Research & citations

Research & citations#

Citing WBC-MJLab#

If you use WBC-MJLab in your research, please cite the software:

@software{wbc_mjlab2026,
  author  = {Nedelchev, Simeon and Chaplygin, Anton and Kozlov, Lev and Domrachev, Ivan},
  title   = {{WBC-MJLab}: Unified Whole-Body Motion Tracking on mjlab},
  url     = {https://github.com/wbc-mjlab/wbc-mjlab},
  year    = {2026},
  version = {0.0.4},
}

Also cite mjlab — WBC-MJLab is an extension of the simulation and RL stack:

@article{zakka2026mjlab,
  author  = {Zakka, Kevin and Liao, Qiayuan and Yi, Brent and Le Lay, Louis and Sreenath, Koushil and Abbeel, Pieter},
  title   = {{mjlab}: A Lightweight Framework for {GPU}-Accelerated Robot Learning},
  journal = {arXiv preprint arXiv:2601.22074},
  year    = {2026},
  url     = {https://arxiv.org/abs/2601.22074},
  eprint  = {2601.22074},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
}

Lineage & inspiration#

WBC-MJLab aims to be a lightweight, accessible, modular take on whole-body motion tracking — presets and tasks on a shared MDP, plug-in robots, and a small CLI — rather than a monolithic Isaac Lab or vendor-specific stack. The design is informed by prior open WBC codebases (reward/RSI patterns, multi-motion training, deploy export) while running on mjlab + MuJoCo Warp instead of Isaac Sim.

Project

Role

HybridRobotics/whole_body_tracking

Reference BeyondMimic training stack (Isaac Lab); adaptive RSI and tracking MDP ideas. Cite the BeyondMimic paper when comparing methods; the repo itself is cited below.

NVlabs/GR00T-WholeBodyControl

NVIDIA’s unified humanoid WBC platform (decoupled controllers, Isaac-GR00T / GEAR-SONIC lineage). Useful reference for deploy-oriented WBC layout; WBC-MJLab targets a smaller, robot-agnostic training surface on mjlab.

When you build on ideas from these codebases, cite them alongside WBC-MJLab and mjlab:

@software{hybridrobotics_wbt,
  author  = {{Hybrid Robotics}},
  title   = {{whole\_body\_tracking}: BeyondMimic Motion Tracking (Isaac Lab)},
  url     = {https://github.com/HybridRobotics/whole_body_tracking},
  year    = {2025},
}

@software{nvlabs_groot_wbc2026,
  author  = {{NVIDIA}},
  title   = {{GR00T} Whole-Body Control},
  url     = {https://github.com/NVlabs/GR00T-WholeBodyControl},
  year    = {2026},
}

Method papers (cite when using a task)#

When you train or compare a registered task, cite the original method paper in addition to wbc-mjlab and mjlab. See Tasks and presets.

Method

Title

wbc-mjlab task(s)

Year

ZEST

Zero-shot Embodied Skill Transfer

Wbc-G1, Wbc-G1-Zest, Wbc-G1-SE, Wbc-G1-Zest-SE

2026

BeyondMimic

From Motion Tracking to Versatile Humanoid Control

Wbc-G1-BinaryFailure

2025

SONIC

Supersized motion tracking

partial (body-velocity rewards, obs.corruption); full preset planned

2025

OmniXtreme

High-dynamic scalable tracking

partial (G1 torque envelope)

2026

BibTeX entries for method papers#

@article{zest2026,
  author  = {Sleiman, Jean-Pierre and Li, He and Adu-Bredu, Alphonsus and Deits, Robin and Kumar, Arun and Bergamin, Kevin and Bhardwaj, Mohak and Biddlestone, Scott and Burger, Nicola and Estrada, Matthew A. and Iacobelli, Francesco and Koolen, Twan and Lambert, Alexander and Lin, Erica and Mungai, M. Eva and Nobles, Zach and Rozen-Levy, Shane and Shi, Yuyao and Wang, Jiashun and Welner, Jakob and Yu, Fangzhou and Zhang, Mike and Rizzi, Alfred and Hodgins, Jessica and Bertrand, Sylvain and Abe, Yeuhi and Kuindersma, Scott and Farshidian, Farbod},
  title   = {{ZEST}: Zero-shot Embodied Skill Transfer for Athletic Robot Control},
  journal = {arXiv preprint arXiv:2602.00401},
  year    = {2026},
  url     = {https://arxiv.org/abs/2602.00401},
  eprint  = {2602.00401},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
}

@article{liao2025beyondmimic,
  author  = {Liao, Qiayuan and Truong, Takara E. and Huang, Xiaoyu and Gao, Yuman and Tevet, Guy and Sreenath, Koushil and Liu, C. Karen},
  title   = {{BeyondMimic}: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion},
  journal = {arXiv preprint arXiv:2508.08241},
  year    = {2025},
  url     = {https://arxiv.org/abs/2508.08241},
  eprint  = {2508.08241},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
}

@article{sonic2025,
  author  = {Luo, Zhengyi and Yuan, Ye and Wang, Tingwu and Li, Chenran and Chen, Sirui and Casta{\~n}eda, Fernando and Cao, Zi-Ang and Li, Jiefeng and Minor, David and Ben, Qingwei and Da, Xingye and Ding, Runyu and Hogg, Cyrus and Song, Lina and Lim, Edy and Jeong, Eugene and He, Tairan and Xue, Haoru and Xiao, Wenli and Wang, Zi and Yuen, Simon and Kautz, Jan and Chang, Yan and Iqbal, Umar and Fan, Linxi and Zhu, Yuke},
  title   = {{SONIC}: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control},
  journal = {arXiv preprint arXiv:2511.07820},
  year    = {2025},
  url     = {https://arxiv.org/abs/2511.07820},
  eprint  = {2511.07820},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
}

@article{omnixtreme2026,
  author  = {Wang, Yunshen and Zhu, Shaohang and Zhi, Peiyuan and Li, Yuhan and Li, Jiaxin and Li, Yong-Lu and Xiao, Yuchen and Wang, Xingxing and Jia, Baoxiong and Huang, Siyuan},
  title   = {{OmniXtreme}: Breaking the Generality Barrier in High-Dynamic Humanoid Control},
  journal = {arXiv preprint arXiv:2602.23843},
  year    = {2026},
  url     = {https://arxiv.org/abs/2602.23843},
  eprint  = {2602.23843},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
}

Technical report#

A formal tech report lives in paper/main.tex (local draft; see repo .gitignore). BibTeX for copy-paste citations: docs/source/_static/refs.bib. Citation metadata: CITATION.cff at the repo root. arXiv submission tracked in issue #31.