Runhan Huang

I am an undergraduate student from Tsinghua University, Yao Class. At Tsinghua University, I am fortunately advised by Prof. Hang Zhao in MARS Lab. At Harvard's Kempner AI institute, I am a visiting researcher advised by Prof. Yilun Du. I also spent time at Shanghai Qizhi Institute.

I am currently seeking for a PhD position for Fall 2026. Feel free to reach out via email at runhanhuang2004(at)gmail.com!

Email  /  CV  /  Scholar  /  Github  /  Linkedin  /  Twitter

Recent News

Research

My research interests center on Robotics, Generative Models and Reinforcement Learning. My goal is to develop robotic systems that can interact robustly and plan effectively in real-world environments, achieving generalizable and adaptable behaviors. I am also open to exploring other relevant research topics. Some papers are highlighted.

We propose a real-to-sim-to-real framework that leverages rapid test-time training (TTT) on novel terrains, significantly enhancing the robot's capability to traverse extremely difficult geometries.

We introduces a test-time adaptable locomotion planner grounded in a diffusion-based generative prior. An interactive training procedure further improves the performance of diffusion-based planners.

MoELoco introduces a multitask locomotion framework that employs a mixture-of-experts strategy to enhance reinforcement learning across diverse tasks while leveraging compositionality to generate new skills.

VR-Robo introduces a digital twin framework using 3D Gaussian Splatting for photorealistic simulation, enabling RGB-based sim-to-real transfer for robot navigation and locomotion.

We propose a proprioception-only, two-stage training framework with goal command and a dedicated tiny trap benchmark, enabling quadruped robots to robustly traverse small obstacles.

Miscellanea

Template forked from Jon Barron. A big thanks to him!