Scholar
Chenxu Zhang
Google Scholar ID: XnefngEAAAAJ
ByteDance Inc.
Citations & Impact
Citations
684
H-index
9
i10-index
8
Publications
20
Co-authors
16
list available
Contact
Publications
Resume (English only)
Academic Achievements
- X-Actor: Emotional and Expressive Long-Range Portrait Acting from Audio; X-UniMotion: Animating Human Images with Expressive, Unified and Identity-Agnostic Motion Latents; X-Dancer: Expressive Music to Human Dance Video Generation; X-Dyna: Expressive Dynamic Human Image Animation; CADDreamer: CAD Object Generation from Single-view Images; X-NeMo: Expressive Neural Motion Reenactment via Disentangled Latent Attention; MagicTalk: Implicit and Explicit Correlation Learning for Diffusion-based Emotional Talking Face Generation; AvatarStudio: High-fidelity and Animatable 3D Avatar Creation from Text; Joint Co-Speech Gesture and Expressive Talking Face Generation using Diffusion with Adapters; Sora Generates Videos with Stunning Geometrical Consistency; Magicanimate: Temporally consistent human image animation using diffusion model; DR2: Disentangled Recurrent Representation Learning for Data-efficient Speech Video Synthesis; Magic-Boost: Boost 3D Generation with Multi-View Conditioned Diffusion.
Research Experience
- ByteDance (CA): Research Scientist (May 2023 – Present); The University of Texas at Dallas: Research Assistant (Jan. 2020 – May 2023); ByteDance (CA): Research Intern (May 2022 – Aug. 2022).
Education
- Ph.D. in Computer Science from the University of Texas at Dallas in 2023, supervised by Prof. Xiaohu Guo; Master's degree in Computer Science from Beihang University in 2018; Bachelor's degree in Software Engineering from Beihang University in 2015.
Background
- A Senior Research Scientist at the Intelligent Creation Lab, ByteDance. His research interests include Computer Graphics, Computer Vision, and AI, with a focus on Talking Face Generation, Conversational Gestures Synthesis, Deblur-NeRF with Human Motion, Text/Image to 3D, and Emotional Talking Avatar.
Miscellany
- Feel free to drop an email if there are common research interests.
