Authors

Author Profiles and Contributions

DexHoldem brings together real-world dexterous manipulation, teleoperated data collection, policy learning, embodied-agent design, perception benchmarking, simulation, and project guidance.

DexHoldem logo

Project lead, equal contribution

Feng Chen*†

Co-proposed and led the project; designed the data-collection infrastructure; maintained the hardware; trained DP, RDT, and ACT; contributed to the embodied-agent and perception-benchmark design; collected data; and built the project website.

Equal contribution

Tianzhe Chu*

Co-proposed the project; designed the data-collection infrastructure; led the embodied-agent and perception-benchmark design; and performed teleoperation.

Equal contribution

Li Sun*

Co-proposed the project; designed the data-collection infrastructure; trained Octo; and performed teleoperation.

Equal contribution

Pei Zhou*

Trained the pi-series and BAKU models; deployed and evaluated policy models and embodied agents; and performed teleoperation.

Simulation and evaluation

Zhuxiu Xu

Designed the simulation component; deployed and evaluated embodied agents; and collected data.

Guidance and feedback

Shenghua Gao

Provided project guidance and feedback.

Co-proposal, guidance, and feedback

Yuexiang Zhai

Co-proposed the project and provided project guidance and feedback.

Guidance and feedback

Yanchao Yang

Provided project guidance and feedback.

Co-proposal, guidance, and feedback

Yi Ma

Co-proposed the project and provided project guidance and feedback.