Sungjae Park

Hi! I'm an incoming Ph.D. student in Computer Science at Stanford University. Previously, I earned M.S. in Robotics from Carnegie Mellon University, where I was advised by Prof. Shubham Tulsiani.

I received my B.S. (summa cum laude) in Mechanical Engineering and Mathematics from Seoul National University, where I worked with Prof. Hanbyul Joo in the Visual Computing Lab.

Email / CV / Scholar / Twitter / Github

Research

My research goal is to enable robots to perform complex manipulation tasks: those involving long-horizon planning, contact-rich interactions, and high-precision dexterous control.

* : Equal Contribution, † : Equal Advising

	πR²: Reactive Real-time Flow Policies Sungjae Park, Shubham Tulsiani. Preprint, 2026 Paper / Website / Code
	Dex4D: Task-Agnostic Point Track Policy for Sim-to-Real Dexterous Manipulation Yuxuan Kuang, Sungjae Park, Katerina Fragkiadaki^†, Shubham Tulsiani^†. Preprint, 2026 Paper / Website / Code
	Temporal Score Rescaling for Temperature Sampling in Diffusion and Flow Models Yanbo Xu^, Yu Wu^, Sungjae Park, Zhizhuo Zhou, Shubham Tulsiani. ICML, 2026 Paper / Website / Code
	DemoDiffusion: One-Shot Human Imitation using pre-trained Diffusion Policy Sungjae Park, Homanga Bharadhwaj, Shubham Tulsiani. ICRA, 2026 Paper / Website / Code
	Learning to Transfer Human Hand Skills for Robot Manipulations Sungjae Park, Seungho Lee, Mingi Choi, Jiye Lee, Jeonghwan Kim, Jisoo Kim, Hanbyul Joo. CoRL X-Embodiment Workshop, 2024* Paper / Website
	DROID: A Large-Scale In-the-Wild Robot Manipulation Dataset DROID Dataset Team RSS, 2024 Paper / Website / Code
	Open X-Embodiment: Robotic Learning Datasets and RT-X Models Open X-Embodiment Collaboration ICRA, 2024 (Best Conference Paper Award) Paper / Website

Teaching

Introduction to Robotics
Student Instructor, Spring 2022

College Physics 1, 2
Undergraduate Tutoring, Spring 2018, Fall 2018, Spring 2021, Fall 2021

Linear Algebra
Undergraduate Tutoring, Spring 2021

Service

Reviewer for ICML, NeurIPS, ICLR, ICRA, RA-L, CoRL, CVPR.

Website template from Jon Barron.