Zobrazeno 1 - 10
of 172 098
pro vyhledávání: '"AN Jingjing"'
Publikováno v:
Zhongguo quanke yixue, Vol 26, Iss 09, Pp 1146-1150 (2023)
As a major treatment for coronary artery disease, percutaneous coronary intervention (PCI) effectively enhances the survival rate of patients. However, the post-PCI in-stent restenosis has become a new cardiovascular problem that is difficult to solv
Externí odkaz:
https://doaj.org/article/a72ad874135a4bea886f54cec593c4b7
Autor:
Zhang, Jiajian, Huang, Wenhui, Chu, Ji, Qiu, Jiawei, Sun, Xuandong, Tao, Ziyu, Zhang, Jiawei, Zhang, Libo, Zhou, Yuxuan, Chen, Yuanzhen, Liu, Yang, Liu, Song, Zhong, Youpeng, Miao, Jian-Jian, Niu, Jingjing, Yu, Dapeng
Fock-state lattices (FSLs), composed of photon number states with infinite Hilbert space, have emerged as a promising platform for simulating high-dimensional physics due to their potential to extend into arbitrarily high dimensions. Here, we demonst
Externí odkaz:
http://arxiv.org/abs/2412.09766
Autor:
Zheng, Jingjing, Cao, Yankai
In this work, we propose a novel Parameter-Efficient Fine-Tuning (PEFT) approach based on Gaussian Graphical Models (GGMs), marking the first application of GGMs to PEFT tasks, to the best of our knowledge. The proposed method utilizes the $\ell_{2,g
Externí odkaz:
http://arxiv.org/abs/2412.08592
Despite the efficiency of prompt learning in transferring vision-language models (VLMs) to downstream tasks, existing methods mainly learn the prompts in a coarse-grained manner where the learned prompt vectors are shared across all categories. Conse
Externí odkaz:
http://arxiv.org/abs/2412.08176
Autor:
Chen, Jiawei, Chen, Wentao, Su, Jing, Xu, Jingjing, Lin, Hongyu, Ren, Mengjie, Lu, Yaojie, Han, Xianpei, Sun, Le
Large language models (LLMs) have shown significant multilingual capabilities. However, the mechanisms underlying the development of these capabilities during pre-training are not well understood. In this paper, we use code LLMs as an experimental pl
Externí odkaz:
http://arxiv.org/abs/2412.07298
To effectively manage and utilize massive distributed data at the network edge, Federated Learning (FL) has emerged as a promising edge computing paradigm across data silos. However, FL still faces two challenges: system heterogeneity (i.e., the dive
Externí odkaz:
http://arxiv.org/abs/2412.07216
Surgical workflow anticipation is the task of predicting the timing of relevant surgical events from live video data, which is critical in Robotic-Assisted Surgery (RAS). Accurate predictions require the use of spatial information to model surgical i
Externí odkaz:
http://arxiv.org/abs/2412.06454
Publikováno v:
CHI'2024: Workshop of the CHI Conference on Human Factors in Computing Systems, May 11--16, 2024, Honolulu, HI, USA
Immigration and aging have always been significant topics of discussion in society, concerning the stability and future development of a country and its people. Research in the field of HCI on immigration and aging has primarily focused on their prac
Externí odkaz:
http://arxiv.org/abs/2412.05119
Artificial Intelligence significantly enhances the visual art industry by analyzing, identifying and generating digitized artistic images. This review highlights the substantial benefits of integrating geometric data into AI models, addressing challe
Externí odkaz:
http://arxiv.org/abs/2412.01450
Autor:
Song, Xue, Cui, Jiequan, Zhang, Hanwang, Shi, Jiaxin, Chen, Jingjing, Zhang, Chi, Jiang, Yu-Gang
In this paper, we propose the LoRA of Change (LoC) framework for image editing with visual instructions, i.e., before-after image pairs. Compared to the ambiguities, insufficient specificity, and diverse interpretations of natural language, visual in
Externí odkaz:
http://arxiv.org/abs/2411.19156