Yuping Wang

This article discusses the fusion of foundation models and federated learning in healthcare.

Seed-TTS creates lifelike speech from text for various applications.

A new model improves accuracy in speech-to-text capabilities across multiple languages.

New dataset improves audio generation from detailed text descriptions.

A system making music creation easy and accessible for all skill levels.

OpenEMMA redefines self-driving technology with advanced AI and smart decision-making.