Zobrazeno 1 - 10
of 9 443
pro vyhledávání: '"An, Pengyuan"'
The performance of automatic speech recognition models often degenerates on domains not covered by the training data. Domain adaptation can address this issue, assuming the availability of the target domain data in the target language. However, such
Externí odkaz:
http://arxiv.org/abs/2412.11185
Autor:
Zhang, Zhilong, Chen, Ruifeng, Ye, Junyin, Sun, Yihao, Wang, Pengyuan, Pang, Jingcheng, Li, Kaiyuan, Liu, Tianshuo, Lin, Haoxin, Yu, Yang, Zhou, Zhi-Hua
World models play a crucial role in decision-making within embodied environments, enabling cost-free explorations that would otherwise be expensive in the real world. To facilitate effective decision-making, world models must be equipped with strong
Externí odkaz:
http://arxiv.org/abs/2411.05619
Proper moral beliefs are fundamental for language models, yet assessing these beliefs poses a significant challenge. This study introduces a novel three-module framework to evaluate the moral beliefs of four prominent large language models. Initially
Externí odkaz:
http://arxiv.org/abs/2411.03665
Autor:
Shi, Pengyuan, Wang, Xiaoyu, Zhang, Lihao, Song, Wenqin, Yang, Kunlin, Wang, Shuxi, Zhang, Ruisheng, Zhang, Liangliang, Taniguchi, Takashi, Watanabe, Kenji, Yang, Sen, Zhang, Lei, Wang, Lei, Shi, Wu, Pan, Jie, Wang, Zhe
Publikováno v:
Phys. Rev. X 14, 041065 (2024)
Magnetoresistance (MR) oscillations serve as a hallmark of intrinsic quantum behavior, traditionally observed only in conducting systems. Here we report the discovery of MR oscillations in an insulating system, the vertical junctions of CrPS$_4$ whic
Externí odkaz:
http://arxiv.org/abs/2410.18258
Autor:
Deng, Linger, Liu, Yuliang, Li, Bohan, Luo, Dongliang, Wu, Liang, Zhang, Chengquan, Lyu, Pengyuan, Zhang, Ziyang, Zhang, Gang, Ding, Errui, Zhu, Yingying, Bai, Xiang
Existing Large Multimodal Models (LMMs) struggle with mathematical geometric reasoning due to a lack of high-quality image-text paired data. Current geometric data generation approaches, which apply preset templates to generate geometric data or use
Externí odkaz:
http://arxiv.org/abs/2410.17885
Large-scale speech generation models have achieved impressive performance in the zero-shot voice clone tasks relying on large-scale datasets. However, exploring how to achieve zero-shot voice clone with small-scale datasets is also essential. This pa
Externí odkaz:
http://arxiv.org/abs/2410.12399
In response to climate change and urban heat island effects, enhancing human thermal comfort in cities is crucial for sustainable urban development. Traditional methods for investigating the urban thermal environment and corresponding human thermal c
Externí odkaz:
http://arxiv.org/abs/2410.11887
Emotion recognition in speech is a challenging multimodal task that requires understanding both verbal content and vocal nuances. This paper introduces a novel approach to emotion detection using Large Language Models (LLMs), which have demonstrated
Externí odkaz:
http://arxiv.org/abs/2407.21315
Autor:
Wu, Jingjing, Fang, Zhengyao, Lyu, Pengyuan, Zhang, Chengquan, Chen, Fanglin, Lu, Guangming, Pei, Wenjie
Transcription-only Supervised Text Spotting aims to learn text spotters relying only on transcriptions but no text boundaries for supervision, thus eliminating expensive boundary annotation. The crux of this task lies in locating each transcription i
Externí odkaz:
http://arxiv.org/abs/2407.19507
The Circular Electron-Positron Collider (CEPC) can also work as a powerful and excellent synchrotron light source, which can generate high-quality synchrotron radiation. This synchrotron radiation has potential advantages in the medical field, with a
Externí odkaz:
http://arxiv.org/abs/2407.15217