) and large multi-modal models (LMMs) require a massive amount of computational and memory resources. We propose a new framework to convert such LLMs/LMMs into a reduced-dimension…

Machine Learning · Computer Science 2025-05-27 Toshiaki Koike-Akino , Xiangyu Chen , Jing Liu , Ye Wang , Pu , Wang , Matthew Brand

Attention mechanisms have improved the performance of NLP tasks while allowing models to remain explainable. Self-attention is currently widely used, however interpretability is difficult due to the numerous attention distributions. Recent…

Computation and Language · Computer Science 2020-10-30 Khalil Mrini , Franck Dernoncourt , Quan Tran , Trung Bui , Walter Chang , Ndapa Nakashole

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