English
Related papers

Related papers: Adaptive Computation Depth via Learned Token Routi…

200 papers

Standard transformer attention computes pairwise similarity between queries and keys, treating all tokens as equally salient regardless of their intrinsic informational content. In turbulent fluid dynamics, coherent structures -- the…

Machine Learning · Computer Science 2026-05-22 Athanasios Zeris

Transformer networks are rapidly becoming SotA in many fields, such as NLP and CV. Similarly to CNN, there is a strong push for deploying Transformer models at the extreme edge, ultimately fitting the tiny power budget and memory footprint…

Machine Learning · Computer Science 2024-04-05 Victor J. B. Jung , Alessio Burrello , Moritz Scherer , Francesco Conti , Luca Benini

Large models based on the Transformer architecture are susceptible to extreme-token phenomena, such as attention sinks and value-state drains. These issues, which degrade model performance, quantization fidelity, and interpretability, arise…

Machine Learning · Computer Science 2026-01-27 Rui Bu , Haofeng Zhong , Wenzheng Chen , Yangyan Li

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

A method is presented for accelerating inference in transformer language models by exploiting the low effective rank of the token activation manifold at each layer. The method decomposes each activation vector into a subspace component and…

Machine Learning · Computer Science 2026-05-06 Stephen J. Thomas

Token-level adaptive computation seeks to reduce inference cost by allocating more computation to harder tokens and less to easier ones. However, prior work is primarily evaluated on natural-language benchmarks using task-level metrics,…

Computation and Language · Computer Science 2026-02-10 Ibraheem Muhammad Moosa , Suhas Lohit , Ye Wang , Moitreya Chatterjee , Wenpeng Yin

Transformers are the mainstream of NLP applications and are becoming increasingly popular in other domains such as Computer Vision. Despite the improvements in model quality, the enormous computation costs make Transformers difficult at…

Machine Learning · Computer Science 2021-10-22 Liu Liu , Zheng Qu , Zhaodong Chen , Yufei Ding , Yuan Xie

The Transformer architecture has become the foundation of modern deep learning, yet its core self-attention mechanism suffers from quadratic computational complexity and lacks grounding in biological neural computation. We propose Selective…

Machine Learning · Computer Science 2026-02-17 Hasi Hays

We propose Low-Rank Sparse Attention (Lorsa), a sparse replacement model of Transformer attention layers to disentangle original Multi Head Self Attention (MHSA) into individually comprehensible components. Lorsa is designed to address the…

Machine Learning · Computer Science 2025-04-30 Zhengfu He , Junxuan Wang , Rui Lin , Xuyang Ge , Wentao Shu , Qiong Tang , Junping Zhang , Xipeng Qiu

Since its introduction in 2017, Transformer has emerged as the leading neural network architecture, catalyzing revolutionary advancements in many AI disciplines. The key innovation in Transformer is a Self-Attention (SA) mechanism designed…

Machine Learning · Computer Science 2024-02-05 Yueyao Yu , Yin Zhang

Deep learning based transient stability assessment (TSA) has achieved great success, yet the lack of interpretability hinders its industrial application. Although a great number of studies have tried to explore the interpretability of…

Systems and Control · Electrical Eng. & Systems 2024-04-04 Hanxuan Wang , Na Lu , Zixuan Wang , Jiacheng Liu , Jun Liu

Transformer-based deep neural networks have achieved great success in various sequence applications due to their powerful ability to model long-range dependency. The key module of Transformer is self-attention (SA) which extracts features…

Artificial Intelligence · Computer Science 2023-01-31 Kyuhong Shim , Jungwook Choi , Wonyong Sung

Transformer architectures are the backbone of the modern AI revolution. However, they are based on simply stacking the same blocks in dozens of layers and processing information sequentially from one block to another. In this paper, we…

Computation and Language · Computer Science 2024-12-24 Prateek Verma , Mert Pilanci

Attention-based architectures have become ubiquitous in machine learning, yet our understanding of the reasons for their effectiveness remains limited. This work proposes a new way to understand self-attention networks: we show that their…

Machine Learning · Computer Science 2023-08-02 Yihe Dong , Jean-Baptiste Cordonnier , Andreas Loukas

Large language models (LLMs) excel at capturing global token dependencies via self-attention but face prohibitive compute and memory costs on lengthy inputs. While sub-quadratic methods (e.g., linear attention) can reduce these costs, they…

Machine Learning · Computer Science 2025-06-18 Yeonju Ro , Zhenyu Zhang , Souvik Kundu , Zhangyang Wang , Aditya Akella

The transformer architecture is central to the success of modern Large Language Models (LLMs), in part due to its surprising ability to perform a wide range of tasks - including mathematical reasoning, memorization, and retrieval - using…

Machine Learning · Computer Science 2025-09-05 Yihe Dong , Lorenzo Noci , Mikhail Khodak , Mufan Li

Transformer encoders contextualize token representations by attending to all other tokens at each layer, leading to quadratic increase in compute effort with the input length. In practice, however, the input text of many NLP tasks can be…

Computation and Language · Computer Science 2023-06-01 Jeremiah Milbauer , Annie Louis , Mohammad Javad Hosseini , Alex Fabrikant , Donald Metzler , Tal Schuster

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

Parameter-efficient tuning aims at updating only a small subset of parameters when adapting a pretrained model to downstream tasks. In this work, we introduce PASTA, in which we only modify the special token representations (e.g., [SEP] and…

Computation and Language · Computer Science 2023-02-15 Xiaocong Yang , James Y. Huang , Wenxuan Zhou , Muhao Chen

The Transformer translation model is based on the multi-head attention mechanism, which can be parallelized easily. The multi-head attention network performs the scaled dot-product attention function in parallel, empowering the model by…

Computation and Language · Computer Science 2021-09-13 Hongfei Xu , Qiuhui Liu , Josef van Genabith , Deyi Xiong