Zobrazeno 1 - 10
of 31
pro vyhledávání: '"Yuan, Ruibin"'
Autor:
Tian, Zeyue, Liu, Zhaoyang, Yuan, Ruibin, Pan, Jiahao, Huang, Xiaoqiang, Liu, Qifeng, Tan, Xu, Chen, Qifeng, Xue, Wei, Guo, Yike
In this work, we systematically study music generation conditioned solely on the video. First, we present a large-scale dataset comprising 190K video-music pairs, including various genres such as movie trailers, advertisements, and documentaries. Fur
Externí odkaz:
http://arxiv.org/abs/2406.04321
Autor:
He, Yingqing, Liu, Zhaoyang, Chen, Jingye, Tian, Zeyue, Liu, Hongyu, Chi, Xiaowei, Liu, Runtao, Yuan, Ruibin, Xing, Yazhou, Wang, Wenhai, Dai, Jifeng, Zhang, Yong, Xue, Wei, Liu, Qifeng, Guo, Yike, Chen, Qifeng
With the recent advancement in large language models (LLMs), there is a growing interest in combining LLMs with multimodal learning. Previous surveys of multimodal large language models (MLLMs) mainly focus on multimodal understanding. This survey el
Externí odkaz:
http://arxiv.org/abs/2405.19334
Autor:
Deng, Qixin, Yang, Qikai, Yuan, Ruibin, Huang, Yipeng, Wang, Yi, Liu, Xubo, Tian, Zeyue, Pan, Jiahao, Zhang, Ge, Lin, Hanfeng, Li, Yizhi, Ma, Yinghao, Fu, Jie, Lin, Chenghua, Benetos, Emmanouil, Wang, Wenwu, Xia, Guangyu, Xue, Wei, Guo, Yike
Music composition represents the creative side of humanity, and itself is a complex task that requires abilities to understand and generate information with long dependency and harmony constraints. While demonstrating impressive capabilities in STEM
Externí odkaz:
http://arxiv.org/abs/2404.18081
Autor:
Qu, Xingwei, Bai, Yuelin, Ma, Yinghao, Zhou, Ziya, Lo, Ka Man, Liu, Jiaheng, Yuan, Ruibin, Min, Lejun, Liu, Xueling, Zhang, Tianyu, Du, Xinrun, Guo, Shuyue, Liang, Yiming, Li, Yizhi, Wu, Shangda, Zhou, Junting, Zheng, Tianyu, Ma, Ziyang, Han, Fengze, Xue, Wei, Xia, Gus, Benetos, Emmanouil, Yue, Xiang, Lin, Chenghua, Tan, Xu, Huang, Stephen W., Chen, Wenhu, Fu, Jie, Zhang, Ge
In this paper, we explore the application of Large Language Models (LLMs) to the pre-training of music. While the prevalent use of MIDI in music modeling is well-established, our findings suggest that LLMs are inherently more compatible with ABC Nota
Externí odkaz:
http://arxiv.org/abs/2404.06393
Autor:
Du, Xinrun, Yu, Zhouliang, Gao, Songyang, Pan, Ding, Cheng, Yuyang, Ma, Ziyang, Yuan, Ruibin, Qu, Xingwei, Liu, Jiaheng, Zheng, Tianyu, Luo, Xinchen, Zhou, Guorui, Yuan, Binhang, Chen, Wenhu, Fu, Jie, Zhang, Ge
In this study, we introduce CT-LLM, a 2B large language model (LLM) that illustrates a pivotal shift towards prioritizing the Chinese language in developing LLMs. Uniquely initiated from scratch, CT-LLM diverges from the conventional methodology by p
Externí odkaz:
http://arxiv.org/abs/2404.04167
Autor:
Yang, Chen, Li, Junzhuo, Niu, Xinyao, Du, Xinrun, Gao, Songyang, Zhang, Haoran, Chen, Zhaoliang, Qu, Xingwei, Yuan, Ruibin, Li, Yizhi, Liu, Jiaheng, Huang, Stephen W., Yue, Shawn, Chen, Wenhu, Fu, Jie, Zhang, Ge
Uncovering early-stage metrics that reflect final model performance is one core principle for large-scale pretraining. The existing scaling law demonstrates the power-law correlation between pretraining loss and training flops, which serves as an imp
Externí odkaz:
http://arxiv.org/abs/2404.01204
Large Language Models (LLMs) exhibit remarkable capabilities but are prone to generating inaccurate or hallucinatory responses. This limitation stems from their reliance on vast pretraining datasets, making them susceptible to errors in unseen scenar
Externí odkaz:
http://arxiv.org/abs/2404.00610
Autor:
Bai, Yuelin, Du, Xinrun, Liang, Yiming, Jin, Yonggang, Liu, Ziqiang, Zhou, Junting, Zheng, Tianyu, Zhang, Xincheng, Ma, Nuo, Wang, Zekun, Yuan, Ruibin, Wu, Haihong, Lin, Hongquan, Huang, Wenhao, Zhang, Jiajun, Chen, Wenhu, Lin, Chenghua, Fu, Jie, Yang, Min, Ni, Shiwen, Zhang, Ge
Recently, there have been significant advancements in large language models (LLMs), particularly focused on the English language. These advancements have enabled these LLMs to understand and execute complex instructions with unprecedented accuracy an
Externí odkaz:
http://arxiv.org/abs/2403.18058
Autor:
Yin, Hanzhi, Cheng, Gang, Steinmetz, Christian J., Yuan, Ruibin, Stern, Richard M., Dannenberg, Roger B.
We describe a novel approach for developing realistic digital models of dynamic range compressors for digital audio production by analyzing their analog prototypes. While realistic digital dynamic compressors are potentially useful for many applicati
Externí odkaz:
http://arxiv.org/abs/2403.16331
Autor:
Yuan, Ruibin, Lin, Hanfeng, Wang, Yi, Tian, Zeyue, Wu, Shangda, Shen, Tianhao, Zhang, Ge, Wu, Yuhang, Liu, Cong, Zhou, Ziya, Ma, Ziyang, Xue, Liumeng, Wang, Ziyu, Liu, Qin, Zheng, Tianyu, Li, Yizhi, Ma, Yinghao, Liang, Yiming, Chi, Xiaowei, Liu, Ruibo, Wang, Zili, Li, Pengfei, Wu, Jingcheng, Lin, Chenghua, Liu, Qifeng, Jiang, Tao, Huang, Wenhao, Chen, Wenhu, Benetos, Emmanouil, Fu, Jie, Xia, Gus, Dannenberg, Roger, Xue, Wei, Kang, Shiyin, Guo, Yike
While Large Language Models (LLMs) demonstrate impressive capabilities in text generation, we find that their ability has yet to be generalized to music, humanity's creative language. We introduce ChatMusician, an open-source LLM that integrates intr
Externí odkaz:
http://arxiv.org/abs/2402.16153