Jisang Park

jisangp at stanford dot edu

I am a Stanford MSCS student and robotics researcher at the IPRL Lab & REAL Lab, where I am co-advised by Jeannette Bohg and Shuran Song. I am fortunate to be directly mentored by Dian Wang and to work closely with Xiaomeng Xu and Han Zhang. Before Stanford, I spent 1.5+ years as a Research Scientist at KAIST. My research focuses on data-efficient and generalizable policy learning for long-horizon bimanual mobile manipulation.

Prior to my research path, I co-founded three startups, gained strategic consulting experience at McKinsey & BCG, and majored in Business Administration and Computer Science. This background motivates my focus on translating robotics research into practical, impactful products.

CV & Resume (On Request) LinkedIn Google Scholar Github X

News

Sep 2026 Mixture of Frames Policy was accepted to CoRL 2026. See you at Austin!
Sep 2026 HoMMI won Best Paper Awards at two IROS 2026 workshops.
Sep 2026 Awarded a Graduate Research Assistantship with Jeannette Bohg for four consecutive quarters.
Apr 2026 HoMMI was accepted to RSS 2026.
Nov 2025 Compositional Phoneme Approximation was accepted to IJCNLP-AACL 2025.
Sep 2025 Joined IPRL Lab & REAL Lab, mentored by Dian Wang.
Sep 2025 Started the MSCS program at Stanford University.
Jan 2024 Appointed as a Research Scientist at KAIST Robust Intelligence & Robotics Lab.
Sep 2023 Joined KAIST Robust Intelligence & Robotics Lab.
Aug 2022 Graduated from Seoul National University with Summa Cum Laude.

Research

Mixture of Frames Policy: Multi-Frame Action Denoising for Bimanual Mobile Manipulation

Dian Wang*, Jisang Park*, Xiaomeng Xu, Han Zhang, Shuran Song, Jeannette Bohg

Conference on Robot Learning (CoRL) 2026

Webpage • Paper • Video • Code

HoMMI: Learning Whole-Body Mobile Manipulation from Human Demonstrations

Xiaomeng Xu, Jisang Park, Han Zhang, Eric Cousineau, Aditya Bhat, Jose Barreiros, Dian Wang, Jeannette Bohg, Shuran Song

Robotics: Science and Systems (RSS 2026)

IROS 2026 Bimanual Robot Learning Workshop (Best Paper)

IROS 2026 ScaleInfra Workshop (Best Paper)

Webpage • Paper • Video • Code

ForeSight: Autoregressive Plan Monitoring for Efficient Long-Horizon Execution in Changing Environments

Jisang Park, Gyungjin Eo, Jeongmin Lee, Jun Park, Yeseung Kim, Daehyung Park

Under review

Video

Compositional phoneme approximation preview

Compositional Phoneme Approximation for L1-Grounded L2 Pronunciation Training

Jisang Park*, Minu Kim*, DaYoung Hong, Jongha Lee

IJCNLP-AACL 2025

Webpage • Paper • Demo

Survey on large language models with intelligent robots

A Survey on Integration of Large Language Models with Intelligent Robots

Yeseung Kim, Dohyun Kim, Jieun Choi, Jisang Park, Nayoung Oh, Daehyung Park

Intelligent Service Robotics, 2024

Paper

Open-domain dialogue empathy dataset preview

Feels like I've Known You Forever: Empathy and Self-Awareness in Human Open-Domain Dialogs

Yoon Kyung Lee, Won Ik Cho, Seoyeon Bae, Hyunwoo Choi, Jisang Park, Nam Soo Kim, Sowon Hahn

Proceedings of the 44th Annual Conference of the Cognitive Science Society, 2022

Paper • Dataset

* Equal contributions.

Projects

Reactive Mobile Manipulation Framework

Skills: ROS2, Behavior Trees, YOLO, SAM, IK, Dynamic & Semantic 3D Scene Graphs

Engineered a real-time ROS2 framework for reactive mobile manipulation by parallelizing YOLO/SAM-based 3D scene graph construction and IK-based control via multi-threaded Behavior Trees.

Reactive Task Planning Benchmark

Skills: Simulation Benchmarking, LLM-based Task Planning

Developed a framework-agnostic benchmark setting for evaluating diverse LLM/VLM-based task-planning frameworks across 100 interruption scenarios in AI2-THOR.

Adaptive Mobile Manipulation Framework

Skills: ROS2, Behavior Trees, MoveIt, Open3D, Force-Torque Sensing, RGBD Sensing

Developed an adaptive manipulation framework combining force-torque-sensor-based collision recovery, 3D pose-driven action adaptation, and MoveIt/Open3D manipulability analysis in dynamic environments.

Voice-Based Robot Navigation Framework

Skills: ROS2, RViz, Qt, NVIDIA Riva ASR, Natural-Language Grounding, 2D LiDAR

Developed a voice-based robot navigation framework through a Qt-based RViz plugin integrating NVIDIA Riva ASR, natural-language goal grounding on a 2D LiDAR map, and ROS2 navigation stacks.

Service

Reviewer

ICRA 2027
CoRL 2026
CoRL 2026 Workshop on Pretrain to Adapt: What Makes a Pretrained Policy Adaptable?
CoRL 2026 Workshop on Robot Learning at Deployment (Learn@Deploy)
ICRA 2026 Workshop on Reinforcement Learning in the Era of Imitation Learning (RL4IL)
CVPR 2026 Workshop on Foundation Models Meet Embodied Agents (FMEA)
CoRL 2025

Teaching

Digital Computer Concept and Practice, Undergraduate Course Assistant, Fall 2021 - Spring 2022, Seoul National University
Core Computing: Thinking with Computers, Undergraduate Tutor, Fall 2021, Seoul National University
Basic Computing: First Adventures in Computing, Undergraduate Tutor, Fall 2021, Seoul National University

Education

	Stanford University M.S. in Computer Science Sep 2025 - Jun 2027 (Expected) Advisors: Jeannette Bohg and Shuran Song
	Seoul National University B.S. in Computer Science & Engineering, B.B.A. in Business Administration Mar 2017 - Aug 2022 Grade: GPA 3.90/4.00 (Summa Cum Laude)