English
Related papers

Related papers: Kronecker Attention Networks

200 papers

Linear attention methods offer Transformers $O(N)$ complexity but typically underperform standard softmax attention. We identify two fundamental limitations affecting these approaches: the restriction to convex combinations that only…

Machine Learning · Computer Science 2026-02-06 Jiecheng Lu , Xu Han , Yan Sun , Viresh Pati , Yubin Kim , Siddhartha Somani , Shihao Yang

Transformers have become prevalent in computer vision due to their performance and flexibility in modelling complex operations. Of particular significance is the 'cross-attention' operation, which allows a vector representation (e.g. of an…

Computer Vision and Pattern Recognition · Computer Science 2022-08-08 Ali Athar , Jonathon Luiten , Alexander Hermans , Deva Ramanan , Bastian Leibe

Attention matrices are fundamental to transformer research, supporting a broad range of applications including interpretability, visualization, manipulation, and distillation. Yet, most existing analyses focus on individual attention heads…

Machine Learning · Computer Science 2026-01-27 Ido Andrew Atad , Itamar Zimerman , Shahar Katz , Lior Wolf

While modern text-to-image models excel at prompt-based generation, they often lack the fine-grained control necessary for specific user requirements like spatial layouts or subject appearances. Multi-condition control addresses this, yet…

Computer Vision and Pattern Recognition · Computer Science 2026-02-09 Chao Zhou , Tianyi Wei , Yiling Chen , Wenbo Zhou , Nenghai Yu

Covariance estimation for matrix-valued data has received an increasing interest in applications. Unlike previous works that rely heavily on matrix normal distribution assumption and the requirement of fixed matrix size, we propose a class…

Methodology · Statistics 2022-04-20 Yichi Zhang , Weining Shen , Dehan Kong

Large Language Models struggle with memory demands from the growing Key-Value (KV) cache as context lengths increase. Existing compression methods homogenize head dimensions or rely on attention-guided token pruning, often sacrificing…

Computation and Language · Computer Science 2025-06-16 Xiaoran Liu , Siyang He , Qiqi Wang , Ruixiao Li , Yuerong Song , Zhigeng Liu , Linlin Li , Qun Liu , Zengfeng Huang , Qipeng Guo , Ziwei He , Xipeng Qiu

Despite the recent popularity of attention-based neural architectures in core AI fields like natural language processing (NLP) and computer vision (CV), their potential in modeling complex physical systems remains under-explored. Learning…

Machine Learning · Computer Science 2024-08-15 Yue Yu , Ning Liu , Fei Lu , Tian Gao , Siavash Jafarzadeh , Stewart Silling

This paper re-examines a continuous optimization framework dubbed NOTEARS for learning Bayesian networks. We first generalize existing algebraic characterizations of acyclicity to a class of matrix polynomials. Next, focusing on a…

Machine Learning · Computer Science 2020-10-20 Dennis Wei , Tian Gao , Yue Yu

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

Attention networks such as transformers have achieved state-of-the-art performance in many domains. These networks rely heavily on the dot product attention operator, which computes the similarity between two points by taking their inner…

Machine Learning · Computer Science 2023-12-05 Albert Tseng , Tao Yu , Toni J. B. Liu , Christopher De Sa

Attention-based neural networks have achieved state-of-the-art results on a wide range of tasks. Most such models use deterministic attention while stochastic attention is less explored due to the optimization difficulties or complicated…

Machine Learning · Computer Science 2021-06-10 Shujian Zhang , Xinjie Fan , Bo Chen , Mingyuan Zhou

Tensor networks are factorisations of high rank tensors into networks of lower rank tensors and have primarily been used to analyse quantum many-body problems. Tensor networks have seen a recent surge of interest in relation to supervised…

Computer Vision and Pattern Recognition · Computer Science 2021-03-26 Raghavendra Selvan , Silas Ørting , Erik B Dam

Autoregressive language models rely on a Key-Value (KV) Cache, which avoids re-computing past hidden states during generation, making it faster. As model sizes and context lengths grow, the KV Cache becomes a significant memory bottleneck,…

Computation and Language · Computer Science 2025-03-05 Nathan Godey , Alessio Devoto , Yu Zhao , Simone Scardapane , Pasquale Minervini , Éric de la Clergerie , Benoît Sagot

Neural operators have emerged as a powerful tool for learning the mapping between infinite-dimensional parameter and solution spaces of partial differential equations (PDEs). In this work, we focus on multiscale PDEs that have important…

Machine Learning · Computer Science 2024-06-11 Xinliang Liu , Bo Xu , Shuhao Cao , Lei Zhang

Relying on recent research results on Neural ODEs, this paper presents a methodology for the design of state observers for nonlinear systems based on Neural ODEs, learning Luenberger-like observers and their nonlinear extension…

Systems and Control · Electrical Eng. & Systems 2023-05-18 Keyan Miao , Konstantinos Gatsis

Self-attention in Transformers relies on globally normalized softmax weights, causing all tokens to compete for influence at every layer. When composed across depth, this interaction pattern induces strong synchronization dynamics that…

Machine Learning · Computer Science 2026-05-26 Jingkun Liu , Yisong Yue , Max Welling , Yue Song

Large transformer models have shown extraordinary success in achieving state-of-the-art results in many natural language processing applications. However, training and deploying these models can be prohibitively costly for long sequences,…

Machine Learning · Computer Science 2020-06-16 Sinong Wang , Belinda Z. Li , Madian Khabsa , Han Fang , Hao Ma

Kolmogorov-Arnold networks (KANs) are a remarkable innovation that consists of learnable activation functions, with the potential to capture more complex relationships from data. Presently, KANs are deployed by replacing multilayer…

Machine Learning · Computer Science 2025-10-23 Subhajit Maity , Killian Hitsman , Xin Li , Aritra Dutta

Partial differential equations (PDEs) are fundamental for modeling complex physical systems, yet classical numerical solvers face prohibitive computational costs in high-dimensional and multi-scale regimes. While Transformer-based neural…

Machine Learning · Computer Science 2026-03-04 Pengyu Lai , Yixiao Chen , Dewu Yang , Rui Wang , Feng Wang , Hui Xu

Transformers, and the attention mechanism in particular, have become ubiquitous in machine learning. Their success in modeling nonlocal, long-range correlations has led to their widespread adoption in natural language processing, computer…

Machine Learning · Computer Science 2025-12-23 Edoardo Calvello , Nikola B. Kovachki , Matthew E. Levine , Andrew M. Stuart