Bo Li

Immersive AR/VR experiences can finally have stereo audio that dynamically tracks visual sources, thanks to a novel framework that binds visual motion to sound localization.

EditaLive achieves real-time character video editing with state-of-the-art performance, preserving facial expressions while eliminating latency issues in live streaming.

Models trained with VBVR-Pro not only excel in a controlled task space but also show significant transferability to external benchmarks, revealing critical insights into visual reasoning mechanisms.

MagicMakeup achieves unprecedented regional control in makeup transfer, ensuring high fidelity and identity preservation even across diverse styles and poses.