作者位次 #4/9ICLR 2026Poster· Deep Learning / Generative Models and Autoencoders
TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference Optimization
Chia-Yu Hung · Navonil Majumder · Zhifeng Kong · Ambuj Mehrish · Amir Zadeh · Chuan Li · Rafael Valle · Bryan Catanzaro · Soujanya Poria