Zobrazeno 1 - 10
of 3 107
pro vyhledávání: '"Zhang, YuLong"'
Low-Rank Adaptation (LoRA) is a parameter-efficient technique for rapidly fine-tuning foundation models. In standard LoRA training dynamics, models tend to quickly converge to a local optimum near the initialization. However, this local optimum may n
Externí odkaz:
http://arxiv.org/abs/2410.22911
Autor:
Yu, Tianyuan, Ma, Xinyu, Patil, Varun, Kocaogullar, Yekta, Zhang, Yulong, Burke, Jeff, Kutscher, Dirk, Zhang, Lixia
This position paper explores how to support the Web's evolution through an underlying data-centric approach that better matches the data-orientedness of modern and emerging applications. We revisit the original vision of the Web as a hypermedia syste
Externí odkaz:
http://arxiv.org/abs/2407.15221
Empirical Risk Minimization (ERM) is fragile in scenarios with insufficient labeled samples. A vanilla extension of ERM to unlabeled samples is Entropy Minimization (EntMin), which employs the soft-labels of unlabeled samples to guide their learning.
Externí odkaz:
http://arxiv.org/abs/2406.02862
Recent advances achieved by deep learning models rely on the independent and identically distributed assumption, hindering their applications in real-world scenarios with domain shifts. To tackle this issue, cross-domain learning aims at extracting d
Externí odkaz:
http://arxiv.org/abs/2401.03253
Limited transferability hinders the performance of deep learning models when applied to new application scenarios. Recently, Unsupervised Domain Adaptation (UDA) has achieved significant progress in addressing this issue via learning domain-invariant
Externí odkaz:
http://arxiv.org/abs/2309.14360
Information-Centric Networking (ICN), with its data-oriented operation and generally more powerful forwarding layer, provides an attractive platform for distributed computing. This paper provides a systematic overview and categorization of different
Externí odkaz:
http://arxiv.org/abs/2309.08973
Limited transferability hinders the performance of deep learning models when applied to new application scenarios. Recently, unsupervised domain adaptation (UDA) has achieved significant progress in addressing this issue via learning domain-invariant
Externí odkaz:
http://arxiv.org/abs/2303.12724
Autor:
CHENG Zhiliang, ZHANG Yulong, YANG Han, HA Hui, WANG Yingdi, CHEN Feifei, LIU Fei, JIAO Yuehua
Publikováno v:
Shipin Kexue, Vol 45, Iss 12, Pp 292-303 (2024)
Type 2 diabetes mellitus (T2DM), a chronic metabolic disease caused by an imbalance between carbohydrate intake and metabolism, is one of the most difficult metabolic diseases to treat worldwide. The main symptoms of T2DM include hyperglycemia, insuf
Externí odkaz:
https://doaj.org/article/74ab6f1b00c54b03bc0b9069559ab085
Autor:
Rotti, Pavana G., Yi, Yaling, Gasser, Grace, Yuan, Feng, Sun, Xingshen, Apak-Evans, Idil, Wu, Peipei, Liu, Guangming, Choi, Soon, Reeves, Rosie, Scioneaux, Attilina E., Zhang, Yulong, Winter, Michael, Liang, Bo, Cunicelli, Nathan, Uc, Aliye, Norris, Andrew W., Sussel, Lori, Wells, Kristen L., Engelhardt, John F.
Publikováno v:
In iScience 20 December 2024 27(12)
Autor:
Tan, Jiaqu, Tian, Zhuoxun, Qin, Fengjie, Kong, Qiaojuan, Li, Dongya, Yang, Fan, Zhang, Zhen, Zhang, Yulong, Li, Yongtao, Lin, Xueming
Publikováno v:
In Chemical Engineering Journal 15 December 2024 502