English
Related papers

Related papers: POTTER: Pooling Attention Transformer for Efficien…

200 papers

The quadratic complexity of transformers fundamentally limits reasoning system deployment in resource-constrained and long-context settings. We introduce Hydra, a modular architecture based upon a state-space backbone which adaptively…

Machine Learning · Computer Science 2025-10-20 Siddharth Chaudhary , Dev Patel , Maheep Chaudhary , Bennett Browning

Transformer-based multi-modal intelligent systems often suffer from high computational and energy costs due to dense self-attention, limiting their scalability under resource constraints. This paper presents SMMT, a sparse multi-modal…

Artificial Intelligence · Computer Science 2025-12-17 Cheng-Han Lu , Pei-Hsuan Tsai

Transformer has achieved great success in NLP. However, the quadratic complexity of the self-attention mechanism in Transformer makes it inefficient in handling long sequences. Many existing works explore to accelerate Transformers by…

Computation and Language · Computer Science 2021-09-03 Chuhan Wu , Fangzhao Wu , Tao Qi , Binxing Jiao , Daxin Jiang , Yongfeng Huang , Xing Xie

Transformer models have become the dominant backbone for sequence modeling, leveraging self-attention to produce contextualized token representations. These are typically aggregated into fixed-size vectors via pooling operations for…

Machine Learning · Computer Science 2025-10-07 Sofiane Ennadir , Levente Zólyomi , Oleg Smirnov , Tianze Wang , John Pertoft , Filip Cornell , Lele Cao

Deep learning-based neural receivers offer promising physical-layer solutions for next-generation wireless systems. We propose an axial self-attention transformer neural receiver that achieves state-of-the-art Block Error Rate (BLER)…

Signal Processing · Electrical Eng. & Systems 2026-03-11 SaiKrishna Saketh Yellapragada , Atchutaram K. Kocharlakota , Mário Costa , Esa Ollila , Sergiy A. Vorobyov

Transformer architectures deliver state-of-the-art accuracy via dense full-attention, but their quadratic time and memory complexity with respect to sequence length limits practical deployment. Linear attention mechanisms offer linear or…

Machine Learning · Computer Science 2026-01-21 Xiaojie Xia , Huigang Zhang , Chaoliang Zhong , Jun Sun , Yusuke Oishi

Transformers have been successfully applied in the field of video-based 3D human pose estimation. However, the high computational costs of these video pose transformers (VPTs) make them impractical on resource-constrained devices. In this…

Computer Vision and Pattern Recognition · Computer Science 2025-09-09 Wenhao Li , Mengyuan Liu , Hong Liu , Pichao Wang , Shijian Lu , Nicu Sebe

Transformers demonstrate competitive performance in terms of precision on the problem of vision-based object detection. However, they require considerable computational resources due to the quadratic size of the attention weights. In this…

Computer Vision and Pattern Recognition · Computer Science 2025-06-02 Giorgos Savathrakis , Antonis Argyros

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

End-to-end Object Detection with Transformer (DETR)proposes to perform object detection with Transformer and achieve comparable performance with two-stage object detection like Faster-RCNN. However, DETR needs huge computational resources…

Computer Vision and Pattern Recognition · Computer Science 2021-10-19 Minghang Zheng , Peng Gao , Renrui Zhang , Kunchang Li , Xiaogang Wang , Hongsheng Li , Hao Dong

The Transformer architecture has achieved remarkable success in natural language processing and high-level vision tasks over the past few years. However, the inherent complexity of self-attention is quadratic to the size of the image,…

Computer Vision and Pattern Recognition · Computer Science 2024-12-05 Pin-Hung Kuo , Jinshan Pan , Shao-Yi Chien , Ming-Hsuan Yang

Since context modeling is critical for estimating depth from a single image, researchers put tremendous effort into obtaining global context. Many global manipulations are designed for traditional CNN-based architectures to overcome the…

Computer Vision and Pattern Recognition · Computer Science 2022-05-02 Chang Shu , Ziming Chen , Lei Chen , Kuan Ma , Minghui Wang , Haibing Ren

The multi-head self-attention mechanism of the transformer model has been thoroughly investigated recently. In one vein of study, researchers are interested in understanding why and how transformers work. In another vein, researchers…

Computation and Language · Computer Science 2022-10-28 Raymond Li , Wen Xiao , Linzi Xing , Lanjun Wang , Gabriel Murray , Giuseppe Carenini

While transformers have begun to dominate many tasks in vision, applying them to large images is still computationally difficult. A large reason for this is that self-attention scales quadratically with the number of tokens, which in turn,…

Computer Vision and Pattern Recognition · Computer Science 2022-09-16 Daniel Bolya , Cheng-Yang Fu , Xiaoliang Dai , Peizhao Zhang , Judy Hoffman

In the world of deep learning, Transformer models have become very significant, leading to improvements in many areas from understanding language to recognizing images, covering a wide range of applications. Despite their success, the…

Machine Learning · Computer Science 2024-07-19 Ghadeer Jaradat , Mohammed Tolba , Ghada Alsuhli , Hani Saleh , Mahmoud Al-Qutayri , Thanos Stouraitis , Baker Mohammad

With the rapid development of autonomous driving, LiDAR-based 3D Human Pose Estimation (3D HPE) is becoming a research focus. However, due to the noise and sparsity of LiDAR-captured point clouds, robust human pose estimation remains…

Computer Vision and Pattern Recognition · Computer Science 2024-12-19 Xiaoqi An , Lin Zhao , Chen Gong , Jun Li , Jian Yang

Transformer-based models have achieved dominant performance in numerous NLP tasks. Despite their remarkable successes, pre-trained transformers such as BERT suffer from a computationally expensive self-attention mechanism that interacts…

Computation and Language · Computer Science 2024-06-04 Jungmin Yun , Mihyeon Kim , Youngbin Kim

Diffusion models have recently gained state of the art performance on many image generation tasks. However, most models require significant computational resources to achieve this. This becomes apparent in the application of medical image…

Computer Vision and Pattern Recognition · Computer Science 2025-04-16 Karan Jain , Mohammad Nayeem Teli

This paper presents CONTHER, a novel reinforcement learning algorithm designed to efficiently and rapidly train robotic agents for goal-oriented manipulation tasks and obstacle avoidance. The algorithm uses a modified replay buffer inspired…

Robotics · Computer Science 2025-03-21 Maria Makarova , Qian Liu , Dzmitry Tsetserukou

Self-attention has recently been adopted for a wide range of sequence modeling problems. Despite its effectiveness, self-attention suffers from quadratic compute and memory requirements with respect to sequence length. Successful approaches…

Machine Learning · Computer Science 2020-10-27 Aurko Roy , Mohammad Saffar , Ashish Vaswani , David Grangier