Minho Heo

[firstname].[lastname] at kaist.ac.kr

I am a second-year master/Ph.D student in the Cognitive Learning for Vision and Robotics Lab (CLVR) at KAIST, advised by Prof. Joseph J. Lim.

Before joining KAIST, I received my B.S. degree in Computer Science at Kookmin University. I also worked for Epic Games as a software engineering consultant and BinaryVR as a software engineering intern.

Twitter  /  Github  /  Google Scholar

profile photo
Research

My research goal is to endow physical robots with the ability to carry out dexterous, long-horizon tasks. My vision begins with creating robots that can assist in our everyday lives and eventually scales up to more complex tasks, like building houses or even entire cities!

This goal is rooted in my curiosity about understanding physical intelligence. To achieve this, I am developing agents with the ability to plan over long horizons, incorporating a physical understanding of the world. They also possess the capability to reactively adjust their control, much like many animals do.

Publications

(representative papers are highlighted)

EXTRACT: Efficient Policy Learning by Extracting Transferrable Robot Skills from Offline Data
Jesse Zhang, Minho Heo, Zuxin Liu, Erdem Bıyık, Joseph J. Lim, Yao Liu, Rasool Fakoor
CoRL 2024
Paper / Website

DROID: A Large-Scale In-the-Wild Robot Manipulation Dataset
DROID Dataset Team Collaboration, ..., Minho Heo, ...
RSS 2024
Paper / Website

Open X-Embodiment: Robotic Learning Datasets and RT-X Models
Open X-Embodiment Collaboration, ..., Minho Heo, ...
ICRA 2024 (Best Conference Paper Award)
Paper / Website

FurnitureBench: Reproducible Real-World Benchmark for Long-Horizon Complex Manipulation
Minho Heo*, Youngwoon Lee*, Doohyun Lee, Joseph J. Lim
RSS 2023 (Best System Paper Award)
Paper / Website / talk

Academic Activities

Conference reviewer

  • ICRA 2025, ICLR 2025, CoRL 2024, RSS 2024


Website template from Jon Barron