English
Related papers

Related papers: Degrees of Freedom for Linear Attention: Distillin…

200 papers

Attention models are typically learned by optimizing one of three standard loss functions that are variously called -- soft attention, hard attention, and latent variable marginal likelihood (LVML) attention. All three paradigms are…

Machine Learning · Computer Science 2023-10-16 Rahul Vashisht , Harish G. Ramaswamy

We establish the universal approximation capability of single-layer, single-head self- and cross-attention mechanisms with minimal attached structures. Our key insight is to interpret single-head attention as an input domain-partition…

Machine Learning · Computer Science 2025-04-29 Hude Liu , Jerry Yao-Chieh Hu , Zhao Song , Han Liu

Large language models (LLMs) have demonstrated remarkable performance across a wide range of tasks. However, the quadratic complexity of softmax attention remains a central bottleneck that limits their scalability. Alman and Song (NeurIPS…

Machine Learning · Computer Science 2026-03-20 Maryam Aliakbarpour , Vladimir Braverman , Junze Yin , Haochen Zhang

In deep learning theory, the covariance matrix of the representations serves as a proxy to examine the network's trainability. Motivated by the success of Transformers, we study the covariance matrix of a modified Softmax-based attention…

Machine Learning · Statistics 2023-12-12 Lorenzo Noci , Chuning Li , Mufan Bill Li , Bobby He , Thomas Hofmann , Chris Maddison , Daniel M. Roy

The transformer's attention mechanism has revolutionized AI and machine learning, with its efficient computation being crucial to its performance. However, calculating attention involves matrix operations interspersed with softmax…

Machine Learning · Computer Science 2025-05-21 Kosmas Alexandridis , Vasileios Titopoulos , Giorgos Dimitrakopoulos

This paper introduces Exact Linear Attention (ELA), a mechanism that achieves linear computational complexity for Transformer attention by exploiting the exact decomposition property of kernel functions, thereby eliminating approximation…

Machine Learning · Computer Science 2026-05-21 Weinuo Ou

In pursuit of faster computation, Efficient Transformers demonstrate an impressive variety of approaches -- models attaining sub-quadratic attention complexity can utilize a notion of sparsity or a low-rank approximation of inputs to reduce…

Machine Learning · Computer Science 2022-11-09 Uladzislau Yorsh , Alexander Kovalenko

Transformers and large language models (LLMs), powered by the attention mechanism, have transformed numerous AI applications, driving the need for specialized hardware accelerators. A major challenge in these accelerators is efficiently…

Machine Learning · Computer Science 2025-07-23 Vasileios Titopoulos , Kosmas Alexandridis , Giorgos Dimitrakopoulos

Prompt-tuning is an emerging strategy to adapt large language models (LLM) to downstream tasks by learning a (soft-)prompt parameter from data. Despite its success in LLMs, there is limited theoretical understanding of the power of…

Machine Learning · Computer Science 2023-06-07 Samet Oymak , Ankit Singh Rawat , Mahdi Soltanolkotabi , Christos Thrampoulidis

Diffusion Large Language Models (dLLMs) deliver strong long-context processing capability in a non-autoregressive decoding paradigm. However, the considerable computational cost of bidirectional full attention limits the inference…

Computation and Language · Computer Science 2026-02-03 Lingkun Long , Yushi Huang , Shihao Bai , Ruihao Gong , Jun Zhang , Ao Zhou , Jianlei Yang

In an effort to reduce the computational load of Transformers, research on linear attention has gained significant momentum. However, the improvement strategies for attention mechanisms typically necessitate extensive retraining, which is…

Computation and Language · Computer Science 2024-04-02 Hanting Chen , Zhicheng Liu , Xutao Wang , Yuchuan Tian , Yunhe Wang

Recent advances in single-frame object detection and segmentation techniques have motivated a wide range of works to extend these methods to process video streams. In this paper, we explore the idea of hard attention aimed for…

Computer Vision and Pattern Recognition · Computer Science 2019-08-21 Yuning Chai

Linear attention reduces the quadratic cost of softmax attention to $\mathcal{O}(T)$, but its memory state grows as $\mathcal{O}(T)$ in Frobenius norm, causing progressive interference between stored associations. We introduce…

Machine Learning · Computer Science 2026-05-13 Vishal Pandey , Gopal Singh

In this work, we propose a method that leverages CLIP feature distillation, achieving efficient 3D segmentation through language guidance. Unlike previous methods that rely on multi-scale CLIP features and are limited by processing speed…

Computer Vision and Pattern Recognition · Computer Science 2025-02-03 Xingyu Miao , Haoran Duan , Yang Bai , Tejal Shah , Jun Song , Yang Long , Rajiv Ranjan , Ling Shao

Transformer models typically calculate attention matrices using dot products, which have limitations when capturing nonlinear relationships between embedding vectors. We propose Neural Attention, a technique that replaces dot products with…

Machine Learning · Computer Science 2025-11-10 Andrew DiGiugno , Ausif Mahmood

Understanding whether attention mechanisms converge to the kernel regime is foundational to the validity of influence functions for transformer accountability. Exact NTK characterization of softmax attention is precluded by its exponential…

Machine Learning · Computer Science 2026-05-08 Jose Marie Antonio Miñoza , Paulo Mario P. Medina , Sebastian C. Ibañez

We characterize the pre-softmax attention matrix $\mathbf{QK^\top}$ in transformers as an associative memory matrix encoding pairwise associations between input features. By decomposing this matrix into its symmetric and skew-symmetric…

Machine Learning · Computer Science 2026-05-28 Hyunmin Cho , Woo Kyoung Han , Kyong Hwan Jin

Attention mechanisms have revolutionized several domains of artificial intelligence, such as natural language processing and computer vision, by enabling models to selectively focus on relevant parts of the input data. While recent work has…

Machine Learning · Computer Science 2026-02-03 Addison Kristanto Julistiono , Davoud Ataee Tarzanagh , Navid Azizan

The quadratic time and memory complexity inherent to self-attention mechanisms, with respect to sequence length, presents a critical computational bottleneck in the training and deployment of large-scale Transformer-based language models.…

Machine Learning · Computer Science 2024-03-19 Praneeth Kacham , Vahab Mirrokni , Peilin Zhong

Modern large language models become multimodal, analyzing various data formats like text and images. While fine-tuning is effective for adapting these multimodal language models (MLMs) to downstream tasks, full fine-tuning is…

Computation and Language · Computer Science 2025-12-01 Alexander Sergeev , Evgeny Kotelnikov