Ekkasit Pinyoanuntapong (เอกสิทธิ์)
I am a Ph.D. student in the WiNS Lab at the University of North Carolina at Charlotte, advised by Prof. Pu Wang. My research interests lie in real-time, scene-aware 3D human motion generation, with a focus on controllability and high-quality synthesis. Currently, I am working on using text-to-motion to guide reinforcement learning through imitation learning, aiming to explore physically plausible motion in simulated environments. In my previous experience, I have worked on augmented reality, physics engine, motion detection and various animation software programs.
Selected Publications

Spatio-Temporal Control for Masked Motion Synthesis
[Previous Name] ControlMM: Controllable Masked Motion Generation
Ekkasit Pinyoanuntapong, Muhammad Usama Saleem, Korrawe Karunratanakul, Pu Wang, Hongfei Xue, Chen Chen, Chuan Guo, Junli Cao, Jian Ren, Sergey Tulyakov
ICCV 2025.






Skeleton-based Human Action Recognition via Convolutional Neural Networks
Ayman Ali, Ekkasit Pinyoanuntapong, Pu Wang, Mohsen Dorodchi
Arxiv 2023.