Curriculum Vitae

Shenzhen, China

Yueci Deng (邓岳慈)

Ph.D. Student · Systems, Simulation & Embodied Intelligence

I build high-performance simulation systems and learning infrastructure for embodied intelligence, connecting 3D perception, synthetic data generation, and Sim2Real robot learning.

Download PDF Email Google ScholarGitHub

Education

The Chinese University of Hong Kong, Shenzhen

2025 – Present

Ph.D. in Computer Science

School of Data Science. Supervisor: Prof. Kui Jia.

Nanyang Technological University, Singapore

Jul 2018 – Jun 2019

M.Sc. in Signal Processing

Electrical and Electronic Engineering.

University of Electronic Science and Technology of China / University of Glasgow

Sep 2014 – Jun 2018

B.Eng. in Electronic Information Engineering / B.Eng. (Honours) in Electronics and Electrical Engineering

Joint college programme. University of Glasgow: First Class Honours.

Industry Experience

DexForce Technology Co., Ltd.

Aug 2022 – Aug 2025

Head of Core Engine Team

  • Led core engine development for a Sim2Real embodied AI platform, spanning robot simulation and large-scale synthetic data generation.
  • Built training and deployment infrastructure and a unified computer vision and robotics library for product development.
  • Developed physics-based simulation, rendering, and domain-adaptation pipelines for robotic perception and control.

Pudu Technology Inc.

Dec 2021 – Jul 2022

Computer Vision Engineer

  • Developed 6D pose estimation, scene reconstruction, and collision avoidance for catering service robots.
  • Automated annotation for synthetic, mixed-reality, and real-world data; researched Sim2Real learning with Tsinghua Shenzhen International Graduate School.

RVBUST Inc.

Apr 2020 – Dec 2021

Computer Vision Engineer

  • Developed point cloud registration, recognition, segmentation, and 6D pose estimation for industrial robot vision.
  • Led a cross-functional team developing bin-picking and 3D inspection products.

Appotronics Inc., Research Institute

Aug 2019 – Apr 2020

Computer Vision Engineer

  • Developed projector autofocus and calibration algorithms for camera alignment, screen correction, and distortion compensation.
  • Prototyped 3D projection mapping and projected AR systems, and authored related patents.

Panasonic R&D Centre Singapore

Sep 2018 – Apr 2019

Research Engineer · Internship

  • Developed object detection, pose estimation, and point cloud processing for robotic picking.
  • Researched deep reinforcement learning for motion planning in simulation.
Robot learning code →

Research Grants & Open Source

Development of Multimodal Databases for Robot Learning of Human Skills

Dec 2024 – Dec 2026

Principal Investigator RMB 4 million

Shenzhen Science and Technology Innovation Project (深圳市具身智能重大专项)

Lead simulator-based data generation, Real2Sim mapping, and multimodal dataset and skill database development for robot learning.

EmbodiChain

Project Lead

A modular, GPU-accelerated platform for simulation, synthetic data generation, and robot policy training and evaluation, supporting Sim2Real transfer.

GitHub · Website

Open3D

Apr 2022 – Present

Open-source Collaborator

Collaborate on tensor-based geometry, 3D reconstruction, and the tensor backend of an open-source 3D data processing library.

GitHub · Website

Publications & Reports

Publications, preprints, and reports listed on my homepage. View project pages and resources →

  1. RiCo: Neural Simulation of Rigid-Body Interactions via Local Contact Reasoning

    Ruixiang Ouyang, Guanren Qiao, Fansen Meng, Yueci Deng, Ruixing Jin, Kui Jia, Guiliang Liu†

    arXiv preprint, 2026

  2. RoboSynChallenge: Mastering Real-World Dexterity via Generalizing Synthesized Manipulation Skills

    RoboSynChallenge Organizing Team

    NeurIPS Competition Report, 2026

  3. PAct: Part-Decomposed Single-View Articulated Object Generation

    Qingming Liu, Xinyue Yao, Shuyuan Zhang, Yueci Deng, Guiliang Liu, Zhen Liu†, Kui Jia

