Kai Shen

FocusDiff: Advancing Fine-Grained Text-Image Alignment for Autoregressive Visual Generation through RL

Janus-Pro-R1: Advancing Collaborative Visual Comprehension and Generation via Reinforcement Learning

MoonCast: High-Quality Zero-Shot Podcast Generation

RALL-E: Robust Codec Language Modeling with Chain-of-Thought Prompting for Text-to-Speech Synthesis