Zobrazeno 1 - 10
of 1 798
pro vyhledávání: '"Wu, Zhiyong"'
One of the primary driving forces contributing to the superior performance of Large Language Models (LLMs) is the extensive availability of human-annotated natural language data, which is used for alignment fine-tuning. This inspired researchers to i
Externí odkaz:
http://arxiv.org/abs/2406.11736
CoLM-DSR: Leveraging Neural Codec Language Modeling for Multi-Modal Dysarthric Speech Reconstruction
Dysarthric speech reconstruction (DSR) aims to transform dysarthric speech into normal speech. It still suffers from low speaker similarity and poor prosody naturalness. In this paper, we propose a multi-modal DSR model by leveraging neural codec lan
Externí odkaz:
http://arxiv.org/abs/2406.08336
This paper presents the multi-speaker multi-lingual few-shot voice cloning system developed by THU-HCSI team for LIMMITS'24 Challenge. To achieve high speaker similarity and naturalness in both mono-lingual and cross-lingual scenarios, we build the s
Externí odkaz:
http://arxiv.org/abs/2404.16619
Autor:
Jiang, Yu, Liang, Jie, Ma, Fuchen, Chen, Yuanliang, Zhou, Chijin, Shen, Yuheng, Wu, Zhiyong, Fu, Jingzhou, Wang, Mingzhe, Li, ShanShan, Zhang, Quan
Fuzzing, a widely-used technique for bug detection, has seen advancements through Large Language Models (LLMs). Despite their potential, LLMs face specific challenges in fuzzing. In this paper, we identified five major challenges of LLM-assisted fuzz
Externí odkaz:
http://arxiv.org/abs/2404.16297
Autor:
He, Xu, Huang, Qiaochu, Zhang, Zhensong, Lin, Zhiwei, Wu, Zhiyong, Yang, Sicheng, Li, Minglei, Chen, Zhiyi, Xu, Songcen, Wu, Xiaofei
Co-speech gestures, if presented in the lively form of videos, can achieve superior visual effects in human-machine interaction. While previous works mostly generate structural human skeletons, resulting in the omission of appearance information, we
Externí odkaz:
http://arxiv.org/abs/2404.01862
Autor:
Sun, Qiushi, Chen, Zhirui, Xu, Fangzhi, Cheng, Kanzhi, Ma, Chang, Yin, Zhangyue, Wang, Jianing, Han, Chengcheng, Zhu, Renyu, Yuan, Shuai, Guo, Qipeng, Qiu, Xipeng, Yin, Pengcheng, Li, Xiaoli, Yuan, Fei, Kong, Lingpeng, Li, Xiang, Wu, Zhiyong
Neural Code Intelligence -- leveraging deep learning to understand, generate, and optimize code -- holds immense potential for transformative impacts on the whole society. Bridging the gap between Natural Language and Programming Language, this domai
Externí odkaz:
http://arxiv.org/abs/2403.14734
Autor:
Huang, Qiaochu, He, Xu, Tang, Boshi, Zhuang, Haolin, Chen, Liyang, Gao, Shuochen, Wu, Zhiyong, Huang, Haozhi, Meng, Helen
Dance generation, as a branch of human motion generation, has attracted increasing attention. Recently, a few works attempt to enhance dance expressiveness, which includes genre matching, beat alignment, and dance dynamics, from certain aspects. Howe
Externí odkaz:
http://arxiv.org/abs/2403.05834
Recent advancements in generative modeling have significantly enhanced the reconstruction of audio waveforms from various representations. While diffusion models are adept at this task, they are hindered by latency issues due to their operation at th
Externí odkaz:
http://arxiv.org/abs/2403.05010
Knowledge Graph (KG) inductive reasoning, which aims to infer missing facts from new KGs that are not seen during training, has been widely adopted in various applications. One critical challenge of KG inductive reasoning is handling low-resource sce
Externí odkaz:
http://arxiv.org/abs/2402.11804
The emergence of Large Language Models (LLMs) like ChatGPT has inspired the development of LLM-based agents capable of addressing complex, real-world tasks. However, these agents often struggle during task execution due to methodological constraints,
Externí odkaz:
http://arxiv.org/abs/2402.10178