Zobrazeno 1 - 10
of 998
pro vyhledávání: '"Zhao Haoran"'
In the rapidly evolving field of legal analytics, finding relevant cases and accurately predicting judicial outcomes are challenging because of the complexity of legal language, which often includes specialized terminology, complex syntax, and histor
Externí odkaz:
http://arxiv.org/abs/2407.21065
Given starting and ending positions and velocities, $L_2$ bounds on the acceleration and velocity, and the restriction to no more than two constant control inputs, this paper provides routines to compute the minimal-time path. Closed form solutions a
Externí odkaz:
http://arxiv.org/abs/2403.04602
Autor:
Zhao, Haoran, Naylor, Andrew, Hsu, Shih-Chieh, Calafiura, Paolo, Farrell, Steven, Feng, Yongbing, Harris, Philip Coleman, Khoda, Elham E, Mccormack, William Patrick, Rankin, Dylan Sheldon, Ju, Xiangyang
Recent studies have shown promising results for track finding in dense environments using Graph Neural Network (GNN)-based algorithms. However, GNN-based track finding is computationally slow on CPUs, necessitating the use of coprocessors to accelera
Externí odkaz:
http://arxiv.org/abs/2402.09633
Autor:
Zhao, Haoran, Uy, Wayne Isaac Tan
Stochastic generators are essential to produce synthetic realizations that preserve target statistical properties. We propose GenFormer, a stochastic generator for spatio-temporal multivariate stochastic processes. It is constructed using a Transform
Externí odkaz:
http://arxiv.org/abs/2402.02010
Autor:
Yu, Guochen, Han, Runqiang, Xu, Chenglin, Zhao, Haoran, Li, Nan, Zhang, Chen, Zheng, Xiguang, Zhou, Chao, Huang, Qi, Yu, Bing
This paper presents the speech restoration and enhancement system created by the 1024K team for the ICASSP 2024 Speech Signal Improvement (SSI) Challenge. Our system consists of a generative adversarial network (GAN) in complex-domain for speech rest
Externí odkaz:
http://arxiv.org/abs/2402.01808
Autor:
Yang, Kaiyuan, Musio, Fabio, Ma, Yihui, Juchler, Norman, Paetzold, Johannes C., Al-Maskari, Rami, Höher, Luciano, Li, Hongwei Bran, Hamamci, Ibrahim Ethem, Sekuboyina, Anjany, Shit, Suprosanna, Huang, Houjing, Prabhakar, Chinmay, de la Rosa, Ezequiel, Waldmannstetter, Diana, Kofler, Florian, Navarro, Fernando, Menten, Martin, Ezhov, Ivan, Rueckert, Daniel, Vos, Iris, Ruigrok, Ynte, Velthuis, Birgitta, Kuijf, Hugo, Hämmerli, Julien, Wurster, Catherine, Bijlenga, Philippe, Westphal, Laura, Bisschop, Jeroen, Colombo, Elisa, Baazaoui, Hakim, Makmur, Andrew, Hallinan, James, Wiestler, Bene, Kirschke, Jan S., Wiest, Roland, Montagnon, Emmanuel, Letourneau-Guillon, Laurent, Galdran, Adrian, Galati, Francesco, Falcetta, Daniele, Zuluaga, Maria A., Lin, Chaolong, Zhao, Haoran, Zhang, Zehan, Ra, Sinyoung, Hwang, Jongyun, Park, Hyunjin, Chen, Junqiang, Wodzinski, Marek, Müller, Henning, Shi, Pengcheng, Liu, Wei, Ma, Ting, Yalçin, Cansu, Hamadache, Rachika E., Salvi, Joaquim, Llado, Xavier, Estrada, Uma Maria Lal-Trehan, Abramova, Valeriia, Giancardo, Luca, Oliver, Arnau, Liu, Jialu, Huang, Haibin, Cui, Yue, Lin, Zehang, Liu, Yusheng, Zhu, Shunzhi, Patel, Tatsat R., Tutino, Vincent M., Orouskhani, Maysam, Wang, Huayu, Mossa-Basha, Mahmud, Zhu, Chengcheng, Rokuss, Maximilian R., Kirchhoff, Yannick, Disch, Nico, Holzschuh, Julius, Isensee, Fabian, Maier-Hein, Klaus, Sato, Yuki, Hirsch, Sven, Wegener, Susanne, Menze, Bjoern
The Circle of Willis (CoW) is an important network of arteries connecting major circulations of the brain. Its vascular architecture is believed to affect the risk, severity, and clinical outcome of serious neuro-vascular diseases. However, character
Externí odkaz:
http://arxiv.org/abs/2312.17670
Autor:
Zhao, Haoran, Williams, Jake Ryland
While Large Language Models (LLMs) become ever more dominant, classic pre-trained word embeddings sustain their relevance through computational efficiency and nuanced linguistic interpretation. Drawing from recent studies demonstrating that the conve
Externí odkaz:
http://arxiv.org/abs/2311.11012
Autor:
Williams, Jake Ryland, Zhao, Haoran
Iterative approximation methods using backpropagation enable the optimization of neural networks, but they remain computationally expensive, especially when used at scale. This paper presents an efficient alternative for optimizing neural networks th
Externí odkaz:
http://arxiv.org/abs/2311.07510
Autor:
Williams, Jake Ryland, Zhao, Haoran
Iterative differential approximation methods that rely upon backpropagation have enabled the optimization of neural networks; however, at present, they remain computationally expensive, especially when training models at scale. In this paper, we prop
Externí odkaz:
http://arxiv.org/abs/2311.07498
Autor:
Chen, Mingcheng, Zhao, Haoran, Zhao, Yuxiang, Fan, Hulei, Gao, Hongqiao, Yu, Yong, Tian, Zheng
Data-driven black-box model-based optimization (MBO) problems arise in a great number of practical application scenarios, where the goal is to find a design over the whole space maximizing a black-box target function based on a static offline dataset
Externí odkaz:
http://arxiv.org/abs/2310.07560