Zobrazeno 1 - 10
of 512
pro vyhledávání: '"Le, Qi"'
Autor:
Wang, Xinran, Le, Qi, Ahmed, Ammar, Diao, Enmao, Zhou, Yi, Baracaldo, Nathalie, Ding, Jie, Anwar, Ali
Ensuring that generative AI systems align with human values is essential but challenging, especially when considering multiple human values and their potential trade-offs. Since human values can be personalized and dynamically change over time, the d
Externí odkaz:
http://arxiv.org/abs/2410.19198
Federated Learning (FL) is a collaborative machine learning framework that allows multiple users to train models utilizing their local data in a distributed manner. However, considerable statistical heterogeneity in local data across devices often le
Externí odkaz:
http://arxiv.org/abs/2409.04986
Autor:
Gupta, Prannaya, Yau, Le Qi, Low, Hao Han, Lee, I-Shiang, Lim, Hugo Maximus, Teoh, Yu Xin, Koh, Jia Hng, Liew, Dar Win, Bhardwaj, Rishabh, Bhardwaj, Rajat, Poria, Soujanya
WalledEval is a comprehensive AI safety testing toolkit designed to evaluate large language models (LLMs). It accommodates a diverse range of models, including both open-weight and API-based ones, and features over 35 safety benchmarks covering areas
Externí odkaz:
http://arxiv.org/abs/2408.03837
A primary function of back-propagation is to compute both the gradient of hidden representations and parameters for optimization with gradient descent. Training large models requires high computational costs due to their vast parameter sizes. While P
Externí odkaz:
http://arxiv.org/abs/2404.13844
Publikováno v:
Shipin Kexue, Vol 45, Iss 20, Pp 366-375 (2024)
Alcoholic liver disease (ALD) is the most common type of chronic liver disease worldwide, manifesting as fatty liver at the early stage, and then evolving into steatohepatitis. ALD can further develop into liver fibrosis and cirrhosis with increasing
Externí odkaz:
https://doaj.org/article/b5b786d7b0e9460c96f90452e7291301
Collaborations among various entities, such as companies, research labs, AI agents, and edge devices, have become increasingly crucial for achieving machine learning tasks that cannot be accomplished by a single entity alone. This is likely due to fa
Externí odkaz:
http://arxiv.org/abs/2305.17052
Autor:
Khan, Ahmad Faraz, Wang, Xinran, Le, Qi, Abdeen, Zain ul, Khan, Azal Ahmad, Ali, Haider, Jin, Ming, Ding, Jie, Butt, Ali R., Anwar, Ali
Existing incentive solutions for traditional Federated Learning (FL) focus on individual contributions to a single global objective, neglecting the nuances of clustered personalization with multiple cluster-level models and the non-monetary incentive
Externí odkaz:
http://arxiv.org/abs/2304.07514
Recommender Systems (RSs) have become increasingly important in many application domains, such as digital marketing. Conventional RSs often need to collect users' data, centralize them on the server-side, and form a global model to generate reliable
Externí odkaz:
http://arxiv.org/abs/2212.08779
Autor:
Pu Ge, Cheng Tan, Jia-xin Liu, Qiong Cai, Si-qi Zhao, Wen-ying Hong, Kun-meng Liu, Jia-le Qi, Chen Hu, Wen-li Yu, Yi-miao Li, Yuan You, Jin-han Guo, Ming-yan Hao, Yang Chen, Lu-tong Pan, Di-yue Liu, Meng-yao Yan, Jin-zi Zhang, Qi-yu Li, Bo-ya Sun, Xiao Han, Fuer Mo, Yi-bo Wu, Ying Bian
Publikováno v:
Heliyon, Vol 10, Iss 12, Pp e32595- (2024)
Objective: To investigate the prevalence of subthreshold depression among Chinese college students and to explore the related factors. Methods: The research subjects were Chinese college students participating in the “2022 Psychology and Behavior I
Externí odkaz:
https://doaj.org/article/d3fa1f958232428185c56617cf570772
Autor:
Junyan An, Xiaotong Shi, Jun Zhang, Le Qi, Wu Xue, Xinyu Nie, Zhihe Yun, Peibiao Zhang, Qinyi Liu
Publikováno v:
Materials Today Bio, Vol 26, Iss , Pp 101030- (2024)
Externí odkaz:
https://doaj.org/article/22538918bf554ce2a459e5f9132f77ab