Yueci Deng (邓岳慈)

Yueci Deng (邓岳慈)

PhD Student at School of Data Science, The Chinese University of Hong Kong, Shenzhen.

I am a first-year CS Ph.D. student at the School of Data Science, Chinese University of Hong Kong, Shenzhen (CUHK-SZ), supervised by Prof Kui Jia. I received my Bachelor’s degree in University of Electronic Science and Technology of China (UESTC, 2014 - 2018), and Master’s degree in Nanyang Technological University (NTU, 2018-2019), Singapore. Before joining CUHK-SZ, I worked as a R&D engineer at DexForce Technology, where I lead the development of DexVerseTM, the world’s leading Sim2Real AI Platform for embodied intelligence.

My research interests are mainly in the following areas:

  • Simulation: Generative simulation, Differentiable rendering and physics, GPU-accelerated simulation.
  • Embodied Intelligence: Large-scale model training with online data streams, Sim2Real and domain adaptation, Continual learning and self-evolution of embodied agents.

Projects

Open3D Open3D: A Modern Library for 3D Data Processing
Website | Code

Description: The leading open-source library for 3D processing with 400K+ monthly downloads from PyPI. Open3D exposes a set of carefully selected data structures and algorithms in both C++ and Python for 3D data processing tasks including point cloud processing, mesh processing, and 3D visualization.

Publications

DexScale DexScale: Automating Data Scaling for Sim2Real Generalizable Robot Control
Guiliang Liu*, Yueci Deng*, Runyi Zhao, Huayi Zhou, Jian Chen, Jietao Chen, Ruiyan Xu, Yunxin Tai, Kui Jia
(*Equal contribution)
International Conference on Machine Learning (ICML), 2025 Poster
Paper / Code (Coming Soon)

Description: A novel data engine for automating data generation and scaling for sim-to-real transfer of robotic manipulation tasks.

YOTO You Only Teach Once: Learn One-Shot Bimanual Robotic Manipulation from Video Demonstrations
Huayi Zhou, Ruixiang Wang, Yunxin Tai, Yueci Deng, Guiliang Liu, Kui Jia
Robotics: Science and Systems (RSS), 2025
Paper / Code

Description: This work proposes the YOTO (You Only Teach Once), which can extract and then inject patterns of bimanual actions from as few as a single binocular observation of hand movements, and teach dual robot arms various complex tasks.