Research

Selected research on human-centered embodied intelligence, humanoid self-representation, reliable embodied-agent systems, 3D vision, and interpretable scientific machine learning.

I study how robots recognize and model their own bodies, and how embodied agents use contact history and execution feedback to act reliably. My current projects explore humanoid self-representation, hygiene-aware household planning, and real-robot deployment with verified action outcomes. My broader work spans interpretable scientific machine learning and generative 3D rigging.

project thumbnail

Humanoid Self-Representation

Learning which body is the self—and how that body occupies 3D space—from sensorimotor experience.
project thumbnail

HygieneRoboBench

A robot’s next safe action depends on what it touched before.
project thumbnail

Thea & Unitree G1

Deploying Unitree G1 locomotion and manipulation within a closed-loop embodied-agent harness for long-horizon tasks and failure recovery.
project thumbnail

Interpretable Scientific ML with KAN

Physics-guided Kolmogorov–Arnold Networks that turn learned predictors into inspectable retrieval formulas.
project thumbnail

Generative 3D Rigging

Learning skeletons, skinning, and semantic correspondence for controllable 3D assets.