Zobrazeno 1 - 10
of 3 846
pro vyhledávání: '"Cheng, Fei"'
Continual learning(CL) is a useful technique to acquire dynamic knowledge continually. Although powerful cloud platforms can fully exert the ability of CL,e.g., customized recommendation systems, similar personalized requirements for edge devices are
Externí odkaz:
http://arxiv.org/abs/2407.10545
Autor:
LLM-jp, Aizawa, Akiko, Aramaki, Eiji, Chen, Bowen, Cheng, Fei, Deguchi, Hiroyuki, Enomoto, Rintaro, Fujii, Kazuki, Fukumoto, Kensuke, Fukushima, Takuya, Han, Namgi, Harada, Yuto, Hashimoto, Chikara, Hiraoka, Tatsuya, Hisada, Shohei, Hosokawa, Sosuke, Jie, Lu, Kamata, Keisuke, Kanazawa, Teruhito, Kanezashi, Hiroki, Kataoka, Hiroshi, Katsumata, Satoru, Kawahara, Daisuke, Kawano, Seiya, Keyaki, Atsushi, Kiryu, Keisuke, Kiyomaru, Hirokazu, Kodama, Takashi, Kubo, Takahiro, Kuga, Yohei, Kumon, Ryoma, Kurita, Shuhei, Kurohashi, Sadao, Li, Conglong, Maekawa, Taiki, Matsuda, Hiroshi, Miyao, Yusuke, Mizuki, Kentaro, Mizuki, Sakae, Murawaki, Yugo, Nakamura, Ryo, Nakamura, Taishi, Nakayama, Kouta, Nakazato, Tomoka, Niitsuma, Takuro, Nishitoba, Jiro, Oda, Yusuke, Ogawa, Hayato, Okamoto, Takumi, Okazaki, Naoaki, Oseki, Yohei, Ozaki, Shintaro, Ryu, Koki, Rzepka, Rafal, Sakaguchi, Keisuke, Sasaki, Shota, Sekine, Satoshi, Suda, Kohei, Sugawara, Saku, Sugiura, Issa, Sugiyama, Hiroaki, Suzuki, Hisami, Suzuki, Jun, Suzumura, Toyotaro, Tachibana, Kensuke, Takagi, Yu, Takami, Kyosuke, Takeda, Koichi, Takeshita, Masashi, Tanaka, Masahiro, Taura, Kenjiro, Tolmachev, Arseny, Ueda, Nobuhiro, Wan, Zhen, Yada, Shuntaro, Yahata, Sakiko, Yamamoto, Yuya, Yamauchi, Yusuke, Yanaka, Hitomi, Yokota, Rio, Yoshino, Koichiro
This paper introduces LLM-jp, a cross-organizational project for the research and development of Japanese large language models (LLMs). LLM-jp aims to develop open-source and strong Japanese LLMs, and as of this writing, more than 1,500 participants
Externí odkaz:
http://arxiv.org/abs/2407.03963
In this work, we employ two AMR-enhanced semantic representations for ICL on RE: one that explores the AMR structure generated for a sentence at the subgraph level (shortest AMR path), and another that explores the full AMR structure generated for a
Externí odkaz:
http://arxiv.org/abs/2406.10432
Publikováno v:
International Conference on Brain Inspired Cognitive Systems 2023
Synthesizing Chinese characters with consistent style using few stylized examples is challenging. Existing models struggle to generate arbitrary style characters with limited examples. In this paper, we propose the Generalized W-Net, a novel class of
Externí odkaz:
http://arxiv.org/abs/2406.06847
Sample selection is the most straightforward technique to combat label noise, aiming to distinguish mislabeled samples during training and avoid the degradation of the robustness of the model. In the workflow, $\textit{selecting possibly clean data}$
Externí odkaz:
http://arxiv.org/abs/2405.17137
Autor:
Virgo, Felix, Cheng, Fei, Pereira, Lis Kanashiro, Asahara, Masayuki, Kobayashi, Ichiro, Kurohashi, Sadao
We propose a voting-driven semi-supervised approach to automatically acquire the typical duration of an event and use it as pseudo-labeled data. The human evaluation demonstrates that our pseudo labels exhibit surprisingly high accuracy and balanced
Externí odkaz:
http://arxiv.org/abs/2403.18504
Autor:
Sun, Yikun, Wan, Zhen, Ueda, Nobuhiro, Yahata, Sakiko, Cheng, Fei, Chu, Chenhui, Kurohashi, Sadao
The creation of instruction data and evaluation benchmarks for serving Large language models often involves enormous human annotation. This issue becomes particularly pronounced when rapidly developing such resources for a non-English language like J
Externí odkaz:
http://arxiv.org/abs/2403.03690
Publikováno v:
Volume 13, Issue 1, 2024, pp. 55-68
This scoping review explores the ethical challenges of using ChatGPT in higher education. By reviewing recent academic articles in English, Chinese, and Japanese, we aimed to provide a deep dive review and identify gaps in the literature. Drawing on
Externí odkaz:
http://arxiv.org/abs/2311.14378
Purpose:Generative Artificial Intelligence (GAI) models, such as ChatGPT, may inherit or amplify societal biases due to their training on extensive datasets. With the increasing usage of GAI by students, faculty, and staff in higher education institu
Externí odkaz:
http://arxiv.org/abs/2311.14381
Temporal relation classification is a pair-wise task for identifying the relation of a temporal link (TLINK) between two mentions, i.e. event, time, and document creation time (DCT). It leads to two crucial limits: 1) Two TLINKs involving a common me
Externí odkaz:
http://arxiv.org/abs/2310.20236