Zobrazeno 1 - 10
of 362
pro vyhledávání: '"Qin, Yujia"'
Autor:
Chen, Wentong, Cui, Junbo, Hu, Jinyi, Qin, Yujia, Fang, Junjie, Zhao, Yue, Wang, Chongyi, Liu, Jun, Chen, Guirong, Huo, Yupeng, Yao, Yuan, Lin, Yankai, Liu, Zhiyuan, Sun, Maosong
Utilizing Graphic User Interface (GUI) for human-computer interaction is essential for accessing a wide range of digital tools. Recent advancements in Vision Language Models (VLMs) highlight the compelling potential to develop versatile agents to hel
Externí odkaz:
http://arxiv.org/abs/2406.11317
Autor:
Guo, Zhicheng, Cheng, Sijie, Wang, Hao, Liang, Shihao, Qin, Yujia, Li, Peng, Liu, Zhiyuan, Sun, Maosong, Liu, Yang
Large Language Models (LLMs) have witnessed remarkable advancements in recent years, prompting the exploration of tool learning, which integrates LLMs with external tools to address diverse real-world challenges. Assessing the capability of LLMs to u
Externí odkaz:
http://arxiv.org/abs/2403.07714
Autor:
Luo, Qinyu, Ye, Yining, Liang, Shihao, Zhang, Zhong, Qin, Yujia, Lu, Yaxi, Wu, Yesai, Cong, Xin, Lin, Yankai, Zhang, Yingli, Che, Xiaoyin, Liu, Zhiyuan, Sun, Maosong
Generative models have demonstrated considerable potential in software engineering, particularly in tasks such as code generation and debugging. However, their utilization in the domain of code documentation generation remains underexplored. To this
Externí odkaz:
http://arxiv.org/abs/2402.16667
In recent developments within the research community, the integration of Large Language Models (LLMs) in creating fully autonomous agents has garnered significant interest. Despite this, LLM-based agents frequently demonstrate notable shortcomings in
Externí odkaz:
http://arxiv.org/abs/2402.12914
Autor:
Qian, Cheng, He, Bingxiang, Zhuang, Zhong, Deng, Jia, Qin, Yujia, Cong, Xin, Zhang, Zhong, Zhou, Jie, Lin, Yankai, Liu, Zhiyuan, Sun, Maosong
Current language model-driven agents often lack mechanisms for effective user participation, which is crucial given the vagueness commonly found in user instructions. Although adept at devising strategies and performing tasks, these agents struggle w
Externí odkaz:
http://arxiv.org/abs/2402.09205
Autor:
Fang, Junjie, Tang, Likai, Bi, Hongzhe, Qin, Yujia, Sun, Si, Li, Zhenyu, Li, Haolun, Li, Yongjian, Cong, Xin, Yan, Yukun, Shi, Xiaodong, Song, Sen, Lin, Yankai, Liu, Zhiyuan, Sun, Maosong
Long-context processing is a critical ability that constrains the applicability of large language models. Although there exist various methods devoted to enhancing the long-context processing ability of large language models (LLMs), they are develope
Externí odkaz:
http://arxiv.org/abs/2402.03009
Autor:
Qian, Cheng, Liang, Shihao, Qin, Yujia, Ye, Yining, Cong, Xin, Lin, Yankai, Wu, Yesai, Liu, Zhiyuan, Sun, Maosong
This paper introduces Investigate-Consolidate-Exploit (ICE), a novel strategy for enhancing the adaptability and flexibility of AI agents through inter-task self-evolution. Unlike existing methods focused on intra-task learning, ICE promotes the tran
Externí odkaz:
http://arxiv.org/abs/2401.13996
Autor:
Tian, Runchu, Ye, Yining, Qin, Yujia, Cong, Xin, Lin, Yankai, Pan, Yinxu, Wu, Yesai, Hui, Haotian, Liu, Weichuan, Liu, Zhiyuan, Sun, Maosong
Large Language Models (LLMs) have demonstrated exceptional coding capability. However, as another critical component of programming proficiency, the debugging capability of LLMs remains relatively unexplored. Previous evaluations of LLMs' debugging a
Externí odkaz:
http://arxiv.org/abs/2401.04621
Autor:
Lyu, Bohan, Cong, Xin, Yu, Heyang, Yang, Pan, Qin, Yujia, Ye, Yining, Lu, Yaxi, Zhang, Zhong, Yan, Yukun, Lin, Yankai, Liu, Zhiyuan, Sun, Maosong
While Large Language Models (LLMs) like ChatGPT and GPT-4 have demonstrated exceptional proficiency in natural language processing, their efficacy in addressing complex, multifaceted tasks remains limited. A growing area of research focuses on LLM-ba
Externí odkaz:
http://arxiv.org/abs/2312.17294
Publikováno v:
Julius-Kühn-Archiv, Vol 463, Iss 1, Pp 292-294 (2018)
Stored-product beetles were regarded as some of the most important stored-product pests in the world. Predicting which one in hundreds of potential invasive stored-product beetles is the most likely to invade a region presents a significant challenge
Externí odkaz:
https://doaj.org/article/f7d0f96200fd4651ab7ff5e59de78ca1