English
Related papers

Related papers: Hierarchical Kernel Transformer: Multi-Scale Atten…

200 papers

The attention mechanisms are playing a boosting role in advancements in sequence-to-sequence problems. Transformer architecture achieved new state of the art results in machine translation, and it's variants are since being introduced in…

Machine Learning · Computer Science 2020-05-12 Abhishek Niranjan , M Ali Basha Shaik , Kushal Verma

Fine-tuning pre-trained Vision Transformers (ViTs) has showcased significant promise in enhancing visual recognition tasks. Yet, the demand for individualized and comprehensive fine-tuning processes for each task entails substantial…

Computer Vision and Pattern Recognition · Computer Science 2024-05-16 Weifeng Lin , Ziheng Wu , Wentao Yang , Mingxin Huang , Jun Huang , Lianwen Jin

Kernel matrices are ubiquitous in computational mathematics, often arising from applications in machine learning and scientific computing. In two or three spatial or feature dimensions, such problems can be approximated efficiently by a…

Numerical Analysis · Mathematics 2025-11-07 Abraham Khan , Chao Chen , Vishwas Rao , Arvind K. Saibaba

Transformer-based LLMs achieve strong results on many language tasks; however, long inputs remain challenging because context windows are finite, and prefill latency and memory grow rapidly with prompt length. Flat token-stream processing…

Computation and Language · Computer Science 2026-05-26 Maryam Haghifam , Zifan He , Jason Cong , Yizhou Sun

Hierarchical text classification (HTC) is a special sub-task of multi-label classification (MLC) whose taxonomy is constructed as a tree and each sample is assigned with at least one path in the tree. Latest HTC models contain three…

Computation and Language · Computer Science 2024-08-13 Zhijian Chen , Zhonghua Li , Jianxin Yang , Ye Qi

Feature fusion plays a pivotal role in achieving high performance in vision models, yet existing attention-based fusion techniques often suffer from substantial computational overhead and implementation complexity, particularly in…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Junyi Hu , Tian Bai , Fengyi Wu , Zhenming Peng , Yi Zhang

Constrained by the low-rank bottleneck inherent in attention mechanisms, current stereo matching transformers suffer from limited nonlinear expressivity, which renders their feature representations sensitive to challenging conditions such…

Computer Vision and Pattern Recognition · Computer Science 2025-08-26 Ziyang Chen , Wenting Li , Yongjun Zhang , Yabo Wu , Bingshu Wang , Yong Zhao , C. L. Philip Chen

Linearization of attention using various kernel approximation and kernel learning techniques has shown promise. Past methods used a subset of combinations of component functions and weight matrices within the random feature paradigm. We…

Machine Learning · Computer Science 2025-09-24 Duke Nguyen , Du Yin , Aditya Joshi , Flora Salim

Transformer-based semantic retrieval is highly effective, yet in many deployments the dominant cost lies in online query encoding rather than corpus indexing. We study the fixed-teacher query-adaptation problem and ask whether repeated…

Machine Learning · Computer Science 2026-05-06 Mohit Kumar , Somayeh Kargaran , Bernhard A. Moser , Manuela Geiß

Hierarchical clustering (HC) is an important data analysis technique in which the goal is to recursively partition a dataset into a tree-like structure while grouping together similar data points at each level of granularity. Unfortunately,…

Data Structures and Algorithms · Computer Science 2025-06-09 Vladimir Braverman , Jon C. Ergun , Chen Wang , Samson Zhou

Transformers are built upon multi-head scaled dot-product attention and positional encoding, which aim to learn the feature representations and token dependencies. In this work, we focus on enhancing the distinctive representation by…

Computer Vision and Pattern Recognition · Computer Science 2022-07-12 Litao Yu , Jian Zhang

The blind image deconvolution is a challenging, highly ill-posed nonlinear inverse problem. We introduce a Multiscale Hierarchical Decomposition Method (MHDM) that is iteratively solving variational problems with adaptive data and…

Numerical Analysis · Mathematics 2025-08-21 Tobias Wolf , Stefan Kindermann , Elena Resmerita , Luminita Vese

Attention-based models, exemplified by the Transformer, can effectively model long range dependency, but suffer from the quadratic complexity of self-attention operation, making them difficult to be adopted for high-resolution image…

Computer Vision and Pattern Recognition · Computer Science 2021-12-28 Long Zhao , Zizhao Zhang , Ting Chen , Dimitris N. Metaxas , Han Zhang

In order to learn quickly with few samples, meta-learning utilizes prior knowledge learned from previous tasks. However, a critical challenge in meta-learning is task uncertainty and heterogeneity, which can not be handled via globally…

Machine Learning · Computer Science 2019-11-19 Huaxiu Yao , Ying Wei , Junzhou Huang , Zhenhui Li

Attention mechanisms in sequence to sequence models have shown great ability and wonderful performance in various natural language processing (NLP) tasks, such as sentence embedding, text generation, machine translation, machine reading…

Computation and Language · Computer Science 2018-08-14 Zehao Dou , Zhihua Zhang

This work proposes an attention-based sequence-to-sequence model for handwritten word recognition and explores transfer learning for data-efficient training of HTR systems. To overcome training data scarcity, this work leverages models…

Computer Vision and Pattern Recognition · Computer Science 2022-09-13 Dmitrijs Kass , Ekta Vats

The transformer has revolutionized modern AI across language, vision, and beyond. It consists of $L$ layers, each running $H$ attention heads in parallel and feeding the combined output to the subsequent layer. In attention, the input…

Computational Complexity · Computer Science 2026-03-13 Barna Saha , Yinzhan Xu , Christopher Ye , Hantao Yu

Decoding-free reranking methods that read relevance signals directly from LLM attention weights offer significant latency advantages over autoregressive approaches, yet suffer from attention score homogenization: middle-context documents…

Information Retrieval · Computer Science 2026-05-20 Juyuan Wang , Chenxing Wang , Yuchen Fang , Huiyun Hu , Junwu Du , Aolin Li , Shunlin Rong , Haijun Wu , Jin Xu , Ligang Liu , Dongliang Liao

Understanding relationships between attention heads is essential for interpreting the internal structure of Transformers, yet existing metrics do not capture this structure well. We focus on the subspaces spanned by attention-head weight…

Computation and Language · Computer Science 2026-01-16 Hiroaki Yamagiwa , Yusuke Takase , Hidetoshi Shimodaira

Multi-head attention layers, as used in the Transformer neural sequence model, are a powerful alternative to RNNs for moving information across and between sequences. While training these layers is generally fast and simple, due to…

Neural and Evolutionary Computing · Computer Science 2019-11-07 Noam Shazeer