AI for Audio, Speech, and Natural Lanaguage Processing, including the following topics: large language models, foundation audio and speech AI models, audio-visual multi-modal AI, speech AI system for health applications, and secure and trustworthy speech AI. I am a Member of Technical Staff at xAI.

Yuan Gong. Member of Technical Staff, xAI. Verified email at x.ai - Homepage. ... Y Gong, Y Kim, X Wu, H Meng, J Glass. Findings of the Association for Computational Linguistics: EMNLP 2023, 3717-3729, 2023. 70 * 2023: Real-time Adversarial Attacks. Y Gong, B Li, C Poellabauer, Y Shi.

Yuan Gong (Chinese: 原弓; pinyin: Yuán Gōng, born 1961 in Shanghai), is a Chinese contemporary artist. He has obtained a PhD degree in theory of art at the Chinese National Academy of Arts in 2012, but has immersed himself in different aspects of Chinese contemporary art since the 1990s.

Research Scientist, MIT CSAIL. YuanGongND has 52 repositories available. Follow their code on GitHub.

‘Falling leaves return to their roots’? The reception of Chinese blockbusters by Chinese university students in New Zealand.

Yuan GONG, Professor (Associate) | Cited by 2,968 | of University of Electronic Science and Technology of China, Chengdu (UESTC) | Read 146 publications | Contact Yuan GONG

Yuan Gong. University of Electronic Science and Technology of China. ... C Gong, Y Gong, X Zhao, Y Luo, Q Chen, X Tan, Y Wu, X Fan, GD Peng, ... Lab on a Chip 18 (18), 2741-2748, 2018. 65: 2018: Reproducible fiber optofluidic laser for disposable and array applications.

Yuan GONG, Research Scientist | Cited by 1,174 | of Massachusetts Institute of Technology, MA (MIT) | Read 40 publications | Contact Yuan GONG

AST is the first convolution-free, purely attention-based model for audio classification which supports variable length input and can be applied to various tasks.

2021年4月5日 · View a PDF of the paper titled AST: Audio Spectrogram Transformer, by Yuan Gong and 2 other authors View PDF Abstract: In the past decade, convolutional neural networks (CNNs) have been widely adopted as the main building block for end-to-end audio classification models, which aim to learn a direct mapping from audio spectrograms to ...