Tianshui Chen

Overcome the scarcity of paired data in speech-preserving facial expression manipulation by personalizing visual-language model prompts with individual visual information and correlating changes in visual and semantic features.

Speakers expressing the same content with different emotions exhibit surprisingly consistent spatial-temporal correlations in their local facial animations, unlocking a new approach to speech-preserving facial expression manipulation.

Ditching language and video intermediaries for direct 3D reasoning unlocks surprising zero-shot generalization in robotic manipulation.