Subin Kim
Ph.D. student
KAIST AI
subin-kim [AT] kaist.ac.kr
About
I am a 2nd year Ph.D. student at Algorithmic Intelligence Laboratory (ALIN-LAB), advised by Prof. Jinwoo Shin at Korea Advanced Institute of Science and Technology (KAIST). I received my B.S. in Electrical Engineering at KAIST in 2022.
The long-term goal of my research is to enhance the practicality of computer vision systems so that they can be widely used in real-world scenarios. To this end, I focus on (i) how to design architecture efficiently in terms of computation and memory by reflecting the character of each data signal and (ii) how to apply computer vision systems newly and variously in real-world applications. Currently, I am mainly interested in coordinate-based neural representations and also broadly interested in generative models.
Publications
Collaborative Score Distillation for Consistent Visual Editing
Subin Kim*, Kyungmin Lee*, June Suk Choi, Jongheon Jeong, Kihyuk Sohn, Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2023
Learning Large-scale Neural Fields via Context Pruned Meta-Learning
Jihoon Tack, Subin Kim, Sihyun Yu, Jaeho Lee, Jinwoo Shin, Jonathan Richard Schwarz
Conference on Neural Information Processing Systems (NeurIPS), 2023
Video Probabilistic Diffusion Models in Projected Latent Space
Sihyun Yu, Kihyuk Sohn, Subin Kim, Jinwoo Shin
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
Winners, Qualcomm Innovation Fellowship Korea 2023
Scalable Neural Video Representations with Learnable Positional Features
Subin Kim*, Sihyun Yu*, Jaeho Lee, Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2022
Winners, Qualcomm Innovation Fellowship Korea 2023
Collaborative Score Distillation for Consistent Visual Editing
Subin Kim*, Kyungmin Lee*, June Suk Choi, Jongheon Jeong, Kihyuk Sohn, Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2023
Learning Large-scale Neural Fields via Context Pruned Meta-Learning
Jihoon Tack, Subin Kim, Sihyun Yu, Jaeho Lee, Jinwoo Shin, Jonathan Richard Schwarz
Conference on Neural Information Processing Systems (NeurIPS), 2023
Video Probabilistic Diffusion Models in Projected Latent Space
Sihyun Yu, Kihyuk Sohn, Subin Kim, Jinwoo Shin
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
Scalable Neural Video Representations with Learnable Positional Features
Subin Kim*, Sihyun Yu*, Jaeho Lee, Jinwoo Shin
Conference on Neural Information Processing Systems (NeurIPS), 2022
Education
Korea Advanced Institute of Science and Technology (KAIST)Mar. 2022 - Present
Ph.D. Student in Artificial Intelligence
Korea Advanced Institute of Science and Technology (KAIST)Mar. 2017 - Feb. 2022
B.S. in Electrical Engineering
Experience
AI Research InternAug. 2021 - Feb. 2022
Upstage AIWinter InternshipJan. 2020 - Feb. 2020
Samsung Electro-MechanicsHonors & Awards
Winner, Qualcomm Innovation Fellowship Korea 2023
2nd Place, SAMSUNG AI Forum 2023
Recipient, Google Conference Scholarships (APAC) NeurIPS 2023
Recipient, NeurIPS 2023 Travel Award
Recipient, CVPR 2023 Travel Award
Demo, CVPR 2023
Art Gallery, CVPR 2023
Recipient, NeurIPS 2022 Travel Award
1st place, Creative Space G A.I & IoT Hackathon
Academic Services
Conference Reviewer, ICML 2023, NeurIPS 2023, ICLR 2024
Workshop Reviewer, SPIGM@ICML'23