English
Related papers

Related papers: Interpretable and Sparse Linear Attention with Dec…

200 papers

The attention operator is arguably the key distinguishing factor of transformer architectures, which have demonstrated state-of-the-art performance on a variety of tasks. However, transformer attention operators often impose a significant…

Machine Learning · Computer Science 2024-12-24 Ziyang Wu , Tianjiao Ding , Yifu Lu , Druv Pai , Jingyuan Zhang , Weida Wang , Yaodong Yu , Yi Ma , Benjamin D. Haeffele

In this paper, we contend that the objective of representation learning is to compress and transform the distribution of the data, say sets of tokens, towards a mixture of low-dimensional Gaussian distributions supported on incoherent…

Machine Learning · Computer Science 2023-06-05 Yaodong Yu , Sam Buchanan , Druv Pai , Tianzhe Chu , Ziyang Wu , Shengbang Tong , Benjamin D. Haeffele , Yi Ma

Sparse-Linear Attention (SLA) combines sparse and linear attention to accelerate diffusion models and has shown strong performance in video generation. However, (i) SLA relies on a heuristic split that assigns computations to the sparse or…

Machine Learning · Computer Science 2026-02-16 Jintao Zhang , Haoxu Wang , Kai Jiang , Kaiwen Zheng , Youhe Jiang , Ion Stoica , Jianfei Chen , Jun Zhu , Joseph E. Gonzalez

Attention mechanisms have achieved significant empirical success in multiple fields, but their underlying optimization objectives remain unclear yet. Moreover, the quadratic complexity of self-attention has become increasingly prohibitive.…

Machine Learning · Computer Science 2025-11-06 Qishuai Wen , Zhiyuan Huang , Chun-Guang Li

Diffusion Transformers (DiTs) set the state of the art in visual generation, yet their quadratic self-attention cost fundamentally limits scaling to long token sequences. Recent Top-K sparse attention approaches reduce the computation of…

Computer Vision and Pattern Recognition · Computer Science 2025-12-19 Yifan Zhou , Zeqi Xiao , Tianyi Wei , Shuai Yang , Xingang Pan

Monocular depth estimation is a central problem in computer vision with applications in robotics, AR, and autonomous driving, yet the self-attention mechanisms that drive modern Transformer architectures remain opaque. We introduce…

Computer Vision and Pattern Recognition · Computer Science 2026-02-12 Vasileios Arampatzakis , George Pavlidis , Nikolaos Mitianoudis , Nikos Papamarkos

Nonlocal self-similarity within images has become an increasingly popular prior in deep-learning models. Despite their successful image restoration performance, such models remain largely uninterpretable due to their black-box construction.…

Image and Video Processing · Electrical Eng. & Systems 2026-02-06 Nikola Janjusevic , Amirhossein Khalilian-Gourtani , Adeen Flinker , Li Feng , Yao Wang

In this paper, we contend that a natural objective of representation learning is to compress and transform the distribution of the data, say sets of tokens, towards a low-dimensional Gaussian mixture supported on incoherent subspaces. The…

Machine Learning · Computer Science 2024-09-09 Yaodong Yu , Sam Buchanan , Druv Pai , Tianzhe Chu , Ziyang Wu , Shengbang Tong , Hao Bai , Yuexiang Zhai , Benjamin D. Haeffele , Yi Ma

Despite the popularity of transformers in practice, their architectures are empirically designed and neither mathematically justified nor interpretable. Moreover, as indicated by many empirical studies, some components of transformer…

Machine Learning · Computer Science 2025-06-05 Peng Wang , Yifu Lu , Yaodong Yu , Druv Pai , Qing Qu , Yi Ma

The maximal coding rate reduction (MCR$^2$) objective for learning structured and compact deep representations is drawing increasing attention, especially after its recent usage in the derivation of fully explainable and highly effective…

Machine Learning · Computer Science 2025-11-17 Peng Wang , Huikang Liu , Druv Pai , Yaodong Yu , Zhihui Zhu , Qing Qu , Yi Ma

Recently, Transformer-based image restoration networks have achieved promising improvements over convolutional neural networks due to parameter-independent global interactions. To lower computational cost, existing works generally limit…

Computer Vision and Pattern Recognition · Computer Science 2023-02-06 Jiale Zhang , Yulun Zhang , Jinjin Gu , Yongbing Zhang , Linghe Kong , Xin Yuan

The quadratic complexity of self-attention in Transformer models remains a significant bottleneck for processing long sequences and deploying large language models efficiently. For this approach, there has been significant research into…

Computation and Language · Computer Science 2026-05-26 Spandan Pratyush

The principle of Maximal Coding Rate Reduction (MCR$^2$) has recently been proposed as a training objective for learning discriminative low-dimensional structures intrinsic to high-dimensional data to allow for more robust training than…

Machine Learning · Computer Science 2022-04-04 Christina Baek , Ziyang Wu , Kwan Ho Ryan Chan , Tianjiao Ding , Yi Ma , Benjamin D. Haeffele

Robust principal component analysis (RPCA) decomposes an observation matrix into low-rank background and sparse object components. This capability has enabled its application in tasks ranging from image restoration to segmentation. However,…

Computer Vision and Pattern Recognition · Computer Science 2025-08-07 Fengyi Wu , Yimian Dai , Tianfang Zhang , Yixuan Ding , Jian Yang , Ming-Ming Cheng , Zhenming Peng

Attention operator has been widely used as a basic brick in visual understanding since it provides some flexibility through its adjustable kernels. However, this operator suffers from inherent limitations: (1) the attention kernel is not…

Computer Vision and Pattern Recognition · Computer Science 2025-07-04 Heeseung Kwon , Francisco M. Castro , Manuel J. Marin-Jimenez , Nicolas Guil , Karteek Alahari

In this paper, we propose a novel token selective attention approach, ToSA, which can identify tokens that need to be attended as well as those that can skip a transformer layer. More specifically, a token selector parses the current…

Computer Vision and Pattern Recognition · Computer Science 2024-06-14 Manish Kumar Singh , Rajeev Yasarla , Hong Cai , Mingu Lee , Fatih Porikli

Speculative decoding is a powerful technique for reducing the latency of Large Language Models (LLMs), offering a fault-tolerant framework that enables the use of highly compressed draft models. In this work, we introduce Self-Distilled…

Computation and Language · Computer Science 2025-06-03 Mike Lasby , Nish Sinnadurai , Valavan Manohararajah , Sean Lie , Yani Ioannou , Vithursan Thangarasa

We introduce a simple post-training method that makes transformer attention sparse without sacrificing performance. Applying a flexible sparsity regularisation under a constrained-loss objective, we show on models up to 7B parameters that…

Machine Learning · Computer Science 2026-05-26 Florent Draye , Anson Lei , Hsiao-Ru Pan , Ingmar Posner , Bernhard Schölkopf

The increasing demand for long-context modeling in large language models (LLMs) is bottlenecked by the quadratic complexity of the standard self-attention mechanism. The community has proposed sparse attention to mitigate this issue.…

Artificial Intelligence · Computer Science 2025-11-18 Jingze Shi , Yifan Wu , Yiran Peng , Bingheng Wu , Liangdong Wang , Guang Liu , Yuyu Luo

Recent advances in large language models highlighted the excessive quadratic cost of self-attention. Despite the significant research efforts, subquadratic attention methods still suffer from inferior performance in practice. We hypothesize…

Machine Learning · Computer Science 2025-05-02 Piotr Piękos , Róbert Csordás , Jürgen Schmidhuber
‹ Prev 1 2 3 10 Next ›