English
Related papers

Related papers: GMAT: Global Memory Augmentation for Transformers

200 papers

Large Language Models (LLMs) incur quadratic attention complexity with input length, creating a major time bottleneck in the prefilling stage. Existing acceleration methods largely exploit attention score sparsity by estimating blocks with…

Computation and Language · Computer Science 2026-04-22 Zhiyuan He , Yike Zhang , Chengruidong Zhang , Huiqiang Jiang , Yuqing Yang , Lili Qiu

The original softmax-based attention mechanism (regular attention) in the extremely successful Transformer architecture computes attention between $N$ tokens, each embedded in a $D$-dimensional head, with a time complexity of $O(N^2D)$.…

Machine Learning · Computer Science 2025-10-28 Armin Gerami , Ramani Duraiswami

Large language models (LLMs) encounter computational challenges during long-sequence inference, especially in the attention pre-filling phase, where the complexity grows quadratically with the prompt length. Previous efforts to mitigate…

Machine Learning · Computer Science 2025-03-03 Xunhao Lai , Jianqiao Lu , Yao Luo , Yiyuan Ma , Xun Zhou

Transformer-based Language Models' computation and memory overhead increase quadratically as a function of sequence length. The quadratic cost poses challenges when employing LLMs for processing long sequences. In this work, we introduce…

Computation and Language · Computer Science 2025-10-23 Kiarash Zahirnia , Zahra Golpayegani , Walid Ahmed , Yang Liu

Transformers have shown superior performance on various vision tasks. Their large receptive field endows Transformer models with higher representation power than their CNN counterparts. Nevertheless, simply enlarging the receptive field…

Computer Vision and Pattern Recognition · Computer Science 2023-09-06 Zhuofan Xia , Xuran Pan , Shiji Song , Li Erran Li , Gao Huang

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

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

Transformer has achieved great success in NLP. However, the quadratic complexity of the self-attention mechanism in Transformer makes it inefficient in handling long sequences. Many existing works explore to accelerate Transformers by…

Computation and Language · Computer Science 2021-09-03 Chuhan Wu , Fangzhao Wu , Tao Qi , Binxing Jiao , Daxin Jiang , Yongfeng Huang , Xing Xie

Transformer-based models consist of interleaved feed-forward blocks - that capture content meaning, and relatively more expensive self-attention blocks - that capture context meaning. In this paper, we explored trade-offs and ordering of…

Machine Learning · Computer Science 2021-05-18 Swetha Mandava , Szymon Migacz , Alex Fit Florea

Modern Language Models (LMs) owe much of their success to masked causal attention, the backbone of Generative Pre-Trained Transformer (GPT) models. Although GPTs can process the entire user prompt at once, the causal masking is applied to…

Computation and Language · Computer Science 2024-12-25 Shahar Katz , Liran Ringel , Yaniv Romano , Lior Wolf

Processing spatial data is a key component in many learning tasks for autonomous driving such as motion forecasting, multi-agent simulation, and planning. Prior works have demonstrated the value in using SE(2) invariant network…

Machine Learning · Computer Science 2025-07-25 Ethan Pronovost , Neha Boloor , Peter Schleede , Noureldin Hendy , Andres Morales , Nicholas Roy

The Transformer translation model (Vaswani et al., 2017) based on a multi-head attention mechanism can be computed effectively in parallel and has significantly pushed forward the performance of Neural Machine Translation (NMT). Though…

Computation and Language · Computer Science 2020-06-26 Hongfei Xu , Josef van Genabith , Deyi Xiong , Qiuhui Liu , Jingyi Zhang

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

In this paper, we share our reflections and insights on understanding Transformer architectures through the lens of associative memory--a classic psychological concept inspired by human cognition. We start with the basics of associative…

Machine Learning · Computer Science 2025-05-27 Shu Zhong , Mingyu Xu , Tenglong Ao , Guang Shi

The Attention module finds common usage in language modeling, presenting distinct challenges within the broader scope of Natural Language Processing. Multi-Head Attention (MHA) employs an absolute positional encoding, which imposes…

Computation and Language · Computer Science 2023-08-08 Herman Sugiharto , Aradea , Husni Mubarok

Memory constraint of always-on devices is one of the major concerns when deploying speech processing models on these devices. While larger models trained with sufficiently large amount of data generally perform better, making them fit in…

Computation and Language · Computer Science 2024-01-09 Yiming Wang , Jinyu Li

The attention mechanism forms the foundational blocks for transformer language models. Recent approaches show that scaling the model achieves human-level performance. However, with increasing demands for scaling and constraints on hardware…

Computation and Language · Computer Science 2024-07-16 Sai Sena Chinnakonduru , Astarag Mohapatra

We present BlockBERT, a lightweight and efficient BERT model for better modeling long-distance dependencies. Our model extends BERT by introducing sparse block structures into the attention matrix to reduce both memory consumption and…

Computation and Language · Computer Science 2020-11-03 Jiezhong Qiu , Hao Ma , Omer Levy , Scott Wen-tau Yih , Sinong Wang , Jie Tang

Despite the empirical success of prompt tuning in adapting pretrained language models to new tasks, theoretical analyses of its capabilities remain limited. Existing theoretical work primarily addresses universal approximation properties,…

Machine Learning · Computer Science 2025-09-03 Maxime Meyer , Mario Michelessa , Caroline Chaux , Vincent Y. F. Tan

World models enable agents to plan within imagined environments by predicting future states conditioned on past observations and actions. However, their ability to plan over long horizons is limited by the effective memory span of the…

Artificial Intelligence · Computer Science 2025-12-09 Eli J. Laird , Corey Clark