English
Related papers

Related papers: Conformal Transformations for Symmetric Power Tran…

200 papers

Transformers have achieved remarkable success in sequence modeling and beyond but suffer from quadratic computational and memory complexities with respect to the length of the input sequence. Leveraging techniques include sparse and linear…

Machine Learning · Computer Science 2022-08-02 Tan Nguyen , Richard G. Baraniuk , Robert M. Kirby , Stanley J. Osher , Bao Wang

Transformers have demonstrated effectiveness in in-context solving data-fitting problems from various (latent) models, as reported by Garg et al. However, the absence of an inherent iterative structure in the transformer architecture…

Machine Learning · Computer Science 2024-03-19 Liu Yang , Kangwook Lee , Robert Nowak , Dimitris Papailiopoulos

The attention mechanism in its standard implementation contains extraneous rotational degrees of freedom that are carried through computation but do not affect model activations or outputs. We introduce a simple symmetry-breaking protocol…

Machine Learning · Computer Science 2026-02-13 Eva Silverstein , Daniel Kunin , Vasudev Shyam

Looped Transformers provide advantages in parameter efficiency, computational capabilities, and generalization for reasoning tasks. However, their expressive power regarding function approximation remains underexplored. In this paper, we…

Machine Learning · Computer Science 2025-06-06 Kevin Xu , Issei Sato

Transformer-based architectures achieved breakthrough performance in natural language processing and computer vision, yet they remain inferior to simpler linear baselines in multivariate long-term forecasting. To better understand this…

Machine Learning · Computer Science 2024-06-04 Romain Ilbert , Ambroise Odonnat , Vasilii Feofanov , Aladin Virmaux , Giuseppe Paolo , Themis Palpanas , Ievgen Redko

Soft Continuum arms, such as trunk and tentacle robots, can be considered as the "dual" of traditional rigid-bodied robots in terms of manipulability, degrees of freedom, and compliance. Introduced two decades ago, continuum arms have not…

Robotics · Computer Science 2018-12-14 Estefany A. Torres , Kohei Nakajima , Isuru S. Godage

Excessive switching activity is a primary contributor to dynamic power dissipation in modern FPGAs, where fine-grained configurability amplifies signal toggling and associated capacitance. Conventional low-power techniques -- gating,…

Hardware Architecture · Computer Science 2025-10-28 Eashan Wadhwa , Shanker Shreejith

Attention is a key part of the transformer architecture. It is a sequence-to-sequence mapping that transforms each sequence element into a weighted sum of values. The weights are typically obtained as the softmax of dot products between…

This paper studies how the model architecture and data configurations influence the empirical memorization capacity of generative transformers. The models are trained using synthetic text datasets derived from the Systematized Nomenclature…

Computation and Language · Computer Science 2025-06-18 Anton Changalidis , Aki Härmä

Different studies of the embedding space of transformer models suggest that the distribution of contextual representations is highly anisotropic - the embeddings are distributed in a narrow cone. Meanwhile, static word representations…

Computation and Language · Computer Science 2021-09-29 Yue Ding , Karolis Martinkus , Damian Pascual , Simon Clematide , Roger Wattenhofer

Transformers achieve remarkable performance in various domains, including NLP, CV, audio processing, and graph analysis. However, they do not scale well on long sequence tasks due to their quadratic complexity w.r.t. the inputs length.…

Machine Learning · Computer Science 2022-02-24 Maksim Zubkov , Daniil Gavrilov

In this work, we address two main shortcomings of transformer architectures: input corruption and rank collapse in their output representation. We unveil self-attention as an autonomous state-space model that inherently promotes smoothness…

Artificial Intelligence · Computer Science 2024-02-27 Tam Nguyen , César A. Uribe , Tan M. Nguyen , Richard G. Baraniuk

The feasible set of real powers that can be transferred by a three-terminal Soft Open Point (SOP) can be increased by selecting non-uniform power ratings for each of the three ac/dc legs of the SOP, then connecting a multi-terminal switch…

Systems and Control · Electrical Eng. & Systems 2023-04-26 Matthew Deakin

Since its introduction, the transformer has shifted the development trajectory away from traditional models (e.g., RNN, MLP) in time series forecasting, which is attributed to its ability to capture global dependencies within temporal…

Machine Learning · Computer Science 2025-01-07 Xiwen Chen , Peijie Qiu , Wenhui Zhu , Huayu Li , Hao Wang , Aristeidis Sotiras , Yalin Wang , Abolfazl Razi

Transformers exhibit proficiency in capturing long-range dependencies, whereas State Space Models (SSMs) facilitate linear-time sequence modeling. Notwithstanding their synergistic potential, the integration of these architectures presents…

Computation and Language · Computer Science 2025-06-19 Bingheng Wu , Jingze Shi , Yifan Wu , Nan Tang , Yuyu Luo

Transformers evaluated in a single, fixed-depth pass are provably limited in expressive power to the constant-depth circuit class TC0. Running a Transformer autoregressively removes that ceiling -- first in next-token prediction and, more…

Machine Learning · Computer Science 2025-07-21 Mrinal Mathur , Mike Doan , Barak Pearlmutter , Sergey Plis

Recent advances in machine learning, specifically transformer architecture, have led to significant advancements in commercial domains. These powerful models have demonstrated superior capability to learn complex relationships and often…

Machine Learning · Computer Science 2024-05-29 Matthew L. Olson , Shusen Liu , Jayaraman J. Thiagarajan , Bogdan Kustowski , Weng-Keen Wong , Rushil Anirudh

Flexible transmission line impedances on one hand are a promising control resource for facilitating grid flexibility, but on the other hand add much complexity to the concerned optimization problems. This paper develops a convexification…

Optimization and Control · Mathematics 2022-04-12 Yue Song , David J. Hill , Tao Liu , Tianlun Chen

As transformer-based language models are trained on increasingly large datasets and with vast numbers of parameters, finding more efficient alternatives to the standard Transformer has become very valuable. While many efficient Transformers…

Machine Learning · Computer Science 2024-11-12 Kai Yang , Jan Ackermann , Zhenyu He , Guhao Feng , Bohang Zhang , Yunzhen Feng , Qiwei Ye , Di He , Liwei Wang

The attention mechanism is a pivotal element within the transformer architecture, making a substantial contribution to its exceptional performance. Within this attention mechanism, Softmax is an imperative component that enables the model…

Hardware Architecture · Computer Science 2024-09-05 Tianhua Xia , Sai Qian Zhang
‹ Prev 1 2 3 10 Next ›