About me

I am a Ph.D. student at KAIST in the Machine Learning and AI (MLAI) Lab, advised by Prof. Sung Ju Hwang. My research interests are in embodied agents, spatially aware intelligence, and robotics. [CV]

Previously, I worked on embodied agents with long-term spatial memory in open-ended environments such as Minecraft, and on injecting spatial structure into transformer architectures (Spatially-Aware Transformer).

Currently, my work focuses on robotics — building sim2real pipelines that bridge physics-based simulators and the real world via video-based world models and vision-language-action (VLA) models, aiming for robust real-world deployment.

Email: junmokane [at] kaist [dot] ac [dot] kr

Conference

• SpeedAug: Policy Acceleration via Tempo-Enriched Policy and RL Fine-Tuning

  [paper]
  ​Taewook Nam, Junmo Cho, Youngsoo Jang, Sung Ju Hwang
  Under Submission, 2026

• GFlowPO: Generative Flow Network as a Language Model Prompt Optimizer

  [paper]
  ​Junmo Cho*, Suhan Kim*, Sangjune An*, Minsu Kim, Dong Bok Lee, Heejun Lee, Sung Ju Hwang, Hae Beom Lee
  Under Submission, 2026

• Mr. Steve: Instruction-Following Agents in Minecraft with What-Where-When Memory

  [paper]
  ​Junyeong Park*, Junmo Cho*, Sungjin Ahn
  International Conference on Learning Representations (ICLR), 2025

• Spatially-Aware Transformer for Embodied Agents

  [paper]
  ​Junmo Cho*, Jaesik Yoon*, Sungjin Ahn
  International Conference on Learning Representations (ICLR), 2024 (Spotlight)

• Robust and Efficient Image Alignment of Biomedical Images through Simultaneous Low Rank and Sparse Decomposition

  [paper]
  ​Junmo Cho*, Seungjae Han*, Eun-Seo Cho, Kijung Shin, Young-Gyu Yoon
  Winter Conference on Applications of Computer Vision (WACV), 2023

• Inducing Functions through Reinforcement Learning without Task Specification

  [paper]
  ​Junmo Cho, Dong-Hwan Lee, Young-Gyu Yoon
  NeurIPS Workshop on Deep Reinforcement Learning (NeurIPS Workshop Deep RL), 2022

Journal

• Abunmix enables the simple and robust multiplexed immunofluorescence imaging

  [paper]
  ​Woonggi La*, Seoungbin Bae*, Junyoung Seo*, Hayeong Yu*, Junmo Cho, Hyunwoo Kim, Hoyeon Nam, Seungjae Han, Euiin Yi, Eunsu Kim, Chan Kang, Hyejin Shin, Chang Woo Song, Young-Gyu Yoon, Jae-Byum Chang
  VIEW, 2026

* denotes equal contribution.

Service

Reviewer: ICML 2022, 2024, 2026 (Awarded as Gold Reviewer), and NeurIPS 2022, 2023.

Teaching Assistant, KAIST: CS672: Reinforcement Learning (Fall 2023, Fall 2024), CS492: Deep Reinforcement Learning and Game AI (Spring 2024, Best TA Award), CS492: Deep Reinforcement Learning (Spring 2023), CoE202: Basics of Artificial Intelligence (Fall 2020), MAS101: Calculus I, Freshmen Tutoring (Spring 2019).

Education

• Ph.D. in Graduate School of AI, KAIST, Aug. 2022 – Present
  Advisor: Prof. Sung Ju Hwang
• M.S. in Electrical Engineering, KAIST, Feb. 2022
  Advisor: Prof. Young-Gyu Yoon
• B.S. in Electrical Engineering and Computer Science (Double Major, Minor in Mathematical Science), KAIST, Feb. 2020