里程碑

Co-authored the paper 'Style-Talker: Finetuning Audio Language Model and Style-Based Text-to-Speech Model for Fast Spoken Dialogue Generation', presented at CoLM 2024.

Co-authored 'StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion' for the NAACL 2025 conference.

Co-authored the paper 'DMOSpeech 2: Reinforcement Learning for Duration Prediction in Metric-Optimized Speech Synthesis', which was his final PhD contribution.

Joined Meta Superintelligence Labs as an AI Research Scientist after completing his PhD in Electrical Engineering at Columbia University.