Exploring the Impact of Table-to-Text Methods on Augmenting LLM-based Question Answering with Domain Hybrid Data

Autor: Min, Dehai, Hu, Nan, Jin, Rihui, Lin, Nuo, Chen, Jiaoyan, Chen, Yongrui, Li, Yu, Qi, Guilin, Li, Yun, Li, Nijun, Wang, Qianren

Augmenting Large Language Models (LLMs) for Question Answering (QA) with domain specific data has attracted wide attention. However, domain data often exists in a hybrid format, including text and semi-structured tables, posing challenges for the sea

Externí odkaz: http://arxiv.org/abs/2402.12869

Realistic human action recognition by Fast HOG3D and self-organization feature map.

Autor: Li, Nijun¹ lnjleo@126.com, Cheng, Xu¹ xcheng@seu.edu.cn, Zhang, Suofei¹ zhangsuofei@seu.edu.cn, Wu, Zhenyang¹ zhenyang@seu.edu.cn

Publikováno v: Machine Vision & Applications. Oct2014, Vol. 25 Issue 7, p1793-1812. 20p.

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Action recognition by Huffman coding and implicit action model.

Autor: Li, Nijun, Zhou, Tongchi, Zhou, Lin, Wu, Zhenyang

Publikováno v: 2015 IEEE International Conference on Computational Intelligence & Virtual Environments for Measurement Systems & Applications (CIVEMSA); 2015, p1-6, 6p