paper-with-me

홈 › Papers

E2ATST: A Temporal-Spatial Optimized Energy-Efficient Architecture for Training Spiking Transformer

2025-08-01 · Yunhao Ma, Yanyu Lin, Mingjing Li, Puli Quan, Chenlin Zhou, Wenyue Zhang, Zhiwei Zhong, Wanyi Jia, Xueke Zhu, Qingyan Meng, Huihui Zhou, Fengwei An arxiv

(1) Pengcheng Laboratory, (2) Southern University of Science and Technology, (3) Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, (4) University of Chinese Academy of Sciences

📄 PDF Abstract BibTeX arXiv:2508.00475

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

ATSTrack: Enhancing Visual-Language Tracking by Aligning Temporal and Spatial Scales

2025-07-01 · Yihao Zhen, Qiang Wang, Yu Qiao, Liangqiong Qu 외

A main challenge of Visual-Language Tracking (VLT) is the misalignment between visual inputs and language descriptions caused by target movement. Previous trackers have explored many effective feature modification method…

Evaluating Spatial Accelerator Architectures with Tiled Matrix-Matrix Multiplication

2021-06-19 · Gordon E. Moon, Hyoukjun Kwon, Geonhwa Jeong, Prasanth Chatarasi 외

There is a growing interest in custom spatial accelerators for machine learning applications. These accelerators employ a spatial array of processing elements (PEs) interacting via custom buffer hierarchies and networks-…

Scheduling

BuildSTG: A Multi-building Energy Load Forecasting Method using Spatio-Temporal Graph Neural Network

2025-07-28 · Yongzheng Liu, Yiming Wang, Po Xu, Yingjie Xu 외 arxiv

Due to the extensive availability of operation data, data-driven methods show strong capabilities in predicting building energy loads. Buildings with similar features often share energy patterns, reflected by spatial dep…

Graph Neural NetworkGraph Learning

Treatment Stitching with Schrödinger Bridge for Enhancing Offline Reinforcement Learning in Adaptive Treatment Strategies

2025-11-15 · Dong-Hee Shin, Deok-Joong Lee, Young-Han Son, Tae-Eui Kam arxiv

Adaptive treatment strategies (ATS) are sequential decision-making processes that enable personalized care by dynamically adjusting treatment decisions in response to evolving patient symptoms. While reinforcement learni…

Reinforcement LearningData AugmentationOffline RL

LSEAttention is All You Need for Time Series Forecasting

2024-10-31 · Dizhen Liang

Transformer-based architectures have achieved remarkable success in natural language processing and computer vision. However, their performance in multivariate long-term forecasting often falls short compared to simpler …

AllMultivariate Time Series ForecastingTime SeriesTime Series Forecasting