Minghuan Liu

Shanghai Jiao Tong University — China

Computer Science · Physical Sciences

12h-index491citations70works1.32yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Reinforcement Learning in Robotics(19), Hydrology and Watershed Management Studies(10), Multimodal Machine Learning Applications(9), Robot Manipulation and Learning(7), Adversarial Robustness in Machine Learning(6)

Publications70 total

What matters in building vision–language–action models for generalist robots
Nature Machine Intelligence·2026
Scalable and General Whole-Body Control for Cross-Humanoid Locomotion
ArXiv.org·2026Open Access
Scalable and General Whole-Body Control for Cross-Humanoid Locomotion
arXiv (Cornell University)·2026Open Access
H-Zero: Cross-Humanoid Locomotion Pretraining Enables Few-shot Novel Embodiment Transfer
arXiv (Cornell University)·2025Open Access
Research on the estimation method of crop net primary productivity based on improved CASA model
Frontiers in Plant Science·2025Open Access
Assessing the impacts of irrigation and soil types on the water balance and groundwater depletion in an irrigation district of the North China Plain based on a coupled SWAT-MODFLOW model
Agricultural Water Management·2025· 2 citedOpen Access
Manipulation as in Simulation: Enabling Accurate Geometry Perception in Robots
arXiv (Cornell University)·2025Open Access
Improving crop evapotranspiration estimation in the Yellow River Basin: A modified SEBAL model approach and spatiotemporal trend analysis
Agricultural Water Management·2025Open Access
River discharge estimation with a small number of data points: a transfer learning approach
Measurement Science and Technology·2025
A Unified and General Humanoid Whole-Body Controller for Fine-Grained Locomotion
2025· 6 citedOpen Access
Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation
2025· 8 cited
WildLMa: Long Horizon Loco-Manipulation in the Wild
2025· 1 cited
Towards Generalist Robot Policies: What Matters in Building Vision-Language-Action Models
2025· 2 citedOpen Access
RHINO: Learning Real-Time Humanoid-Human-Object Interaction from Human Demonstrations
arXiv (Cornell University)·2025Open Access
EXPERT expands prime editing efficiency and range of large fragment edits
Nature Communications·2025· 13 citedOpen Access
Re$^3$Sim: Generating High-Fidelity Simulation Data via 3D-Photorealistic Real-to-Sim for Robotic Manipulation
arXiv (Cornell University)·2025Open Access
A Unified and General Humanoid Whole-Body Controller for Versatile Locomotion
arXiv (Cornell University)·2025Open Access
Multi-Agent Trajectory Prediction with Scalable Diffusion Transformer
2024· 1 cited
What Matters in Building Vision-Language-Action Models for Generalist Robots
ArXiv.org·2024Open Access
PromptDepthAnything++: Accurate 4K Metric Depth Estimation via Pattern-Agnostic Prompting
arXiv (Cornell University)·2024Open Access
page 1 of 4Next →

Frequent Co-authors

Weinan Zhang(24), Yong Yu(8), Menghui Zhu(6), Jian Shen(5), Yao Jiang(4), Xu Xu(4), Quanzhong Huang(4), Guanhua Huang(4), Kan Ren(4), Zhengbang Zhu(4), Yuzheng Zhuang(4), Tadaharu ISHIKAWA(4), Kenji Yoshimi(4), Xinghang Li(3), Tao Kong(3), Weijun Hong(3), Tairan He(3), Ming Zhou(3), Yufei Xue(3), Zhengyu Yang(3)