Zobrazeno 1 - 10
of 2 545
pro vyhledávání: '"CHEN Xinyi"'
Autor:
LI Haoping, DU Xinyi, ZHU Chengbiao, JIN Zhuhong, CHEN Xinyi, YU Botao, LI Jingrui, AN Yuting
Publikováno v:
Taiyuan Ligong Daxue xuebao, Vol 55, Iss 4, Pp 603-611 (2024)
Purposes In actual processing of factories, the varying health status of each machine can cause machine failures and subsequently affect the processing and construction time. This article focuses on the problem of flexible job shops with machine dist
Externí odkaz:
https://doaj.org/article/445916c9cd05423b85123828683294cf
Publikováno v:
Energy Reports, Vol 9, Iss , Pp 391-402 (2023)
Seawater desalination is one of the effective means to efficiently consume renewable energy and to improve the flexibility of system control in the new power system. In the optimal operation of new power systems, seawater desalination is usually cons
Externí odkaz:
https://doaj.org/article/d5d12e30bee14c709b573915df3d35a6
Autor:
Zhou, Zihan, Li, Chong, Chen, Xinyi, Wang, Shuo, Chao, Yu, Li, Zhili, Wang, Haoyu, An, Rongqiao, Shi, Qi, Tan, Zhixing, Han, Xu, Shi, Xiaodong, Liu, Zhiyuan, Sun, Maosong
Enlarging the context window of large language models (LLMs) has become a crucial research area, particularly for applications involving extremely long texts. In this work, we propose a novel training-free framework for processing long texts, utilizi
Externí odkaz:
http://arxiv.org/abs/2410.09342
Shadow detection is crucial for accurate scene understanding in computer vision, yet it is challenged by the diverse appearances of shadows caused by variations in illumination, object geometry, and scene context. Deep learning models often struggle
Externí odkaz:
http://arxiv.org/abs/2410.07695
Autor:
Agarwal, Naman, Chen, Xinyi, Dogariu, Evan, Feinberg, Vlad, Suo, Daniel, Bartlett, Peter, Hazan, Elad
We address the challenge of efficient auto-regressive generation in sequence prediction models by introducing FutureFill: a method for fast generation that applies to any sequence prediction algorithm based on convolutional operators. Our approach re
Externí odkaz:
http://arxiv.org/abs/2410.03766
Autor:
Zheng, Fuchen, Chen, Xinyi, Chen, Xuhang, Li, Haolun, Guo, Xiaojiao, Huang, Guoheng, Pun, Chi-Man, Zhou, Shoujun
Medical image segmentation, a crucial task in computer vision, facilitates the automated delineation of anatomical structures and pathologies, supporting clinicians in diagnosis, treatment planning, and disease monitoring. Notably, transformers emplo
Externí odkaz:
http://arxiv.org/abs/2409.07779
Spiking Neural Networks (SNNs) hold great potential to realize brain-inspired, energy-efficient computational systems. However, current SNNs still fall short in terms of multi-scale temporal processing compared to their biological counterparts. This
Externí odkaz:
http://arxiv.org/abs/2408.14917
This paper introduces FALCON, a novel Fast Autonomous expLoration framework using COverage path guidaNce, which aims at setting a new performance benchmark in the field of autonomous aerial exploration. Despite recent advancements in the domain, exis
Externí odkaz:
http://arxiv.org/abs/2407.00577
Autor:
Zhang, Yichen, Chen, Xinyi, Liu, Peize, Wang, Junzhe, Zou, Hetai, Pan, Neng, Gao, Fei, Shen, Shaojie
As quadrotors take on an increasingly diverse range of roles, researchers often need to develop new hardware platforms tailored for specific tasks, introducing significant engineering overhead. In this article, we introduce the UniQuad series, a unif
Externí odkaz:
http://arxiv.org/abs/2407.00578
Autor:
Chen, Xinyi, Liao, Baohao, Qi, Jirui, Eustratiadis, Panagiotis, Monz, Christof, Bisazza, Arianna, de Rijke, Maarten
Following multiple instructions is a crucial ability for large language models (LLMs). Evaluating this ability comes with significant challenges: (i) limited coherence between multiple instructions, (ii) positional bias where the order of instruction
Externí odkaz:
http://arxiv.org/abs/2406.19999