Publications

You can also find my articles on my Google Scholar profile.

Journal Articles

E2HiL: Entropy-Guided Sample Selection for Efficient Real-World Human-in-the-Loop Reinforcement Learning

Published in IEEE Robotics and Automation Letters (RA-L), 2026

A human-in-the-loop reinforcement learning framework that actively selects informative samples via entropy guidance, sharply reducing the number of human interventions needed to learn real-world robotic manipulation.

Recommended citation: Haoyuan Deng, Yudong Lin, Yuanjiang Xue, Haoyang Du, Qianzhun Wang, Boyang Zhou, Zhenyu Wu, Ziwei Wang. (2026). "E2HiL: Entropy-Guided Sample Selection for Efficient Real-World Human-in-the-Loop Reinforcement Learning." IEEE Robotics and Automation Letters.
Download Paper

Preprints

Facet-0: A Robotic Foundation Model for Contact-Rich Precise Manipulation

Published in arXiv preprint arXiv:2609.01596, 2026

A robotic foundation model that predicts and values the contact consequences of its actions, reaching 82% success on sub-millimeter assembly tasks where the strongest baseline reaches 15%.

Recommended citation: Haoyuan Deng, Haichao Liu, Wenkai Guo, Yuan Ling, Zaijia Yang, Yuanjiang Xue, Haosheng Sun, Liangzi Wang, Ziwei Wang. (2026). "Facet-0: A Robotic Foundation Model for Contact-Rich Precise Manipulation." arXiv preprint arXiv:2609.01596.
Download Paper

DexTeleop-0: Force-Aware Bimanual Dexterous Teleoperation with Ego-Centric Perception towards Shared Autonomy

Published in arXiv preprint arXiv:2606.23431, 2026

A tactile-driven adaptation strategy that closes the embodiment gap in bimanual dexterous teleoperation, translating coarse human tracking intent into precise, force-compliant robot commands.

Recommended citation: Haichao Liu, Yuyao Jiang, Hyunsun Park, Yuanjiang Xue, Ziwei Wang. (2026). "DexTeleop-0: Force-Aware Bimanual Dexterous Teleoperation with Ego-Centric Perception towards Shared Autonomy." arXiv preprint arXiv:2606.23431.
Download Paper

UniManip: General-Purpose Zero-Shot Robotic Manipulation with Agentic Operational Graph

Published in arXiv preprint arXiv:2602.13086, 2026

A bi-level Agentic Operational Graph that unifies semantic reasoning with physical grounding, achieving zero-shot manipulation of unseen objects and tasks and direct transfer from fixed-base to mobile manipulation.

Recommended citation: Haichao Liu, Yuanjiang Xue, Yuheng Zhou, Haoyuan Deng, Yinan Liang, Lihua Xie, Ziwei Wang. (2026). "UniManip: General-Purpose Zero-Shot Robotic Manipulation with Agentic Operational Graph." arXiv preprint arXiv:2602.13086.
Download Paper