ULTRA: Unified Multimodal Control for Autonomous Humanoid Whole-Body Loco-Manipulation

Xialin He*, Sirui Xu*, Xinyao Li, Runpei Dong, Liuyu Bian, Yu-Xiong Wang, Liang-Yan Gui

IROS2026 (Oral)

A unified framework for autonomous humanoid whole-body loco-manipulation combining physics-driven motion retargeting with multimodal control.

ContactMimic: Humanoid Object Interaction via Contact Control

Xinyao Li*, Xialin He*, Runpei Dong, Saurabh Gupta

CoRL2026
🏅 Best Paper Award, Contact & Learning Workshop, IROS 2026

A learning framework tracking part-level contact commands alongside keypoint trajectories for precise, controllable humanoid-object interaction.

Learning Getting-Up Policies for Real-World Humanoid Robots

Xialin He*, Runpei Dong*, Zixuan Chen, Saurabh Gupta

RSS2025

A learning framework for humanoid fall recovery with two-stage training: discovering getting-up trajectories, then refining them for smoothness and robustness.

Learning Smooth Humanoid Locomotion through Lipschitz-Constrained Policies

Zixuan Chen*, Xialin He*, Yen-Jen Wang*, Qiayuan Liao, Yanjie Ze, Zhongyu Li, S. Shankar Sastry, Jiajun Wu, Koushil Sreenath, Saurabh Gupta, Xue Bin Peng

IROS2025 (Oral)

Lipschitz-Constrained Policies (LCP) for smooth locomotion in legged robots.

OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning

Tairan He*, Zhengyi Luo*, Xialin He*, Wenli Xiao, Chong Zhang, Weinan Zhang, Kris Kitani, Changliu Liu, Guanya Shi

CoRL2024

A learning-based system for whole-body humanoid teleoperation and autonomy.

Visual Manipulation with Legs

Xialin He*, Chengjing Yuan*, Wenxuan Zhou, Ruihan Yang, David Held, Xiaolong Wang

CoRL2024

Enabling quadruped robots to manipulate objects with legs using RL and point cloud observations.

HERO: Learning Humanoid End-Effector Control for Visual Whole-Body Open-Vocabulary Object Grasping

Runpei Dong*, Ziyan Li*, Arjun Gupta, Xialin He, Saurabh Gupta

CoRL2026

HERO enables visual loco-manipulation of arbitrary objects with humanoid robots.

InterPrior: Scaling Generative Control for Physics-Based Human-Object Interactions

Sirui Xu, Samuel Schulter, Morteza Ziyadi, Xialin He, Xiaohan Fei, Yu-Xiong Wang, Liang-Yan Gui

CVPR2026 (Highlight)
🏅 Best Poster Award, Interactive Physical AI Workshop

A scalable generative controller for humanoid human-object interactions.

SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation

Zekun Qi*, Wenyao Zhang*, Yufei Ding*, Runpei Dong, ..., Xialin He, ..., Li Yi

NeurIPS2025 (Spotlight)

Semantic orientation using natural language for improved robotic manipulation.

AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time

Junyu Zhang*, Runpei Dong*, ..., Xialin He, ..., Huan Zhang

EMNLP2025

A test-time framework controlling reasoning speed using a universal alpha parameter.

Generalizable Humanoid Manipulation with 3D Diffusion Policies

Yanjie Ze, Zixuan Chen, Wenhao Wang, Tianyi Chen, Xialin He, Ying Yuan, Xue Bin Peng, Jiajun Wu

IROS2025 (Oral)

iDP3 enables humanoid robots to perform autonomous tasks using egocentric 3D visual representations.

Sim-to-Real Transfer for Quadrupedal Locomotion via Terrain Transformer

Hang Lai, Weinan Zhang, Xialin He, Chen Yu, Zheng Tian, Yong Yu, Jun Wang

ICRA2023

Terrain Transformer (TERT) for quadrupedal locomotion over multiple terrains.