Scholar
Yuxuan Mu
Google Scholar ID: Feoyh4AAAAAJ
Simon Fraser University
Citations & Impact
Citations
336
H-index
6
i10-index
5
Publications
11
Co-authors
15
list available
Publications
Resume (English only)
Academic Achievements
- StableMotion: Training motion cleanup models with unpaired corrupted data, SIGGRAPH Asia 2025 (first author)
- MotionDreamer: One-to-more motion synthesis with localized generative masked transformer, ICLR 2025
- GSD: First 3D diffusion model directly on Gaussian Splatting for real-world reconstruction, ECCV 2024
- MoMask: Generative masked modeling for text-driven 3D human motion generation, CVPR 2024 (co-first author)
- Generative Human Motion Stylization in Latent Space, ICLR 2024 (co-first author)
- RACon: Retrieval-augmented simulated character locomotion control, ICME 2024 (Oral, first author)
- Event-based Human Pose Tracking by Spiking Spatiotemporal Transformer, IEEE TCSVT 2023
Background
- Ph.D. student at the GrUVi Lab, Simon Fraser University, advised by Professor Xue bin (Jason) Peng
- Research focuses on character animation and embodied AI
- Work centers around 3D human motion—spanning estimation, generation, physics simulation, and control
- Aims to bridge the gap between physical and virtual worlds for richer perception, understanding, and interaction
- Designs generative models and reinforcement learning systems that leverage physics simulations to better capture and replicate human behavior
