Minyoung Hwang

I'm a research intern at CMU, advised by Yonatan Bisk. Previously, I worked at the PRIOR team of the Allen Institute for AI (AI2). I received my M.S. and B.S. in Electrical and Computer Engineering at Seoul National University (SNU).

Research Keywords: robotics, human-robot interaction, reinforcement learning, computer vision

Timeline

Previously, I was a research intern at the PRIOR team of the Allen Institute for AI (AI2), supervised by Kiana Ehsani and closely worked with Ani Kembhavi and Luca Weihs. I received my M.S. in the Robot Learning Laboratory (RLLAB, advised by Songhwai Oh), Department of Electrical and Computer Engineering at Seoul National University (SNU), Korea. I was co-advised by Yoonseon Oh and Kyungjae Lee during my M.S. program. I received a B.S. degree (with highest honors) in Electrical and Computer Engineering from SNU in 2021. When I was an undergraduate, I fell into robotics and developed an omnidirectional motion-controlled robot cleaner with a wonderful team in SNU. I also participated the Silicon Valley Innovation - Startup Training Program in San Jose State University and was mentored by Koohyoung Lee (CTO of NeuroSky). Before my B.S., I majored Mathematics in Daejeon Science High School for the Gifted.

Skills: I received numerous awards for talent in Mathematics. I was honored to be fully supported by the Presidential Science Scholarship in Mathematics during my undergraduate degree. For details, go to Honors and Awards. I TAed 4+ Math/ECE lectures and I love to share my knowledge and insights with others.

I am applying for 2024 Fall PhD programs! I received the Global Korea Scholarship which will fully support the first 2 years of my PhD program.

Email  /  CV  /  Google Scholar  /  LinkedIn  /  Twitter  /  Github

profile photo


News

Research

I'm interested in robotics, human-robot interaction, computer vision, and reinforcement learning. Much of my research is about applying mathematical concepts/theories to robot learning. Representative papers are highlighted.

Promptable Behaviors: Personalizing Multi-Objective Rewards from Human Preferences
Minyoung Hwang, Luca Weihs, Chanwoo Park, Kimin Lee, Ani Kembhavi, Kiana Ehsani
CVPR (Computer Vision and Pattern Recognition), 2024
project page | paper

We propose a novel framework that facilitates efficient personalization of robotic agents to diverse human preferences in complex environments.

Sequential Preference Ranking for Efficient Reinforcement Learning from Human Feedback
Minyoung Hwang, Gunmin Lee, Hogun Kee, Chan Woo Kim, Kyungjae Lee, Songhwai Oh
NeurIPS (Neural Information Processing Systems), 2023
project page | paper

We propose a novel RLHF framework called SeqRank, that uses sequential preference ranking to enhance the feedback efficiency.

Meta-Explore: Exploratory Hierarchical Vision-and-Language Navigation Using Scene Object Spectrum Grounding
Minyoung Hwang, Jaeyeon Jeong, Minsoo Kim, Yoonseon Oh, Songhwai Oh
CVPR (Computer Vision and Pattern Recognition), 2023
project page | video | paper | poster

We propose and end-to-end learnable hierarchical navigation policy for vision-and-language navigation (VLN) that finds an unvisited and near-optimal local goal by recognizing semantically meaningful clues.

Improving Image-Goal Navigation with Visual Language Grounding via Image Captioning
Minyoung Hwang, Songhwai Oh
CICS (Conference on Information and Control Systems), 2022
paper

We propose a visual navigation method that the agent augments language observations and use the multi-modal observations for hierarchical exploration.

Geometric Understanding of Reward Function in Multi-Agent Visual Exploration
Minyoung Hwang, Obin Kwon, Songhwai Oh
ICCAS (International Conference on Control, Automation and Systems), 2021
video | paper

We present a new reward shaping method for multi-agent visual exploration with geometric understanding of the environment.

Video Inference for Human Motion with Texture Generation
Minyoung Hwang, Songhwai Oh
Bachelor's Thesis, Electrical and Computer Engineering Department, Seoul National University, Korea, Oct 2020
video | paper | poster

We propose a novel method to reconstruct 3D multi-view video with texture generation from a 2D human motion video.


Challenges

I hosted and participated in some challenges.

RC Car Racing Challenge
Robot Learning Laboratory, SNU
Head TA
TA demo | project page | videos and photos

We hosted RC car racing challenges in 2022 Spring & 2021 Fall ECE 430.457 'Introduction to Intelligent Systems'.

Startup Team UP-CARE (Use your Phone Camera for Health and Environment)
Silicon Valley Innovation and Startup Program, Grand Prize (1st Prize), 2020

We present a startup item for fall detection for elderly using phone camera based on human pose estimation.

Scrupulous Robot Cleaner with Mecanum Wheels and Pointed-Shaped Inlet
International Capstone Design Fair, 1st Prize, 2019
SNU College of Engineering Creative Design Fair, 2nd Prize, 2019

We present an omnidirectional robot cleaner with autonomous & hand-motion controlled modes. I leaded development of control algorithm considering robot dynamics.


Patent
Envelope with built-in sieve (KR20140003720U)
Minyoung Hwang

We invented an envelope with built-in seive to sift powder automatically in the process of taking it out of the bag.


Book
Wanna be Engineer
Minyoung Hwang and 33 other STEM members
MegaStudy Books, 2022
blog post

The first self help book written by SNU engineering students, including the stories of studying in middle and high school years, the reason for choosing engineering majors, and the career path after graduation.


Honors and Awards
University Students Contest of Mathematics, Gold Medal, Korean Mathematical Society, Nov 2018
Training Lineup for IMO (International Mathematical Olympiad), Korean Mathematical Society, 2016 Spring
KMO (Korean Math Olympiad) Winter School, 2014, 2015
The Presidential Science Scholarship (Field: Mathematics), Ministry of Science and ICT, 2017-2020
Talent Award of Korea (Field: Mathematics), Ministry of Education of Korea, Nov 2015
Global Korea Scholarship, Ministry of Education of Korea, 2024-2026

Teaching

I TAed the following courses in the department of Electrical and Computer Engineering and the department of Mathematics.

Introduction to Intelligent Systems, TA (English Lecture)
SNU, 2021 Fall and 2022 Spring

Managed RC car racing project and teach students how to use ROS and Gazebo. Head TA for 2022 Spring Lecture.

Signals and Systems, Major Tutor
SNU, 2021 Spring

Tutoring for Seoul National University ECE major subject.

Introduction to Circuit Theory and Laboratory, Undergraduate TA
SNU, 2019 Spring

Supported and helped students do electric circuit experiments.

Basic Calculus Tutor
SNU, 2018 - 2020

Taught Basic Calculus 1, 2 and Basic Calculus for Biological Science.


Misc
Reviewer, T-RO 2022
Member of IEEE Robotics & Automation Society (2022 - Current)
10th President, SNU Tomorrow’s Edge Membership (STEM, Honor Society in Engineering College), Seoul National University (2019 - Current)
Representative for NorthEast Asia SRT (Student Round Table, 2019)


template adapted from this awesome website
Last updated: Sep 2023