@Terry Pettus Park, Seattle. (Photo Credit: Jessica O.)
đź“ŤTable of Contentsđź“Ť
I am a CS PhD student at Georgia Tech advised by Prof. Sehoon Ha and supported by the NSF Graduate Research Fellowship (GRFP).
My research interests are in artificial intelligence and control techniques that enable robots to make our lives better. Specifically, my research agenda is to develop a robotic guide dog 🦮 for visually impaired people that could remove barriers in one’s life, assisting one’s everyday activities.
đź”— **[LinkedIn] [Google Scholar]**
🏢 Office: 3222A Klaus Advanced Computing Building 📨 E-mail: [email protected]
IRIM Robotics Open House @GT, National Robotics Week, 2023
Poster @HRI2023
Modeling social interaction dynamics using temporal graph networks [arXiv]
J. T. Kim, Archit Naik, Isuru Jayarathne, Sehoon Ha, Jouh Yeong Chew
EEE International Conference on Robot & Human Interactive Communication (RO-MAN’24), 2024, Pasadena, CA.
Transforming a Quadruped into a Guide Robot for the Visually Impaired: Formalizing Wayfinding, Interaction Modeling, and Safety Mechanism [arXiv] [website]
J. T. Kim, Wenaho Yu, Yash Kothari, Jie Tan, Greg Turk, Sehoon Ha
Conference on Robot Learning (CoRL’23), 2023, Atlanta, GA.
How to Train Your Guide Dog: Wayfinding and Safe Navigation with Human-Robot Modeling [link] [video]
J. T. Kim, Wenaho Yu, Jie Tan, Greg Turk, Sehoon Ha
International Conference on Human-Robot Interaction (HRI’23) Late Breaking Report, 2023, Stockholm, Sweden.
Learning Robot Structure and Motion Embeddings using Graph Neural Networks [arXiv]
J. T. Kim, Jeongeun Park, Sungjoon Choi, Sehoon Ha
ICML 2022 Workshop on Machine Learning for Computational Design (ICML'22-ML4CompDesign), 2022, Baltimore, MD.
RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening [arXiv]
Sungha Choi, Sanghun Jung, Huiwon Yun, J. T. Kim, Seungryong Kim, Jaegul Choo
IEEE Conference on Computer Vision and Pattern Recognition (CVPR'21), 2021, Virtual (Oral presentation, 4.7% acceptance rate).
Predicting Energetics Materials’ Crystalline Density from Chemical Structure by Machine Learning [link]
Phan Nguyen, Donald Loveland, J. T. Kim, Piyush Karande, Anna M. Hiszpanski, T. Yong-Jin Han
Journal of Chemical Information and Modeling 61.5 (2021): 2147-2158.
Observation Space Matters: Benchmark and Optimization Algorithm [arXiv]
J. T. Kim, Sehoon Ha
IEEE International Conference on Robotics and Automation (ICRA'21), 2021, Xian, China.
Distilling Wikipedia Mathematical Knowledge into Neural Network Models [arXiv] [poster]
J. T. Kim, Mikel Landajuela Larma, Brenden K. Petersen
1st Mathematical Reasoning in General Artificial Intelligence Workshop at ICLR 2021 (ICLR'21-MATH-AI), 2021.
Deep symbolic regression: Recovering mathematical expressions from data via risk-seeking policy gradients [arXiv] [techexplore]
Brenden K. Petersen, Mikel Landajuela Larma, T. Nathan Mundhenk, Claudio P. Santiago, Soo K. Kim, J. T. Kim
International Conference on Learning Representations (ICLR'21), 2021, Virtual (Oral presentation).
An Interactive Visualization Platform for Deep Symbolic Regression [pdf]
J. T. Kim, Sookyung Kim, Brenden K. Petersen
International Joint Conference on Artificial Intelligence (IJCAI'20), Demonstrations Track, 2020, Yokohama, Japan (26.7% acceptance rate).
Cars Can’t Fly Up in the Sky: Improving Urban-Scene Segmentation via Height-driven Attention Networks [pdf] [supp] [video]
Sungha Choi, J. T. Kim, Jaegul Choo
IEEE Conference on Computer Vision and Pattern Recognition (CVPR'20), 2020, Seattle, WA (22.1% acceptance rate).
Optimizing 3D structure of H2O molecule using DDPG [pdf] [poster]
Soo Kyung Kim, Peggy Li, J. T. Kim, Piyush Karande, T. Yong Han
ICML 2019 Workshop on Reinforcement Learning for Real Life (ICML'19-RL4RealLife), 2019, Long Beach, CA.
RetainVis: Visual analytics with interpretable and interactive recurrent neural networks on electronic medical records [pdf] [video]
Bum Chul Kwon, Min-Je Choi, J. T. Kim, Edward Choi, Young Bin Kim, Soonwook Kwon, Jimeng Sun, Jaegul Choo
IEEE Trans. on Visualization and Computer Graphics (TVCG), 2019 (Proc. IEEE VIS'18) (25.6% acceptance rate).
