LessMimic: Long-Horizon Humanoid Interaction with Unified Distance Field Representations
Yutang Lin*, Jieming Cui*, Yixuan Li, Baoxiong Jia, Yixin Zhu†, Siyuan Huang†

Project / Code / Video / Paper

We introduce LessMimic, a unified interaction representation enabling reference-free inference, geometric generalization, and long-horizon skill composition within one policy remains an open challenge.

UniAct: Unified Motion Generation and Action Streaming for Humanoid Robots
Nan Jiang*, Zimo He*, Wanhe Yu, Lexi Pang, Yunhao Li, Hongjie Li, Jieming Cui, Yuhan Li, Zizhou Wang, Yixin Zhu†, Siyuan Huang†

Project / Code / Video / Paper

We introduce UniAct, a two-stage framework integrating a fine-tuned MLLM with a causal streaming pipeline, enabling humanoid robots to execute multimodal instructions with sub-500ms latency.

CLONE: Closed-Loop Whole-Body Humanoid Teleoperation for Long-Horizon Tasks
Yixuan Li*, Yutang Lin*, Jieming Cui, Tengyu Liu, Wei Liang, Yixin Zhu†, Siyuan Huang†

Project / Code / Video / Paper

We introduce CLONE, an MoE-based policy with closed-loop error correction for holistic humanoid teleoperation. It enables capabilities previously unattainable with existing systems—such as whole-body coordination and long-horizon task execution, with minimal input from a commercial MR headset.

GROVE: A Generalized Reward for Learning Open-Vocabulary Physical Skill
Jieming Cui*, Tengyu Liu*, Ziyu Meng, Jiale Yu,Ran Song,Wei Zhang, Yixin Zhu†, Siyuan Huang†

Project / Code / Video / 北大新闻网 / 北大科研进展速览

We introduce GROVE, a generalized reward framework that enables open-vocabulary physical skill learning without manual engineering or task-specific demonstrations.

AnySkill: Learning Open-Vocabulary Physical Skill for Interactive Agents
Jieming Cui*, Tengyu Liu*, Nian Liu*, Yaodong Yang, Yixin Zhu†, Siyuan Huang†

Project / Code / Video / Paper

We propose AnySkill, a novel hierarchical method that learns physically plausible interactions following open-vocabulary instructions. An important feature of our method is the use of image-based rewards for the high-level policy, which allows the agent to learn interactions with objects without manual reward engineering.

ProBio: A Protocol-guided Multimodal Dataset for Molecular Biology Lab
Jieming Cui*, Ziren Gong* , Baoxiong Jia*, Siyuan Huang, Zilong Zheng†, Jianzhu Ma†, Yixin Zhu†

Project / Code / Video / Paper / 北大AI院官微

We first curate a comprehensive multimodal dataset, named ProBio, as an initial step towards monitoring system. This dataset comprises fine-grained hierarchical annotations intended for the purpose of studying activity understanding in Biology lab.

Full-Body Articulated Human-Object Interaction
Nan Jiang*, Tengyu Liu*, Zhexuan Cao, Jieming Cui, He Wang, Yixin Zhu†, Siyuan Huang†

Project / Code / Paper

We present CHAIRS, a large-scale motion-captured f-AHOI dataset, consisting of 16.2 hours of versatile interactions between 46 participants and 74 articulated and rigid sittable objects. CHAIRS provides 3D meshes of both humans and articulated objects during the entire interactive process, as well as realistic and physically plausible full-body interactions.