English
Related papers

Related papers: Less is More! A slim architecture for optimal lang…

200 papers

Transformer-based models have achieved strong performance in remote sensing image captioning by capturing long-range dependencies and contextual information. However, their practical deployment is hindered by high computational costs,…

Computer Vision and Pattern Recognition · Computer Science 2025-06-12 Swadhin Das , Divyansh Mundra , Priyanshu Dayal , Raksha Sharma

Accommodating long sequences efficiently in autoregressive Transformers, especially within an extended context window, poses significant challenges due to the quadratic computational complexity and substantial KV memory requirements…

Computation and Language · Computer Science 2024-06-25 Chao Lou , Zixia Jia , Zilong Zheng , Kewei Tu

Multimodal sentiment analysis (MSA) leverages information fusion from diverse modalities (e.g., text, audio, visual) to enhance sentiment prediction. However, simple fusion techniques often fail to account for variations in modality…

Machine Learning · Computer Science 2025-10-03 Han Wu , Yanming Sun , Yunhe Yang , Derek F. Wong

While linear attention reduces the quadratic complexity of standard Transformers to linear time, it often lags behind in expressivity due to the removal of softmax normalization. This omission eliminates \emph{global competition}, a…

Machine Learning · Computer Science 2026-02-03 Mingwei Xu , Xuan Lin , Xinnan Guo , Wanqing Xu , Wanyun Cui

The original softmax-based attention mechanism (regular attention) in the extremely successful Transformer architecture computes attention between $N$ tokens, each embedded in a $D$-dimensional head, with a time complexity of $O(N^2D)$.…

Machine Learning · Computer Science 2025-10-28 Armin Gerami , Ramani Duraiswami

Transformers have had tremendous impact for several sequence related tasks, largely due to their ability to retrieve from any part of the sequence via softmax based dot-product attention. This mechanism plays a crucial role in Transformer's…

Machine Learning · Computer Science 2025-07-15 Sai Surya Duvvuri , Inderjit S. Dhillon

Human pose estimation in complicated situations has always been a challenging task. Many Transformer-based pose networks have been proposed recently, achieving encouraging progress in improving performance. However, the remarkable…

Computer Vision and Pattern Recognition · Computer Science 2023-11-27 Chengpeng Wu , Guangxing Tan , Chunyu Li

Transformers have achieved great success in machine translation, but transformer-based NMT models often require millions of bilingual parallel corpus for training. In this paper, we propose a novel architecture named as attention link (AL)…

Computation and Language · Computer Science 2023-02-02 Zeping Min

Attention mechanisms have become ubiquitous in NLP. Recent architectures, notably the Transformer, learn powerful context-aware word representations through layered, multi-headed attention. The multiple heads learn diverse types of word…

Computation and Language · Computer Science 2019-09-09 Gonçalo M. Correia , Vlad Niculae , André F. T. Martins

Vision Transformers (ViTs) have achieved strong performance in visual recognition, yet their deployment in resource-constrained industrial environments remains limited. Some main challenges are their high computational cost, memory…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Phat Nguyen , Xue Geng , Kaixin Xu , Wang Zhe , Xulei Yang , Ngai-Man Cheung

Adaptive optimizers such as Adam have achieved great success in training large-scale models like large language models and diffusion models. However, they often generalize worse than non-adaptive methods, such as SGD on classical…

Machine Learning · Computer Science 2025-12-23 Yiheng Zhang , Shaowu Wu , Yuanzhuo Xu , Jiajun Wu , Shang Xu , Steve Drew , Xiaoguang Niu

The Transformer architecture has been successful across many domains, including natural language processing, computer vision and speech recognition. In keyword spotting, self-attention has primarily been used on top of convolutional or…

Audio and Speech Processing · Electrical Eng. & Systems 2022-04-11 Axel Berg , Mark O'Connor , Miguel Tairum Cruz

The attention mechanism is a pivotal element within the transformer architecture, making a substantial contribution to its exceptional performance. Within this attention mechanism, Softmax is an imperative component that enables the model…

Hardware Architecture · Computer Science 2024-09-05 Tianhua Xia , Sai Qian Zhang

The computational and memory challenges of large language models (LLMs) have sparked several optimization approaches towards their efficient implementation. While prior LLM-targeted quantization, and prior works on sparse acceleration have…

Hardware Architecture · Computer Science 2025-03-18 Abhishek Moitra , Arkapravo Ghosh , Shrey Agarwal , Aporva Amarnath , Karthik Swaminathan , Priyadarshini Panda

Amortized optimization accelerates the solution of related optimization problems by learning mappings that exploit shared structure across problem instances. We explore the use of Scale Equivariant Graph Metanetworks (ScaleGMNs) for this…

Artificial Intelligence · Computer Science 2025-10-10 Bart Kuipers , Freek Byrman , Daniel Uyterlinde , Alejandro García-Castellanos

Training stable biological foundation models requires rethinking attention mechanisms: we find that using sigmoid attention as a drop in replacement for softmax attention a) produces better learned representations: on six diverse…

Machine Learning · Computer Science 2026-05-01 Vijay Sadashivaiah , Georgios Dasoulas , Judith Mueller , Soumya Ghosh

The Transformer architecture is ubiquitously used as the building block of large-scale autoregressive language models. However, finding architectures with the optimal trade-off between task performance (perplexity) and hardware constraints…

The Transformer architecture has significantly advanced natural language processing (NLP) and has been foundational in developing large language models (LLMs) such as LLaMA and OPT, which have come to dominate a broad range of NLP tasks.…

Artificial Intelligence · Computer Science 2024-03-27 Youpeng Zhao , Di Wu , Jun Wang

Point cloud processing methods leverage local and global point features %at the feature level to cater to downstream tasks, yet they often overlook the task-level context inherent in point clouds during the encoding stage. We argue that…

Computer Vision and Pattern Recognition · Computer Science 2026-01-30 Yong He , Hongshan Yu , Chaoxu Mu , Mingtao Feng , Tongjia Chen , Zechuan Li , Anwaar Ulhaq , Ajmal Mian

Softmax attention defines an interaction through $d_h$ head dimensions, but not all dimensions carry equal weight once real text passes through. We decompose the attention logit field into a learned component and a generated component and…

Computation and Language · Computer Science 2026-04-09 Wonsuk Lee