English
Related papers

Related papers: FuXi-\beta: Towards a Lightweight and Fast Large-S…

200 papers

Recency bias is a useful inductive prior for sequential modeling: it emphasizes nearby observations and can still allow longer-range dependencies. Standard Transformer attention lacks this property, relying on all-to-all interactions that…

Machine Learning · Computer Science 2026-04-23 Kareem Hegazy , Michael W. Mahoney , N. Benjamin Erichson

We propose a novel framework for producing a class of parameter and compute efficient models called AttentionLitesuitable for resource-constrained applications. Prior work has primarily focused on optimizing models either via knowledge…

Computer Vision and Pattern Recognition · Computer Science 2021-01-14 Souvik Kundu , Sairam Sundaresan

The deployment of Large Language Models (LLMs) faces a critical bottleneck when handling lengthy inputs: the prohibitive memory footprint of the Key Value (KV) cache. To address this bottleneck, the token pruning paradigm leverages…

Computation and Language · Computer Science 2026-03-03 Yifei Wang , Yueqi Wang , Zhenrui Yue , Huimin Zeng , Yong Wang , Ismini Lourentzou , Zhengzhong Tu , Xiangxiang Chu , Julian McAuley

Transformer model with multi-head attention requires caching intermediate results for efficient inference in generation tasks. However, cache brings new memory-related costs and prevents leveraging larger batch size for faster speed. We…

Computation and Language · Computer Science 2021-06-15 Yu Yan , Jiusheng Chen , Weizhen Qi , Nikhil Bhendawade , Yeyun Gong , Nan Duan , Ruofei Zhang

Self-attention networks have shown remarkable progress in computer vision tasks such as image classification. The main benefit of the self-attention mechanism is the ability to capture long-range feature interactions in attention-maps.…

Computer Vision and Pattern Recognition · Computer Science 2021-03-19 Andong Tan , Duc Tam Nguyen , Maximilian Dax , Matthias Nießner , Thomas Brox

Multi-head, key-value attention is the backbone of the widely successful Transformer model and its variants. This attention mechanism uses multiple parallel key-value attention blocks (called heads), each performing two fundamental…

Machine Learning · Computer Science 2022-02-15 Sarthak Mittal , Sharath Chandra Raparthy , Irina Rish , Yoshua Bengio , Guillaume Lajoie

The softmax content-based attention mechanism has proven to be very beneficial in many applications of recurrent neural networks. Nevertheless it suffers from two major computational limitations. First, its computations for an attention…

Machine Learning · Computer Science 2016-09-20 Alexandre de Brébisson , Pascal Vincent

Attention mechanism is contributing to the majority of recent advances in machine learning for natural language processing. Additionally, it results in an attention map that shows the proportional influence of each input in its decision.…

Computation and Language · Computer Science 2025-01-23 Duc Hau Nguyen , Cyrielle Mallart , Guillaume Gravier , Pascale Sébillot

Attention-based graph neural networks have made great progress in feature matching learning. However, insight of how attention mechanism works for feature matching is lacked in the literature. In this paper, we rethink cross- and…

Computer Vision and Pattern Recognition · Computer Science 2023-07-12 Yuxin Deng , Jiayi Ma

Transformers are mostly relying on softmax attention, which introduces quadratic complexity with respect to sequence length and remains a major bottleneck for efficient inference. Prior work on linear or hybrid attention typically replaces…

In the era of advancing information technology, recommender systems have emerged as crucial tools for dealing with information overload. However, traditional recommender systems still have limitations in capturing the dynamic evolution of…

Information Retrieval · Computer Science 2025-04-09 Mingjian Fu , Hengsheng Chen , Dongchun Jiang , Yanchao Tan

Timeseries analytics is of great importance in many real-world applications. Recently, the Transformer model, popular in natural language processing, has been leveraged to learn high quality feature embeddings from timeseries, core to the…

Machine Learning · Computer Science 2023-06-06 Jiaming Liang , Lei Cao , Samuel Madden , Zachary Ives , Guoliang Li

Linear recurrent neural networks have emerged as efficient alternatives to the original Transformer's softmax attention mechanism, thanks to their highly parallelizable training and constant memory and computation requirements at inference.…

Machine Learning · Computer Science 2026-01-21 Younes Bouhadjar , Maxime Fabre , Felix Schmidt , Emre Neftci

While Transformers have shown remarkable success in natural language processing, their attention mechanism's large memory requirements have limited their ability to handle longer contexts. Prior approaches, such as recurrent memory or…

Computation and Language · Computer Science 2023-11-21 Amirkeivan Mohtashami , Martin Jaggi

Many advanced Large Language Model (LLM) applications require long-context processing, but the self-attention module becomes a bottleneck during the prefilling stage of inference due to its quadratic time complexity with respect to sequence…

Machine Learning · Computer Science 2025-06-02 Xiaodong Ji , Hailin Zhang , Fangcheng Fu , Bin Cui

This work presents a sparse-attention Transformer architecture for modeling documents that contain large tables. Tables are ubiquitous on the web, and are rich in information. However, more than 20% of relational tables on the web have 20…

Computation and Language · Computer Science 2021-09-10 Julian Martin Eisenschlos , Maharshi Gor , Thomas Müller , William W. Cohen

Transformer-based models excel in speech recognition. Existing efforts to optimize Transformer inference, typically for long-context applications, center on simplifying attention score calculations. However, streaming speech recognition…

Machine Learning · Computer Science 2024-01-22 Yang Li , Liangzhen Lai , Yuan Shangguan , Forrest N. Iandola , Zhaoheng Ni , Ernie Chang , Yangyang Shi , Vikas Chandra

Chunked prefill has become a widely adopted serving strategy for long-context large language models, but efficient attention computation in this regime remains challenging. Existing sparse attention methods are primarily designed for…

Computation and Language · Computer Science 2026-05-19 Jiwon Song , Dongwon Jo , Beomseok Kang , Jae-Joon Kim

Linear attention mechanisms have emerged as efficient alternatives to full self-attention in Graph Transformers, offering linear time complexity. However, existing linear attention models often suffer from a significant drop in…

Computer Vision and Pattern Recognition · Computer Science 2026-01-29 Zhaolin Hu , Kun Li , Hehe Fan , Yi Yang

Retrieval-augmented generation framework can address the limitations of large language models by enabling real-time knowledge updates for more accurate answers. An efficient way in the training phase of retrieval-augmented models is…

Computation and Language · Computer Science 2024-02-20 Zizhong Li , Haopeng Zhang , Jiawei Zhang