ZiangZheng | Tsinghua University

About Me

I am an MPhil student at Tsinghua University (School of Vehicle and Mobility, iDlab) working on full-stack humanoid learning: scalable RL for embodied agents, foundation behavior priors (adversarial / diffusion / generative), predictive world models, and closed-loop sim-to-real on Unitree G1. I am the founder of Renforce Dynamics (20+ open-source repos, 1,100+ stars) and gait group lead of the THMOS humanoid soccer team.

Research Interests

Foundation Behavior Models for humanoid whole-body control: adversarial / diffusion motion priors, task-priority optimization, multimodal motion tracking
Predictive World Models for embodied agents: video-conditioned inverse dynamics, VLM-based reasoning under egocentric POMDP
Self-Improving RL: jump-start initialization, self-evolving motion priors, lifelong policy distillation
Cross-Embodiment Sim-to-Real: morphology-agnostic latent-to-latent policies, scalable training infrastructure (IsaacLab / IsaacSim / mjlab / Genesis)

📄 CV: latest (2026-05) · dated archive

News

[2025-07] Released TrackerLab — IsaacLab extension for multi-mode whole-body tracking.
[2025-06] Transferable Latent-to-Latent Locomotion Policy accepted to IROS 2025 (First Author).
[2025-04] Canonical Form of Datatic Description in Control Systems accepted to ACC 2025.
[2025-03] Learn a Safe and Efficient MPC with Lagrange Multiplier Neural Network accepted to IEEE TCST.
[2023] Adaptive Device Sampling and Deadline Determination accepted to Journal of Cloud Computing.

Publications

RA-L

Jump-Start Reinforcement Learning with Self-Evolving Priors for Extreme Monopedal Locomotion

Ziang Zheng, Guojian Zhan, Shiqi Liu, Yao Lyu, Tao Zhang, Shengbo Eben Li

IEEE Robotics and Automation Letters (RA-L), 2025.

PDF Code BibTex Under Review (First Author)

IROS

Transferable Latent-to-Latent Locomotion Policy for Efficient and Versatile Motion Control of Diverse Legged Robots

Ziang Zheng, Guojian Zhan, Bin Shuai, Shengtao Qin, Jiangtao Li, Tao Zhang, Shengbo Eben Li

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2025.

PDF Code BibTex Accepted (First Author)

TCST

Learn a Safe and Efficient Model Predictive Controller with Lagrange Multiplier Neural Network

Guojian Zhan, Ziang Zheng, Feihong Zhang, Jingliang Duan, Shengbo Eben Li, Songan Zhang, H. Eric Tseng

IEEE Transactions on Control Systems Technology (TCST), 2025.

PDF Code BibTex Accepted (Co-First Author)

ACC

Canonical Form of Datatic Description in Control Systems

Guojian Zhan, Ziang Zheng, Shengbo Eben Li

American Control Conference (ACC), 2025.

PDF Code BibTex Accepted (Co-First Author)

JCC

Adaptive Device Sampling and Deadline Determination for Cloud-Based Heterogeneous Federated Learning

Deyu Zhang, Wang Sun, Zi-Ang Zheng, Wenxin Chen, Shiwen He

Journal of Cloud Computing, 2023.

PDF Code BibTex Accepted

GitHub

beyondAMP: A Unified AMP Framework Supporting Arbitrary Task–Prior Combinations

Ziang Zheng

GitHub Repository, 2025.

PDF Code BibTex Open Source

GitHub

TrackerLab: One-Step Unify IsaacLab with Multi-Mode Whole-Body Control

Ziang Zheng

GitHub Repository, 2025.

PDF Code BibTex Open Source

GitHub

GenesisLab: Lightweight Robot Learning Framework for Personal-PC-Scale Training

Ziang Zheng

GitHub Repository, 2025.

PDF Code Open Source

GitHub

MuGS: MuJoCo Gaussian Splatting for Photorealistic Sim-to-Real Rendering

Ziang Zheng

GitHub Repository, 2025.

PDF Code Open Source

GitHub

SoccerLab / IsaacNPC: Multi-Agent Parallel Simulation for Humanoid Soccer

Ziang Zheng

GitHub Repository, 2025.

PDF Code Project Page Open Source

Services

Open Source Community

Renforce Dynamics - Leader