    ACM SIGGRAPH Asia, 2026

  4. Backpropagating Through Simulation: Analytic Policy Gradients for Sample and Learning Efficient Differentiable Continuous Control

    Yueci Deng†

    arXiv preprint, 2026

  5. Focus-Then-Contact: Speeding Up Robotic Contact-Rich Task Learning with Affordance-Guided Real-World Residual Reinforcement Learning

    Guanren Qiao, Ruixiang Ouyang, Sheng Xu, Ruixing Jin, Yueci Deng, Yunxin Tai, Kui Jia, Guiliang Liu†

    ICML, 2026

  6. From Reaction to Anticipation: Proactive Failure Recovery through Agentic Task Graph for Robotic Manipulation

    Sheng Xu, Ruixing Jin, Huayi Zhou, Bo Yue, Guanren Qiao, Yunxin Tai, Yueci Deng, Kui Jia, Guiliang Liu†

    RSS, 2026

  7. YOTO++: Learning Long-Horizon Closed-Loop Bimanual Manipulation from One-Shot Human Video Demonstrations

    Huayi Zhou, Ruixiang Wang, Yunxin Tai, Yueci Deng, Guiliang Liu, Kui Jia†

    IEEE TPAMI, 2026

  8. EWA: Aligning Video World Models with Executable Robot Actions via Inverse Dynamics Rewards

    Ruixiang Wang, Qingming Liu, Yueci Deng, Guiliang Liu, Zhen Liu†, Kui Jia

    arXiv preprint, 2026

  9. Sim2Real VLA: Zero-Shot Generalization of Synthesized Skills to Realistic Manipulation

    Runyi Zhao, Sheng Xu, Ruixing Jin, Yueci Deng, Yunxin Tai, Kui Jia, Guiliang Liu†

    ICLR Poster, 2026

  10. GS-World: An Engine-driven Learning Paradigm for Pursuing Embodied Intelligence using World Models of Generative Simulation

    Guiliang Liu, Yueci Deng, Zhen Liu, Kui Jia†

    Position paper, 2025

  11. 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†

    ICML Poster, 2025

  12. 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†

    RSS, 2025

* Equal contribution; † Corresponding author.

Technical Skills

Programming & tools
C / C++ / CUDA · Python · CMake · Git
Research & engineering
3D Computer Vision · Robotics · Machine Learning · Computer Graphics · Differentiable Simulation
Delivery
Applied R&D · Technology Productization · Large-scale Software Development

Patents & Applications

A: application publication; B: invention grant; U: utility model grant.

  • CN114155291ABox pose recognition method, apparatus, terminal and storage medium.
  • CN114653629BVision-based sorting method, intelligent sorting system and readable storage medium.
  • CN114820781AMachine vision-based intelligent handling method, apparatus, system and storage medium.
  • CN217453968URobot, robotic arm and pneumatic gripper.
  • CN121018513ARobot URDF model free assembly and constraint management method and system.
  • CN121683799ASemantic recognition-based dynamic URDF model construction system and method.
  • CN121934817ARobot URDF model construction method, apparatus, electronic device and storage medium.
  • CN122595497ARobot model generation method, apparatus, device and medium.
  • CN122574319AGrasping pose generation method, apparatus, device and computer-readable storage medium.
  • CN122595647AData processing method, apparatus, computer, storage medium and program product.
  • CN113359381BProjection system and projection screen adjustment method.
  • CN113467600BAugmented reality-based information display method, system, apparatus and projection device.
  • CN113467601BAugmented reality-based information display method, system, apparatus and projection device.
  • CN113497925BProjection focusing method and projection focusing device.
  • CN113573035AVision-based adaptive AR-HUD brightness adjustment method.
  • CN113934098BProjection device, automatic focusing method and apparatus.
  • CN114286064AReal-time focusing method, apparatus, system and computer-readable storage medium.