Výsledky vyhledávání

Report

Advancing Tool-Augmented Large Language Models: Integrating Insights from Errors in Inference Trees

Autor: Chen, Sijia, Wang, Yibo, Wu, Yi-Feng, Chen, Qing-Guo, Xu, Zhao, Luo, Weihua, Zhang, Kaifu, Zhang, Lijun

Tool-augmented large language models (LLMs) leverage tools, often in the form of APIs, to enhance their reasoning capabilities on complex tasks, thus taking on the role of intelligent agents interacting with the real world. The recently introduced To

Externí odkaz: http://arxiv.org/abs/2406.07115

Zobrazit plný text záznamu

Report

TAI++: Text as Image for Multi-Label Image Classification by Co-Learning Transferable Prompt

Autor: Wu, Xiangyu, Jiang, Qing-Yuan, Yang, Yang, Wu, Yi-Feng, Chen, Qing-Guo, Lu, Jianfeng

The recent introduction of prompt tuning based on pre-trained vision-language models has dramatically improved the performance of multi-label image classification. However, some existing strategies that have been explored still have drawbacks, i.e.,

Externí odkaz: http://arxiv.org/abs/2405.06926

Zobrazit plný text záznamu