English
Related papers

Related papers: Exact Causal Attention with 10% Fewer Operations

200 papers

Cross Attention is a popular method for retrieving information from a set of context tokens for making predictions. At inference time, for each prediction, Cross Attention scans the full set of $\mathcal{O}(N)$ tokens. In practice, however,…

Machine Learning · Computer Science 2024-03-04 Leo Feng , Frederick Tung , Hossein Hajimirsadeghi , Yoshua Bengio , Mohamed Osama Ahmed

In modern machine learning, inner product attention computation is a fundamental task for training large language models such as Transformer, GPT-1, BERT, GPT-2, GPT-3 and ChatGPT. Formally, in this problem, one is given as input three…

Machine Learning · Computer Science 2023-05-11 Josh Alman , Zhao Song

Recently, several studies have explored methods for using KG embedding to answer logical queries. These approaches either treat embedding learning and query answering as two separated learning tasks, or fail to deal with the variability of…

Machine Learning · Computer Science 2019-10-02 Gengchen Mai , Krzysztof Janowicz , Bo Yan , Rui Zhu , Ling Cai , Ni Lao

The computational and memory demands of vanilla attention scale quadratically with the sequence length $N$, posing significant challenges for processing long sequences in Transformer models. FlashAttention alleviates these challenges by…

Machine Learning · Computer Science 2025-03-04 Guoxia Wang , Jinle Zeng , Xiyuan Xiao , Siming Wu , Jiabin Yang , Lujing Zheng , Zeyu Chen , Jiang Bian , Dianhai Yu , Haifeng Wang

Long-context modeling is crucial for next-generation language models, yet the high computational cost of standard attention mechanisms poses significant computational challenges. Sparse attention offers a promising direction for improving…

We present a fast algorithm for approximate Canonical Correlation Analysis (CCA). Given a pair of tall-and-thin matrices, the proposed algorithm first employs a randomized dimensionality reduction transform to reduce the size of the input…

Data Structures and Algorithms · Computer Science 2013-05-03 Haim Avron , Christos Boutsidis , Sivan Toledo , Anastasios Zouzias

Self-attention in transformer models is an incremental associative memory that maps key vectors to value vectors. One way to speed up self-attention is to employ GPU-compatible vector search algorithms based on standard partitioning methods…

Computation and Language · Computer Science 2025-06-04 Pierre-Emmanuel Mazaré , Gergely Szilvasy , Maria Lomeli , Francisco Massa , Naila Murray , Hervé Jégou , Matthijs Douze

Category-Agnostic Pose Estimation (CAPE) aims to localize keypoints on an object of any category given few exemplars in an in-context manner. Prior arts involve sophisticated designs, e.g., sundry modules for similarity calculation and a…

Computer Vision and Pattern Recognition · Computer Science 2024-07-19 Yujia Liang , Zixuan Ye , Wenze Liu , Hao Lu

Remarkable effectiveness of the channel or spatial attention mechanisms for producing more discernible feature representation are illustrated in various computer vision tasks. However, modeling the cross-channel relationships with channel…

Computer Vision and Pattern Recognition · Computer Science 2023-06-07 Daliang Ouyang , Su He , Guozhong Zhang , Mingzhu Luo , Huaiyong Guo , Jian Zhan , Zhijie Huang

We revisit the I/O complexity of attention in large language models. Given query-key-value matrices $Q,K,V\in\mathbb{R}^{n\times d}$, and a machine with fast memory size $M$, the goal is to compute the "attention matrix" $A=\text{softmax}(Q…

Machine Learning · Computer Science 2026-05-25 Pál András Papp , Aleksandros Sobczyk , Anastasios Zouzias

Transformers are slow and memory-hungry on long sequences, since the time and memory complexity of self-attention are quadratic in sequence length. Approximate attention methods have attempted to address this problem by trading off model…

Machine Learning · Computer Science 2022-06-24 Tri Dao , Daniel Y. Fu , Stefano Ermon , Atri Rudra , Christopher Ré

Self-attention based Transformer has demonstrated the state-of-the-art performances in a number of natural language processing tasks. Self-attention is able to model long-term dependencies, but it may suffer from the extraction of…

Computation and Language · Computer Science 2019-12-30 Guangxiang Zhao , Junyang Lin , Zhiyuan Zhang , Xuancheng Ren , Qi Su , Xu Sun

In large language models built upon the Transformer architecture, recent studies have shown that inter-head interaction can enhance attention performance. Motivated by this, we propose Multi-head Explicit Attention (MEA), a simple yet…

Machine Learning · Computer Science 2026-01-28 Runyu Peng , Yunhua Zhou , Demin Song , Kai Lv , Bo Wang , Qipeng Guo , Xipeng Qiu

Elementary Cellular Automata (ECA) are a well-studied computational universe that is, despite its simple configurations, capable of impressive computational variety. Harvesting this computation in a useful way has historically shown itself…

Cellular Automata and Lattice Gases · Physics 2024-07-26 Tom Eivind Glover , Ruben Jahren , Francesco Martinuzzi , Pedro Gonçalves Lind , Stefano Nichele

The attention mechanism is the computational core of modern Transformer architectures, but its quadratic complexity in the input sequence length is the bottleneck for large-scale inference. This has motivated a rapidly growing body of work…

Neural network architectures in natural language processing often use attention mechanisms to produce probability distributions over input token representations. Attention has empirically been demonstrated to improve performance in various…

Computation and Language · Computer Science 2021-05-10 George Chrysostomou , Nikolaos Aletras

Active learning enhances annotation efficiency by selecting the most revealing samples for labeling, thereby reducing reliance on extensive human input. Previous methods in semantic segmentation have centered on individual pixels or small…

Computer Vision and Pattern Recognition · Computer Science 2025-08-07 Jinchao Ge , Zeyu Zhang , Minh Hieu Phan , Bowen Zhang , Akide Liu , Yang Zhao , Shuwen Zhao

Motivated by the factorization inherent in the original fast multipole method and the improved fast Gauss transform we introduce a factorable form of attention that operates efficiently in high dimensions. This approach reduces the…

Machine Learning · Computer Science 2024-02-13 Armin Gerami , Monte Hoover , Pranav S. Dulepet , Ramani Duraiswami

Recent advances in efficient Transformers have exploited either the sparsity or low-rank properties of attention matrices to reduce the computational and memory bottlenecks of modeling long sequences. However, it is still challenging to…

Machine Learning · Computer Science 2021-10-29 Beidi Chen , Tri Dao , Eric Winsor , Zhao Song , Atri Rudra , Christopher Ré

In recent years, learned image compression (LIC) technologies have surpassed conventional methods notably in terms of rate-distortion (RD) performance. Most present learned techniques are VAE-based with an autoregressive entropy model,…

Image and Video Processing · Electrical Eng. & Systems 2024-10-08 Minghao Han , Shiyin Jiang , Shengxi Li , Xin Deng , Mai Xu , Ce Zhu , Shuhang Gu
‹ Prev 1 3 4 5 6 7 10 Next ›