Zobrazeno 1 - 10
of 424
pro vyhledávání: '"Wu Yiran"'
Publikováno v:
Science and Engineering of Composite Materials, Vol 30, Iss 1, Pp 1511-6 (2023)
In order to improve the utilization value of recycled materials, the study considers recycled materials such as polyester/nylon/spandex as raw materials. Using polyester/polyamide/spandex as raw materials, the recycled polyester/polyamide/spandex mix
Externí odkaz:
https://doaj.org/article/9c4baf5dfe3c4d02b73258a7365b2218
Autor:
Lin, Matthieu, Sheng, Jenny, Zhao, Andrew, Wang, Shenzhi, Yue, Yang, Wu, Yiran, Liu, Huan, Liu, Jun, Huang, Gao, Liu, Yong-Jin
In a compound AI system, components such as an LLM call, a retriever, a code interpreter, or tools are interconnected. The system's behavior is primarily driven by parameters such as instructions or tool definitions. Recent advancements enable end-to
Externí odkaz:
http://arxiv.org/abs/2410.16392
It is a notable trend to use Large Language Models (LLMs) to tackle complex tasks, e.g., tasks that require a sequence of actions and dynamic interaction with tools and external environments. In this paper, we propose StateFlow, a novel LLM-based tas
Externí odkaz:
http://arxiv.org/abs/2403.11322
Despite extensive pre-training in moral alignment to prevent generating harmful information, large language models (LLMs) remain vulnerable to jailbreak attacks. In this paper, we propose AutoDefense, a multi-agent defense framework that filters harm
Externí odkaz:
http://arxiv.org/abs/2403.04783
Autor:
Wu, Qingyun, Bansal, Gagan, Zhang, Jieyu, Wu, Yiran, Li, Beibin, Zhu, Erkang, Jiang, Li, Zhang, Xiaoyun, Zhang, Shaokun, Liu, Jiale, Awadallah, Ahmed Hassan, White, Ryen W, Burger, Doug, Wang, Chi
AutoGen is an open-source framework that allows developers to build LLM applications via multiple agents that can converse with each other to accomplish tasks. AutoGen agents are customizable, conversable, and can operate in various modes that employ
Externí odkaz:
http://arxiv.org/abs/2308.08155
Autor:
Zhang, Zeyu, Su, Yi, Yuan, Hui, Wu, Yiran, Balasubramanian, Rishab, Wu, Qingyun, Wang, Huazheng, Wang, Mengdi
Off-policy Learning to Rank (LTR) aims to optimize a ranker from data collected by a deployed logging policy. However, existing off-policy learning to rank methods often make strong assumptions about how users generate the click data, i.e., the click
Externí odkaz:
http://arxiv.org/abs/2306.07528
Autor:
Wu, Yiran, Jia, Feiran, Zhang, Shaokun, Li, Hangyu, Zhu, Erkang, Wang, Yue, Lee, Yin Tat, Peng, Richard, Wu, Qingyun, Wang, Chi
Employing Large Language Models (LLMs) to address mathematical problems is an intriguing research endeavor, considering the abundance of math problems expressed in natural language across numerous science and engineering fields. LLMs, with their gene
Externí odkaz:
http://arxiv.org/abs/2306.01337
In this work, we propose a hyperparameter optimization method named \emph{HyperTime} to find hyperparameters robust to potential temporal distribution shifts in the unseen test data. Our work is motivated by an important observation that it is, in ma
Externí odkaz:
http://arxiv.org/abs/2305.18421
Autor:
Ji, Ziying1 (AUTHOR), Wu, Yiran1 (AUTHOR), Liu, Lu1 (AUTHOR), Zheng, Wei2 (AUTHOR), Wu, Meng1 (AUTHOR), Li, Yuexia1 (AUTHOR), Sun, Zhengming2 (AUTHOR), Ying, Guobing1,2 (AUTHOR) gbying@seu.edu.cn
Publikováno v:
Small Structures. Nov2024, Vol. 5 Issue 11, p1-11. 11p.
Generalization in deep reinforcement learning over unseen environment variations usually requires policy learning over a large set of diverse training variations. We empirically observe that an agent trained on many variations (a generalist) tends to
Externí odkaz:
http://arxiv.org/abs/2206.12984