Rongjie Huang
Researcher at Meta
Menlo Park, California, United States
Summary
🤩
Rockstar🎓
Top SchoolRongjie Huang is a researcher based in Menlo Park with six years of experience advancing multimodal AI, specializing in audio-visual language processing, speech synthesis, and multimodal LLMs. He has first-author publications at NeurIPS/ICLR/ICML/ACL/IJCAI and has core-contributed to Meta’s Seamless Interaction work and speech-text interleaved LLMs that fuse duplex audio with gesture and facial motion. His prior internships at Shanghai AI Lab and Tencent produced state-of-the-art audio generation and diffusion models (e.g., Lumina-Next, FastDiff), and his open-source focus spans multimodal synthesis, speech translation, and self-supervised learning. Rongjie combines strong academic rigor with product-facing research, frequently turning novel generative ideas into widely referenced algorithms like AudioGPT, UniAudio, and Make-A-Voice.
6 years of coding experience
Postgraduate Degree, Artificial inteligience, Postgraduate Degree, Artificial inteligience at Zhejiang University
Github Skills (74)
style-transfer10
speech10
audio10
ctc10
music10
sequence10
text-to-speech9
python9
sequence-to-sequence9
pytorch9
facebook9
generative-model9
artificial-intelligence9
cookbook9
speech-synthesis9
Programming languages (5)
Github contributions (5)
Rongjiehuang/FastDiff
May 2022 - Aug 2022
Contributions:24 commits, 21 pushes, 22 comments in 3 months
Rongjiehuang/awesome-speech-to-speech-translation
May 2022 - Jan 2023
Contributions:4 commits, 3 pushes in 8 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.