Zobrazeno 1 - 10
of 47
pro vyhledávání: '"Zhu, Tinghui"'
Large Vision-Language Models (LVLMs) have demonstrated impressive capabilities for capturing and reasoning over multimodal inputs. However, these models are prone to parametric knowledge conflicts, which arise from inconsistencies of represented know
Externí odkaz:
http://arxiv.org/abs/2410.03659
Autor:
Chen, Jiangjie, Wang, Xintao, Xu, Rui, Yuan, Siyu, Zhang, Yikai, Shi, Wei, Xie, Jian, Li, Shuang, Yang, Ruihan, Zhu, Tinghui, Chen, Aili, Li, Nianqi, Chen, Lida, Hu, Caiyu, Wu, Siye, Ren, Scott, Fu, Ziquan, Xiao, Yanghua
Recent advancements in large language models (LLMs) have significantly boosted the rise of Role-Playing Language Agents (RPLAs), i.e., specialized AI systems designed to simulate assigned personas. By harnessing multiple advanced abilities of LLMs, i
Externí odkaz:
http://arxiv.org/abs/2404.18231
By leveraging the retrieval of information from external knowledge databases, Large Language Models (LLMs) exhibit enhanced capabilities for accomplishing many knowledge-intensive tasks. However, due to the inherent flaws of current retrieval systems
Externí odkaz:
http://arxiv.org/abs/2404.03302
Autor:
Xie, Jian, Zhang, Kai, Chen, Jiangjie, Zhu, Tinghui, Lou, Renze, Tian, Yuandong, Xiao, Yanghua, Su, Yu
Planning has been part of the core pursuit for artificial intelligence since its conception, but earlier AI agents mostly focused on constrained settings because many of the cognitive substrates necessary for human-level planning have been lacking. R
Externí odkaz:
http://arxiv.org/abs/2402.01622
Recent advancements have significantly augmented the reasoning capabilities of Large Language Models (LLMs) through various methodologies, especially chain-of-thought (CoT) reasoning. However, previous methods fail to address reasoning errors in inte
Externí odkaz:
http://arxiv.org/abs/2401.17686
Autor:
Zhu, Tinghui, Liu, Jingping, Liang, Jiaqing, Jiang, Haiyun, Xiao, Yanghua, Wang, Zongyu, Xie, Rui, Xian, Yunsen
Taxonomy expansion task is essential in organizing the ever-increasing volume of new concepts into existing taxonomies. Most existing methods focus exclusively on using textual semantics, leading to an inability to generalize to unseen terms and the
Externí odkaz:
http://arxiv.org/abs/2309.06105
Publikováno v:
In Neurocomputing 14 October 2023 554
Autor:
Xu, Jun, Zhu, Tinghui, Chen, Xiangzhen, Zhao, Dan, Li, Yongxin, Zhang, Lina, Bi, Ning, Gou, Jian, Jia, Lei
Publikováno v:
In Journal of Luminescence April 2023 256
Autor:
Gou, Jian, Hu, Yousong, Zhu, Tinghui, Chen, Junyu, Xu, Jun, Bi, Ning, Zhang, Lina, Li, Yongxin, Jia, Lei
Publikováno v:
In Colloids and Surfaces A: Physicochemical and Engineering Aspects 20 November 2022 653
Autor:
Xu, Jun, Zhu, Tinghui, Shi, Jianchao, Song, Bo, Zhang, Lina, Zhao, Dan, Dong, Xiyan, Bi, Ning, Gou, Jian, Jia, Lei
Publikováno v:
In Journal of Rare Earths November 2022 40(11):1715-1727