Scholar
Haiyang Liu
Google Scholar ID: U_9vNgsAAAAJ
The University of Tokyo
Citations & Impact
Citations
413
H-index
5
i10-index
4
Publications
9
Co-authors
8
list available
Publications
Resume (English only)
Academic Achievements
- Selected publications include 'Livatar-1: Real-Time Talking Heads Generation with Tailored Flow Matching', 'Video Motion Graphs', 'TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio-Motion Embedding and Diffusion Interpolation', 'EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Mask Audio Gesture Modeling', 'BEAT: A Large Scale Semantic and Emotional Multi Modal Dataset for Conversational Gesture Synthesis', and 'DisCo: Disentangled Implicit Content and Rhythm Learning for Diverse Co-Speech Gesture Synthesis'.
Research Experience
- During the PhD, interned at Hedra Research (real-time human video generation), Adobe Research - Video AI Lab (multi-modal human video generation, mentor: Yang Zhou), CyberAgent AI Lab - Computer Graphic Group (co-speech video generation, mentor: Takafumi Taketomi), and Huawei Research Tokyo - Digital Human Lab (co-speech gesture generation, mentor: Naoya Iwamoto).
Education
- Received M.E. from Waseda University in 2020.9; B.E. from Southeast University in 2019.9.
Background
- Currently a final-year PhD student in Information Science and Technology at The University of Tokyo, focusing on human video generation and motion generation using multi-modal conditions such as speech, text scripts, keypoints, and images. Interested in impact-driven research problems and simple yet effective ideas.
Miscellany
- Seeking full-time positions starting in 2025.
