Jaedong Hwang
PhD Student
MIT
: jdhwangmit.edu
About
I am a PhD student at MIT EECS advised by Ila Fiete. Prior to MIT, I received M.S. in ECE and B.S. in CSE from Seoul National University where I had a wonderful experience with Bohyung Han and Byoung-Tak Zhang. From June 2020 to March 2021, I did an internship at Adobe Research under the guidance of Joon-Young Lee and Seoung Wug Oh.
My research focuses on reducing the need for extensive fine-grained data collection to train artificial intelligence (AI) models and bridging the gap between neuroscience and AI, particularly in learning from imperfect data, such as noisy, weakly labeled, or entirely unsupervised data. I aim to develop more robust and realistic computer vision models and advance the field of embodied intelligence. While artificial neural networks were originally inspired by neuroscience, many current models have diverged from their biological origins in pursuit of performance, often overlooking key insights from how the brain learns. I am reseach on boosting both neuroscience and machine learning research to reconnect them each other again and make more efficient AI system. My work addresses these challenges through three main research directions:
- Learning from imperfect supervision: I develop methods to efficiently utilize imperfectly labeled and realistic data.
- Building Efficient AI via Neuroscience: Drawing inspiration from efficiency of the human cognition and brain, I develop AI models that mimic human-like learning processes, aiming to significantly expand AI capabilities.
- Boosting Neuroscience Research via Machine Learning: Recognizing the extensive time and resources required for neuroscience experiments, my research aims to provide tools and models that offer deeper insights into neural data, helping to interpret and understand brain function more effectively.
Please feel free to drop me an email if you have any questions or want to chat with me.
I wrote personal notes about how I applied for graduate school written in Korean (updated in Spring 2024).
News
- [07/2024] One paper is accepted to TMLR 2024 with Featured Certification (4% among accepted papers).
- [05/2024] One paper is accepted to ICML 2024.
- [04/2024] One paper is accepted to IJCAI 2024 as a long talk (16% among accepted papers).
- [05/2023] Two papers are accepted to CCN 2023.
- [04/2023] One paper is accepted to ICML 2023.
- [10/2022] One paper is accepted to WACV 2023.
- [04/2022] I am selected as a Highlighted Reviewer (top 9%) in ICLR 2022!
- [09/2021] I am selected as an Outstanding Reviewer (top 5%) in ICCV 2021!
- [09/2021] I joined Fiete Lab @ MIT as a PhD Student advised by Ila Fiete.
- [08/2021] I have been awarded Distinguished Dissertation Award from SNU ECE.
- [05/2021] I am selected as an Outstanding Reviewer in CVPR 2021!
- [03/2021] One paper is accepted to CVPR 2021.
- [11/2020] One paper is accepted to WACV 2021.
- [09/2020] I am selected as a candidate for Doctoral Study Abroad Program Fellowship (2021-2026).
- [08/2020] I am selected as a candidate for The Government Scholarship for Overseas Study (2021-2023).
- [06/2020] I joined Adobe Research @ Remote (due to COVID-19) as a Deep Learning Research Intern mentored by Joon-Young Lee, Seoung Wug Oh.
- [09/2019] I joined Computer Vision Lab @ Seoul National University as a Master's student advised by Professor Bohyung Han.
- [10/2018] One paper is accepted to SPIE Medical Imaging (@San Diego, Feb 2019).
- [09/2018] I joined Computer Vision Lab @ Seoul National University as a Research Intern advised by Professor Bohyung Han. more
Education
Massachusetts Institute of Technology
Seoul National University
(Distinguished Dissertation Award)
Seoul National University
(Summa Cum Laude)
(Apr 2015 - Jan 2017: Military Service)
Publications
Show:
All /
Selected
Topics:
All /
Artificial Intelligence /
Neuroscience
|
Breaking Neural Network Scaling Laws with Modularity |
|
Grid Cell-Inspired Fragmentation and Recall for
Efficient
Map Building |
|
A Multi-Region Brain Model to Shed Light on the Role of
Hippocampus in Spatially Embedded Decision Tasks |
|
Towards Exact Computation of Inductive Bias
|
|
|
Neuro-Inspired Fragmentation and Recall to Overcome
Catastrophic Forgetting in Curiosity |
|
Generalizable Relational Inference with Cognitive
Maps in
a Hippocampal Model and in Primates |
|
A Grid Cell-Place Cell Scaffold Allows Rapid Learning
and
Generalization at Multiple Levels on Mental Navigation Tasks
|
|
Model-Agnostic Measure of Generalization
Difficulty
|
|
Stop or Forward: Dynamic Layer Skipping for Efficient
Action Recognition |
|
Exemplar-Based Open-Set Panoptic Segmentation
Network
|
|
Weakly Supervised Instance Segmentation by Deep
Community
Learning |
|
Robust harmonic field based tooth segmentation in
real-life noisy scanned mesh |
|
Learning from Noisy Demonstration Sets via
Meta-Learned
Suitability Assessor |
|
An adaptive computational discourse system based on
data-driven learning algorithm |
Professional Experience
Adobe Research, Adobe Inc., CA (remote)
Deep Learning Research Intern, Mentor: Joon-Young Lee, Seoung Wug Oh
Computer Vision Lab, Seoul National University, Korea
Research Intern, Advisor: Bohyung Han
T-Brain, SKT, Korea
Research Intern
CLVR Lab, University of Southern California, CA
Visiting Student, Advisor: Joseph Lim
Cybercrime Investigation Unit, Seoul Metropolitan Police Agency, Korea
Investigator (Auxiliary Police) - as secondment of military service
BioIntelligence Lab, Seoul National University, Korea
Research Intern, Advisor: Byoung-Tak Zhang
Awards & Honors
-
Highlighted Reviewer in ICLR2022
-
Outstanding Reviewer in ICCV2021
-
Distinguished Dissertation Award in ECE, SNU2021
-
Outstanding Reviewer in CVPR2021
-
Best Paper of Brain-Mind-Behavior department, SNU2017
-
Seoul Metropolitan Police Agency Award Certificate2016
-
ISIS 2015 Best Session Paper Award2015
-
Jongha Fellowship2014
Scholarships
Doctoral Study Abroad Program Fellowship
Government Scholarship for Overseas Study
(declined)
Seoam Scholarship (Merit-based)
Services
Reviewer
2020: ECCV
2021: CVPR, ICCV, WACV
2022: CVPR, ICLR, ICML, NeurIPS, WACV
2023: ICLR, ICML, NeurIPS, ICCV, WACV, CCN, NeurIPSW-AMHN
2024: ICML
2025: ICLR
- Journal
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
Transaction on Machine Learning Research (TMLR)
Volunteer
- GAAP (The Graduate Application Assistance Program) in MIT EECS 2021-2024
Teaching Assistant
- Spring 2020: 035.001 Digital Computer Concept and Practice (Instructor: Bohyung Han)