Hello, I'm a/an

I'm Yubin, a final year PhD student at MIT Media Lab and a student researcher at Google Research .
My research objective and interest lies in Health AI, Agents, and AI Safety.
Specifically, I'm interested in bridging the gap between the Agent/Robot and Healthcare, delivering Personalized and Long-term interventions.

Updates

2026

Jan Gave an invited talk on "Agent Scaling Law" at Adobe Research. I enjoyed the insightful discussions that followed, especially on how we can approach evaluation for agent systems and the architecture designs 🎙️.
Jan Our paper on "Towards a Science of Scaling Agent Systems" is released as a preprint paper

2025

Dec Gave an invited talk on "Healthcare Agents: Language Model Agents in Health Prediction and Decision-Making" to MBZUAI 🎙️.
Sep Our paper on "Tiered Agentic Oversight: A Hierarchical Multi-Agent System for AI Safety in Healthcare" is selected as a spotlight poster at AI Cures 2025.
Aug Our paper on "The Anatomy of a Personal Health Agent" is released as a preprint paper
Aug Our paper on "BehaviorSFT: Behavioral Token Conditioning for Clinical Agents Across the Proactivity Spectrum" is accepted as a findings paper at EMNLP 2025.
May Our paper on "VocalAgent: Large Language Models for Vocal Health Diagnostics with Safety-Aware Evaluation" is accepted as an oral paper at Interspeech 2025.
May I've started a PhD internship at Google Research on Multi-Agent Systems for Biomarker Discovery at Scale
Mar Our paper on "Social robots as conversational catalysts: Enhancing long-term human-human interaction at home" is published as a cover paper at Science Robotics.

2024

Sep Our paper on "MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making" is accepted as an oral paper at NeurIPS 2024.
Jul Our paper on "EmpathicStories++: A Multi-modal Dataset for Empathy towards Personal Experiences" is accepted as a Findings at ACL 2024.
May I've started a research internship at Honda Research Institute on LLMs in Displaying Group Dynamics
Apr Our paper on "Health-LLM: Large Language Models for Health Prediction via Wearable Sensor Data" is accepted at CHIL 2024.
Mar Our paper on "Diffusion-EDFs: Bi-equivariant Denoising Generative Modeling on SE(3) for Visual Robotic Manipulation" is accepted at CVPR 2024.

2023

Sep I started MAS graduate program at MIT Media Lab
Jul Our paper on "HIINT: Historical, Intra-and Inter-personal Dynamics Modeling with Cross-person Memory Transformer" is accepted at ICMI 2023
Apr Our paper on "Multipar-T: Multiparty-Transformer for Capturing Contingent Behaviors in Group Conversations" is accepted at IJCAI 2023
Jan Our paper on "Joint Engagement Classification using Video Augmentation Techniques for Multi-person Human-robot Interaction" is accepted at AAMAS 2023

2022

Jul I started my visting scholar program at MIT

Projects

My experience has been focused on implementing personalized technology with foundation models for human-agent interactions in an intuitive and reciprocal manner. Specifically, I am interested in developing personal agents that can maintain long-term interactions with humans in the wild and perform continual learning.

Tiered Agentic Oversight: A Hierarchical Multi-Agent System for AI Safety in Healthcare
Multi-tier agentic oversight with case escalation for medical AI safety

The Anatomy of a Personal Health Agent
Building blocks for personal health agents

Towards a Science of Scaling Agent Systems
When and why agent systems work at scale

InvThink: Mitigating Safety Risks Through Inverse Reasoning
Inverse reasoning for safer AI responses

Health-LLM: Large Language Models for Health Prediction via Wearable Sensor Data
LLMs as personalized health learners

MDAgents: Adaptive Collaboration Strategy for LLMs in Medical Decision Making
Mirroring real clinical decision making with LLMs

Conversational AI Agents for Elder Care
Emotional Wellness and Medication Support for Older Adults

Digital Companion Robot Design for Older Adults
Investigation of Digital Companion Robot in VR Environemnt for Older Adults

Group Joint Engagement from RoomReader Dataset
Group Joint Engagement

Development of Auto Dyadic App
Robot Co-reading Activity

Development of AI Avatar
DMLab Intern

MineRL : Training AI agents in Open World Environments
MineRL

ODMG-PF
ODMG-PF

Training Self-driving Car using DDPG Algorithm
Self-driving Car

ICRA RoboMaster AI Challenge
ICRA RoboMaster AI Challenge

Development of Indoor Serving Robot
Bear Robotics Intern

Explainable Human-Robot Interaction Learning with Video Augmentation Techniques
Joint Engagement Recognition from robot co-reading interaction videos

Journey

Document

April 19th, 1995
Borned in South Korea
Grew up in a city called Incheon which is located next to Seoul.

Sept, 2007
Lived in Toronto, Canada
Graduated from Crestwood elmentary school in Toronto.

Mar 2011 - Feb 2013
Graduated from Incheon Science High School (ISHS)
Majoring Mathematics and Physics.

Mar 2014 - Feb 2022
Graduated from Yonsei University
Majoring Computer Science and Mechanical Engineering.

Mar 2016 - Dec 2017
Military Service
Republic of Korea Marine Corps (ROKMC)

Mar 2019
Robotics Engineer Intern, Bear Robotics
Interned at Bear Robotics, Redwood City, CA

May 2019
ICRA RoboMaster AI Challenge
3rd Prize, Final Competition, Montreal

July 2020
R&D, Deep Machine Lab
Interned at Deep Machine Lab, Seoul

2022
Visiting Researcher, MIT Media Lab
Personal Robots Group, MIT Media Lab

2023 - Present
Research Assistant, MIT Media Lab
Media Arts and Sciences (MAS)

Contact

If you have any question or would like to discuss about works, please contact me via following form: