Zhitong He

Papers

Total Citations

H-Index

About

Zhitong He is an emerging researcher working at the intersection of human-computer interaction, computer graphics, and artificial intelligence, with a particular focus on **gesture and motion synthesis**. His notable work centers on generating naturalistic, speech-synchronized body movements using deep learning architectures. In his paper *"Cospeech Body Motion Generation Using a Transformer"* (2024), He explores how transformer-based models can be leveraged to automatically produce coherent, expressive body gestures that align with spoken language — a challenging problem with significant implications for virtual avatars, social robots, and animation pipelines. While his publication record is still in its early stages, with his most prominent work accumulating citations shortly after its release in 2024, the timeliness of the research speaks to a rapidly growing field driven by advances in large-scale sequence modeling. By addressing the synchronization of non-verbal communication with speech, He's contributions stand to meaningfully improve the naturalness of human-agent interaction. As the field of embodied AI and digital humans continues to expand, Zhitong He represents a promising voice in next-generation motion generation research.