Featured Works

Three ivory, sage, and terracotta flows representing vision, language, and action merge into an open eye shape

Z-sight: Unifying Vision-Language-Action and Latent World Modeling

Bringing latent world modeling into vision-language-action models.

Publishing
Minimal 3D robotic arm holding a terracotta sphere, representing control

Ψ0.1: A Steerable Humanoid VLA Model for Long-Horizon Loco-Manipulation

Steerable humanoid control that combines world modeling with vision-language-action learning.

Publishing
A ceramic robot with closed eyes dreaming of a terracotta cube in a thought bubble

WE-Dream: Generalizable Humanoid World-Action Models with Latent-Action Pretraining and Routed Attention

Learning from human video to generalize humanoid control across tasks, environments, and skill combinations.

Publishing
Two 3D robotic grippers jointly holding a sphere, representing collaboration

DUET: Dual-Robot Understanding via Efficient Teaching

Learning coordinated robot collaboration from human demonstrations.

Paper Project Video
A stylized DNA double helix used as a conceptual symbol of genetics and molecular biomarkers

Exploration of Potential Biomarkers for Diagnosing Dementia through Machine Learning Techniques

Muchen Xu · American Journal of Student Research ·

Using machine learning to identify blood-based miRNA candidates for dementia diagnosis and subtype differentiation.

Paper (PDF)