Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Zeng, Yankai"'
Autor:
Zeng, Yankai, Rajashekharan, Abhiramon, Basu, Kinjal, Wang, Huaduo, Arias, Joaquín, Gupta, Gopal
The development of large language models (LLMs), such as GPT, has enabled the construction of several socialbots, like ChatGPT, that are receiving a lot of attention for their ability to simulate a human conversation. However, the conversation is not
Externí odkaz:
http://arxiv.org/abs/2407.18498
Autor:
Zeng, Yankai, Rajasekharan, Abhiramon, Padalkar, Parth, Basu, Kinjal, Arias, Joaquín, Gupta, Gopal
Achieving human-like communication with machines remains a classic, challenging topic in the field of Knowledge Representation and Reasoning and Natural Language Processing. These Large Language Models (LLMs) rely on pattern-matching rather than a tr
Externí odkaz:
http://arxiv.org/abs/2303.08941
Publikováno v:
EPTCS 385, 2023, pp. 274-287
Humans understand language by extracting information (meaning) from sentences, combining it with existing commonsense knowledge, and then performing reasoning to draw conclusions. While large language models (LLMs) such as GPT-3 and ChatGPT are able
Externí odkaz:
http://arxiv.org/abs/2302.03780
Knowledge-based visual question answering (VQA) requires answering questions with external knowledge in addition to the content of images. One dataset that is mostly used in evaluating knowledge-based VQA is OK-VQA, but it lacks a gold standard knowl
Externí odkaz:
http://arxiv.org/abs/2109.04014
Autor:
Luo, Man, Sampat, Shailaja Keyur, Tallman, Riley, Zeng, Yankai, Vancha, Manuha, Sajja, Akarshan, Baral, Chitta
GQA~\citep{hudson2019gqa} is a dataset for real-world visual reasoning and compositional question answering. We found that many answers predicted by the best vision-language models on the GQA dataset do not match the ground-truth answer but still are
Externí odkaz:
http://arxiv.org/abs/2103.15022
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.