Zobrazeno 1 - 10
of 297
pro vyhledávání: '"Zhou, Yutong"'
Autor:
Zhou, Yutong, Shimada, Nobutaka
Text-to-image generation has attracted significant interest from researchers and practitioners in recent years due to its widespread and diverse applications across various industries. Despite the progress made in the domain of vision and language re
Externí odkaz:
http://arxiv.org/abs/2305.14598
Autor:
Zhou, Yutong
We propose a cyclic generative adversarial network with spatial-wise and channel-wise attention modules for text-to-image synthesis. To accurately depict and design scenes with multiple occluded objects, we design a pre-trained ordering recovery mode
Externí odkaz:
http://arxiv.org/abs/2305.14522
Publikováno v:
Jisuanji kexue yu tansuo, Vol 18, Iss 5, Pp 1339-1347 (2024)
Emotional dialogue generation models do not consider the emotional intensity factor in response generation, which leads to the inappropriateness of the emotional expression in generated response, and reduces the user interaction experience. Inspired
Externí odkaz:
https://doaj.org/article/f38c180bc0b74f9c9ea6381fd8d1c002
Autor:
Mosca, Edoardo, Dementieva, Daryna, Ajdari, Tohid Ebrahim, Kummeth, Maximilian, Gringauz, Kirill, Zhou, Yutong, Groh, Georg
Interpretability and human oversight are fundamental pillars of deploying complex NLP models into real-world applications. However, applying explainability and human-in-the-loop methods requires technical proficiency. Despite existing toolkits for mo
Externí odkaz:
http://arxiv.org/abs/2303.03124
Autor:
Qiu, Lvchao1 (AUTHOR), Zhou, Yutong1 (AUTHOR), Zhao, Zhoufeng1 (AUTHOR), Wang, Qi2 (AUTHOR), Chu, Lijun2 (AUTHOR), Wen, Shipeng2 (AUTHOR) wensp@mail.buct.edu.cn
Publikováno v:
Polymers (20734360). May2024, Vol. 16 Issue 10, p1309. 13p.
Autor:
Zhou, Yutong1 (AUTHOR), Qiu, Lvchao1 (AUTHOR), Xu, Zongchao2 (AUTHOR) niejingkai@geiri.sgcc.com.cn, Huang, Shixuan3 (AUTHOR), Nie, Jingkai2 (AUTHOR) yinhang@geiri.sgcc.com.cn, Yin, Hang2 (AUTHOR), Tu, Feng3 (AUTHOR), Zhao, Zhoufeng1 (AUTHOR)
Publikováno v:
Polymers (20734360). May2024, Vol. 16 Issue 9, p1186. 13p.
Publikováno v:
Jisuanji kexue yu tansuo, Vol 18, Iss 1, Pp 58-74 (2024)
Knowledge-driven dialogue generation models aim to enhance dialogue generation models by using different forms of knowledge, so that dialogue generation models can not only learn semantic interactions from dialogue data, but also deeply understand us
Externí odkaz:
https://doaj.org/article/1683eb357df74be38d3109ea4fce13f1
Publikováno v:
Zhejiang dianli, Vol 42, Iss 11, Pp 72-77 (2023)
Nitrile butadiene rubber (NBR) is a crucial sealing material for oil-immersed equipment, and its properties have a direct impact on the safe operation of equipment. With elastic strain energy density and hardness as the property parameters, t
Externí odkaz:
https://doaj.org/article/feaa160d1150473498543e0d509859f2
Mining aligned natural language (NL) and programming language (PL) pairs is a critical task to NL-PL understanding. Existing methods applied specialized hand-crafted features or separately-trained models for each PL. However, they usually suffered fr
Externí odkaz:
http://arxiv.org/abs/2203.10744
Publikováno v:
In Chemical Engineering Journal 1 July 2024 491