Zobrazeno 1 - 10
of 110
pro vyhledávání: '"Li, Xiangang"'
Nowadays, open-source large language models like LLaMA have emerged. Recent developments have incorporated supervised fine-tuning (SFT) and reinforcement learning fine-tuning (RLFT) to align these models with human goals. However, SFT methods treat a
Externí odkaz:
http://arxiv.org/abs/2309.11235
Recently, the instruction-tuning of large language models is a crucial area of research in the field of natural language processing. Due to resource and cost limitations, several researchers have employed parameter-efficient tuning techniques, such a
Externí odkaz:
http://arxiv.org/abs/2304.08109
Recently, significant public efforts have been directed towards developing low-cost models with capabilities akin to ChatGPT, thereby fostering the growth of open-source conversational models. However, there remains a scarcity of comprehensive and in
Externí odkaz:
http://arxiv.org/abs/2304.07854
Autor:
Ji, Yunjie, Deng, Yong, Gong, Yan, Peng, Yiping, Niu, Qiang, Zhang, Lei, Ma, Baochang, Li, Xiangang
The success of ChatGPT has recently attracted numerous efforts to replicate it, with instruction-tuning strategies being a key factor in achieving remarkable results. Instruction-tuning not only significantly enhances the model's performance and gene
Externí odkaz:
http://arxiv.org/abs/2303.14742
Autor:
Ji, Yunjie, Gong, Yan, Peng, Yiping, Ni, Chao, Sun, Peiyan, Pan, Dongyu, Ma, Baochang, Li, Xiangang
As a natural language assistant, ChatGPT is capable of performing various tasks, including but not limited to article generation, code completion, and data analysis. Furthermore, ChatGPT has consistently demonstrated a remarkable level of accuracy an
Externí odkaz:
http://arxiv.org/abs/2303.07610
In this paper, we delve into semi-supervised 2D human pose estimation. The previous method ignored two problems: (i) When conducting interactive training between large model and lightweight model, the pseudo label of lightweight model will be used to
Externí odkaz:
http://arxiv.org/abs/2303.04346
Autor:
Deng, Yong, Dou, Chenxiao, Chen, Liangyu, Miao, Deqiang, Sun, Xianghui, Ma, Baochang, Li, Xiangang
PCL detection task is aimed at identifying and categorizing language that is patronizing or condescending towards vulnerable communities in the general media.Compared to other NLP tasks of paragraph classification, the negative language presented in
Externí odkaz:
http://arxiv.org/abs/2208.01312
Machine Reading Comprehension with Unanswerable Questions is a difficult NLP task, challenged by the questions which can not be answered from passages. It is observed that subtle literal changes often make an answerable question unanswerable, however
Externí odkaz:
http://arxiv.org/abs/2208.01299
This paper describes our best system and methodology for ADD 2022: The First Audio Deep Synthesis Detection Challenge\cite{Yi2022ADD}. The very same system was used for both two rounds of evaluation in Track 3.2 with a similar training methodology. T
Externí odkaz:
http://arxiv.org/abs/2204.08720
Autor:
Wen, Cheng, Guo, Tingwei, Tan, Xingjun, Yan, Rui, Zhou, Shuran, Xie, Chuandong, Zou, Wei, Li, Xiangang
In this paper, we describe our speech generation system for the first Audio Deep Synthesis Detection Challenge (ADD 2022). Firstly, we build an any-to-many voice conversion (VC) system to convert source speech with arbitrary language content into the
Externí odkaz:
http://arxiv.org/abs/2204.08692