Zobrazeno 1 - 10
of 189
pro vyhledávání: '"Xu, Shengwei"'
We introduce the GEM (Generative Estimator for Mutual Information), an evaluation metric for assessing language generation by Large Language Models (LLMs), particularly in generating informative judgments, without the need for a gold standard referen
Externí odkaz:
http://arxiv.org/abs/2411.07127
Peer prediction mechanisms motivate high-quality feedback with provable guarantees. However, current methods only apply to rather simple reports, like multiple-choice or scalar numbers. We aim to broaden these techniques to the larger domain of text-
Externí odkaz:
http://arxiv.org/abs/2405.15077
Because high-quality data is like oxygen for AI systems, effectively eliciting information from crowdsourcing workers has become a first-order problem for developing high-performance machine learning algorithms. Two prevalent paradigms, spot-checking
Externí odkaz:
http://arxiv.org/abs/2402.13567
Autor:
Sheng, Dianmo, Chen, Dongdong, Tan, Zhentao, Liu, Qiankun, Chu, Qi, Bao, Jianmin, Gong, Tao, Liu, Bin, Xu, Shengwei, Yu, Nenghai
The rapid advancement of large language models (LLMs) has accelerated the emergence of in-context learning (ICL) as a cutting-edge approach in the natural language processing domain. Recently, ICL has been employed in visual understanding tasks, such
Externí odkaz:
http://arxiv.org/abs/2312.02520
Publikováno v:
Tongxin xuebao, Vol 45, Pp 20-36 (2024)
To solve the problems of low security and high resource overhead of existing hidden policy ciphertext policy attribute-based encryption (CP-ABE) schemes, a partially hidden policy multi-authority CP-ABE scheme with constant length ciphertext was prop
Externí odkaz:
https://doaj.org/article/d8aeb4360bfc41c99be6df3dee5077f1
Autor:
Xu, Shengwei1 (AUTHOR) 18510529691@163.com, Liu, Runsheng2 (AUTHOR) besti_paradise@163.com
Publikováno v:
Entropy. Jul2024, Vol. 26 Issue 7, p590. 23p.
Multi-round competitions often double or triple the points awarded in the final round, calling it a bonus, to maximize spectators' excitement. In a two-player competition with $n$ rounds, we aim to derive the optimal bonus size to maximize the audien
Externí odkaz:
http://arxiv.org/abs/2107.08207
Autor:
Huang, Zhihuan, Xu, Shengwei, Shan, You, Lu, Yuxuan, Kong, Yuqing, Liu, Tracy Xiao, Schoenebeck, Grant
Information flow measures, over the duration of a game, the audience's belief of who will win, and thus can reflect the amount of surprise in a game. To quantify the relationship between information flow and audiences' perceived quality, we conduct a
Externí odkaz:
http://arxiv.org/abs/2106.02851
Copy-move forgery detection identifies a tampered image by detecting pasted and source regions in the same image. In this paper, we propose a novel two-stage framework specially for copy-move forgery detection. The first stage is a backbone self deep
Externí odkaz:
http://arxiv.org/abs/2012.08697
Autor:
Nie, Enguang, Chen, Yandao, Xu, Shengwei, Yu, Zhiyang, Ye, Qingfu, Li, Qing X., Yang, Zhen, Wang, Haiyan
Publikováno v:
In Journal of Advanced Research July 2024