Lianghua Huang

ReWorld achieves unprecedented control fidelity and video generation quality by elegantly separating short-term control from long-term memory, outperforming existing models in interactive environments.

Video can be reimagined as a dynamic interplay of stable contexts and evolving events, revolutionizing real-time interaction capabilities in AI.

Skip the bulky bidirectional teacher: this new method trains a fast, causal audio-video generator directly, slashing sampling steps while maintaining top-tier quality.