Rongjie Huang (黄融杰) is at Seamless Team at FAIR. Previously, I graduated from College of Computer Science, Zhejiang University, supervised by Prof. Zhou Zhao. I also obtained Bachelor’s degree at Zhejiang University. My research interest includes Multi-modal Large Language Model, Video-Audio Generative Models, and Audio-Visual Language Processing. I have published first-author papers at the top international AI conferences such as NeurIPS/ICLR/ICML/ACL/IJCAI. I developed a few well-known Speech/NLP algorithms including:

• Multimodal LLMs: Seamless-Interaction (LLama4+Dyadic Motion Diffusion), AudioGPT, UniAudio, Make-A-Voice
• Omini-modal Audio Generative Models: Lumina-T2X (omini-modal), Make-An-Audio, Make-An-Audio-2, FastDiff, GenerSpeech
• Multimodal Translation: TranSpeech, and AV-TranSpeech

🔥 News