English
Related papers

Related papers: Attention-Only Transformers via Unrolled Subspace …

200 papers

The training and generalization dynamics of the Transformer's core mechanism, namely the Attention mechanism, remain under-explored. Besides, existing analyses primarily focus on single-head attention. Inspired by the demonstrated benefits…

Machine Learning · Computer Science 2024-10-15 Puneesh Deora , Rouzbeh Ghaderi , Hossein Taheri , Christos Thrampoulidis

The powerful modeling capabilities of all-attention-based transformer architectures often cause overfitting and - for natural language processing tasks - lead to an implicitly learned internal language model in the autoregressive…

Machine Learning · Computer Science 2022-09-21 Timo Lohrenz , Björn Möller , Zhengyang Li , Tim Fingscheidt

Today's denoising diffusion models do not "denoise" in the classical sense, i.e., they do not directly predict clean images. Rather, the neural networks predict noise or a noised quantity. In this paper, we suggest that predicting clean…

Computer Vision and Pattern Recognition · Computer Science 2026-01-08 Tianhong Li , Kaiming He

Vision transformer has emerged as a new paradigm in computer vision, showing excellent performance while accompanied by expensive computational cost. Image token pruning is one of the main approaches for ViT compression, due to the facts…

Computer Vision and Pattern Recognition · Computer Science 2023-07-07 Xiangcheng Liu , Tianyi Wu , Guodong Guo

In recent literature there are plenty of works that combine handcrafted and learnable regularizers to solve inverse imaging problems. While this hybrid approach has demonstrated promising results, the motivation for combining handcrafted…

Computer Vision and Pattern Recognition · Computer Science 2025-05-23 Alexandros Gkillas , Dimitris Ampeliotis , Kostas Berberidis

Transformers have attained outstanding performance across various modalities, owing to their simple but powerful scaled-dot-product (SDP) attention mechanisms. Researchers have attempted to migrate Transformers to graph learning, but most…

Machine Learning · Computer Science 2026-01-30 Liheng Ma , Soumyasundar Pal , Yingxue Zhang , Philip H. S. Torr , Mark Coates

Tensorizing a neural network involves reshaping some or all of its dense weight matrices into higher-order tensors and approximating them using low-rank tensor network decompositions. This technique has shown promise as a model compression…

Machine Learning · Computer Science 2025-05-27 Safa Hamreras , Sukhbinder Singh , Román Orús

Contemporary speech enhancement predominantly relies on audio transforms that are trained to reconstruct a clean speech waveform. The development of high-performing neural network sound recognition systems has raised the possibility of…

Audio and Speech Processing · Electrical Eng. & Systems 2025-11-18 Mark R. Saddler , Andrew Francl , Jenelle Feather , Kaizhi Qian , Yang Zhang , Josh H. McDermott

In recent years, a ton of research has been conducted on real image denoising tasks. However, the efforts are more focused on improving real image denoising through creating a better network architecture. We explore a different direction…

Computer Vision and Pattern Recognition · Computer Science 2022-07-06 Agus Gunawan , Muhammad Adi Nugroho , Se Jin Park

This paper presents a novel knowledge distillation neural architecture leveraging efficient transformer networks for effective image classification. Natural images display intricate arrangements encompassing numerous extraneous elements.…

Computer Vision and Pattern Recognition · Computer Science 2025-02-25 Dewan Tauhid Rahman , Yeahia Sarker , Antar Mazumder , Md. Shamim Anower

We study the performance of transformer architectures for multivariate time-series forecasting in low-data regimes consisting of only a few years of daily observations. Using synthetically generated processes with known temporal and…

Machine Learning · Computer Science 2026-02-11 Cyril Garcia , Guillaume Remy

Transformers have achieved great success across a wide range of applications, yet the theoretical foundations underlying their success remain largely unexplored. To demystify the strong capacities of transformers applied to versatile…

Machine Learning · Computer Science 2026-03-25 Chenyang Zhang , Qingyue Zhao , Quanquan Gu , Yuan Cao

In this paper, I introduce the retrieval problem, a simple yet common reasoning task that can be solved only by transformers with a minimum number of layers, which grows logarithmically with the input size. I empirically show that large…

Machine Learning · Computer Science 2025-10-29 Tiberiu Musat

The Transformer is an extremely powerful and prominent deep learning architecture. In this work, we challenge the commonly held belief in deep learning that going deeper is better, and show an alternative design approach that is building…

Machine Learning · Computer Science 2022-11-10 Jason Ross Brown , Yiren Zhao , Ilia Shumailov , Robert D Mullins

Autoencoders are neural network formulations where the input and output of the network are identical and the goal is to identify the hidden representation in the provided datasets. Generally, autoencoders project the data nonlinearly onto a…

Signal Processing · Electrical Eng. & Systems 2019-07-10 Debjani Bhowick , Deepak K. Gupta , Saumen Maiti , Uma Shankar

Self-attention, as the key block of transformers, is a powerful mechanism for extracting features from the inputs. In essence, what self-attention does is to infer the pairwise relations between the elements of the inputs, and modify the…

Machine Learning · Computer Science 2021-03-09 Lemeng Wu , Xingchao Liu , Qiang Liu

The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism.…

Computation and Language · Computer Science 2023-08-03 Ashish Vaswani , Noam Shazeer , Niki Parmar , Jakob Uszkoreit , Llion Jones , Aidan N. Gomez , Lukasz Kaiser , Illia Polosukhin

Multi-scale Vision Transformer (ViT) has emerged as a powerful backbone for computer vision tasks, while the self-attention computation in Transformer scales quadratically w.r.t. the input patch number. Thus, existing solutions commonly…

Computer Vision and Pattern Recognition · Computer Science 2022-07-12 Ting Yao , Yingwei Pan , Yehao Li , Chong-Wah Ngo , Tao Mei

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

The dot product self-attention is known to be central and indispensable to state-of-the-art Transformer models. But is it really required? This paper investigates the true importance and contribution of the dot product-based self-attention…

Computation and Language · Computer Science 2021-05-25 Yi Tay , Dara Bahri , Donald Metzler , Da-Cheng Juan , Zhe Zhao , Che Zheng