Zobrazeno 1 - 10
of 924
pro vyhledávání: '"LIU Zicheng"'
Publikováno v:
IET Energy Systems Integration, Vol 5, Iss 1, Pp 80-94 (2023)
Abstract With the high‐proportion integration of renewable energy and power electronic equipment, the inertia supporting ability of new power system continues to decline, which seriously threatens the frequency stability of power grids. In order to
Externí odkaz:
https://doaj.org/article/876973ec68bd47fe9a486470c65a4b91
Recently, Vision Large Language Models (VLLMs) integrated with vision encoders have shown promising performance in vision understanding. The key of VLLMs is to encode visual content into sequences of visual tokens, enabling VLLMs to simultaneously pr
Externí odkaz:
http://arxiv.org/abs/2412.09919
Text-to-image diffusion models have demonstrated tremendous success in synthesizing visually stunning images given textual instructions. Despite remarkable progress in creating high-fidelity visuals, text-to-image models can still struggle with preci
Externí odkaz:
http://arxiv.org/abs/2411.16713
Autor:
Li, Siyuan, Tian, Juanxi, Wang, Zedong, Zhang, Luyuan, Liu, Zicheng, Jin, Weiyang, Liu, Yang, Sun, Baigui, Li, Stan Z.
This paper delves into the interplay between vision backbones and optimizers, unvealing an inter-dependent phenomenon termed \textit{\textbf{b}ackbone-\textbf{o}ptimizer \textbf{c}oupling \textbf{b}ias} (BOCB). We observe that canonical CNNs, such as
Externí odkaz:
http://arxiv.org/abs/2410.06373
Recent advancements in timestep-distilled diffusion models have enabled high-quality image generation that rivals non-distilled multi-step models, but with significantly fewer inference steps. While such models are attractive for applications due to
Externí odkaz:
http://arxiv.org/abs/2410.03190
Publikováno v:
电力工程技术, Vol 41, Iss 4, Pp 18-24,107 (2022)
The new power system is gradually evolving into a low inertia power system with high penetration of DC and new energy, and the inertia of the load side is gradually increasing. Asynchronous motors occupy a high proportion in the load side, and their
Externí odkaz:
https://doaj.org/article/200496b3fd704b1ca9c95e07eb35dde6
Autor:
Cui, Qinpeng, Liu, Yixuan, Zhang, Xinyi, Bao, Qiqi, Liao, Qingmin, Wang, Li, Lu, Tian, Liu, Zicheng, Wang, Zhongdao, Barsoum, Emad
Diffusion-based image super-resolution (SR) models have attracted substantial interest due to their powerful image restoration capabilities. However, prevailing diffusion models often struggle to strike an optimal balance between efficiency and perfo
Externí odkaz:
http://arxiv.org/abs/2409.17778
Autor:
Jin, Xin, Zhu, Hongyu, Li, Siyuan, Wang, Zedong, Liu, Zicheng, Yu, Chang, Qin, Huafeng, Li, Stan Z.
As Deep Neural Networks have achieved thrilling breakthroughs in the past decade, data augmentations have garnered increasing attention as regularization techniques when massive labeled data are unavailable. Among existing augmentations, Mixup and re
Externí odkaz:
http://arxiv.org/abs/2409.05202
Autor:
Ni, Minheng, Wu, Chenfei, Yuan, Huaying, Yang, Zhengyuan, Gong, Ming, Wang, Lijuan, Liu, Zicheng, Zuo, Wangmeng, Duan, Nan
With the advancement of generative models, the synthesis of different sensory elements such as music, visuals, and speech has achieved significant realism. However, the approach to generate multi-sensory outputs has not been fully explored, limiting
Externí odkaz:
http://arxiv.org/abs/2408.11564
Autor:
Yu, Weihao, Yang, Zhengyuan, Ren, Lingfeng, Li, Linjie, Wang, Jianfeng, Lin, Kevin, Lin, Chung-Ching, Liu, Zicheng, Wang, Lijuan, Wang, Xinchao
MM-Vet, with open-ended vision-language questions targeting at evaluating integrated capabilities, has become one of the most popular benchmarks for large multimodal model evaluation. MM-Vet assesses six core vision-language (VL) capabilities: recogn
Externí odkaz:
http://arxiv.org/abs/2408.00765