Posts by Collection

portfolio

publications

UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling

Published in arXiv (accepted at NeurIPS 2026), 2026

UniT establishes a unified physical language — a single tokenizer that enables zero-shot human-to-humanoid transfer for both policy learning and world modeling.

Recommended citation: Boyu Chen, Yi Chen, Lu Qiu, Jerry Bai, Yuying Ge, and Yixiao Ge. "UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling." arXiv preprint arXiv:2604.19734, 2026.
Download Paper | Download Bibtex

Inside Fe₀: What Cross-Embodiment Data Teaches an Embodied Foundation Model

Published in XPENG Robotics Blog, 2026

Fe0 takes UniT’s cross-embodiment premise to scale, learning from large heterogeneous datasets and studying what capabilities transfer—and where scaling still fails.

Recommended citation: Yizhuo Li, Xiaoyu Zhang, Yuying Ge, Teng Wang, Boyu Chen, Yi Chen, Bo Liu, Feng Qiu, Jiacheng Wei, Yuguo Gan, Hui Zhou, Yixiao Ge. "Inside Fe0: What Cross-Embodiment Data Teaches an Embodied Foundation Model." XPENG Robotics Blog, 2026.
Download Bibtex

AnyWorld: Factorized Egocentric World Models for Cross-Embodiment Generalization

Published in arXiv (accepted at CoRL 2026), 2026

AnyWorld extends UniT through world modeling, turning human interactions into controllable robot-native experience for downstream UniT policy adaptation.

Recommended citation: Cheng Chen, Jerry Bai, Jiacheng Wei, Boyu Chen, Xiaoji Zheng, Fan Wu, Minghao Yang, Tianrun Chen, Ruibo Li, Xiaoyu Yue, Xiaoyang Guo, Yixiao Ge, Guosheng Lin, and Fayao Liu. "AnyWorld: Factorized Egocentric World Models for Cross-Embodiment Generalization." arXiv preprint arXiv:2608.29242, 2026.
Download Paper | Download Bibtex

GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives

Published in arXiv preprint, 2026

GroundingPI learns points and boxes as shared visual primitives, then transfers its perceptual representations to robotic manipulation and autonomous driving.

Recommended citation: Qize Yu, Lianrui Fan, Boyu Chen, Jiaqi Liang, Xini Ding, Yue Chen, Zetian Song, Yuran Wang, Yi Zou, Kaixuan Wang, Tianxing Chen, Wenxuan Song, Bohan Zhou, Mingleyang Li, Siqiao Huang, Yuqi Ye, Caigao Jiang, Wei Wei, Ruihai Wu, Hang Zhang, Yixiao Ge, Shuchang Zhou, Shilong Liu, Xianming Liu, Ping Luo, Shiyu Huang. "GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives." arXiv preprint arXiv:2609.39601, 2026.
Download Paper | Download Bibtex

Boyu Chen