Developed a comprehensive live streaming digital human system by integrating large language models, voice synthesis, and lip-sync generation technologies, enabling real-time user interaction and character-based responses.

Created a video digital human generation system, focusing on high-fidelity lip-syncing and facial expression transfers using AI-driven technology, ensuring consistency in visual and emotional expression.

Optimized the integration of AI technologies such as facial expression transfer and lip-sync drivers, ensuring smooth transitions between actions and emotions, while enhancing the digital human's interaction capabilities.

Refined motion and pose transfer tools, improving the ability to animate characters with more natural movements, integrating seamlessly with real-time video content.