PC: Kiroong Choe

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

  • [01/2025] One paper is accepted to ICLR 2025.
  • [01/2025] I gave a talk at Voxel51 Boston AI, ML, and CV Meetup on Feb. 28th.
  • [12/2024] Our TMLR paper is invited to present at ICLR 2025.
  • [12/2024] I have been awarded the Travel Award from NeuroAI Workshop @ NeurIPS 2024 for the best student-author paper.
  • [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 the 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
Ph.D. Student in Electrical Engineering and Computer Science (Advisor: Ila Fiete)
Sep 2021 - Present
Seoul National University
M.S. in Electrical and Computer Engineering (Advisor: Bohyung Han)
(Distinguished Dissertation Award)
Sep 2019 - Aug 2021
Seoul National University
B.S. in Computer Science and Engineering (minor: Brain-Mind-Behavior)
(Summa Cum Laude)
Mar 2013 - Aug 2019
(Apr 2015 - Jan 2017: Military Service)

Publications

Show: All / Selected
Topics: All / Artificial Intelligence / Neuroscience

ImageNet-RIB Benchmark: Large Pre-Training Datasets Don't Guarantee Robustness after Fine-Tuning
 Jaedong Hwang, Brian Cheung, Zhang-Wei Hong, Akhilan Boopathy, Pulkit Agrawal, Ila Fiete.
 NeurIPS Workshop - Fine-Tuning in Modern Machine Learning: Principles and Scalability. 2024.
 [paper], [arXiv], [project page], [slide], [poster]

Breaking Neural Network Scaling Laws with Modularity
 Akhilan Boopathy, Sunshine Jiang, William Yue, Jaedong Hwang, Abhiram Iyer, Ila Fiete.
 ICLR. 2025.
  [paper], [poster], [blog]

Grid Cell-Inspired Fragmentation and Recall for Efficient Map Building
 Jaedong Hwang, Zhang-Wei Hong, Eric Chen, Akhilan Boopathy, Pulkit Agrawal, Ila Fiete.
 TMLR. 2024. (Featured Certification; 4% among accepted papers)
  [paper], [project page], [code], [slide], [poster], [video]

A Multi-Region Brain Model to Shed Light on the Role of Hippocampus in Spatially Embedded Decision Tasks
 Yi Xie, Jaedong Hwang, Carlos Broady, David Tank, Ila Fiete.
 CCN. 2024.
  [paper]

Towards Exact Computation of Inductive Bias
  Akhilan Boopathy, William Yue, Jaedong Hwang, Abhiram Iyer, Ila Fiete.
 IJCAI. 2024. (long; 16% among accepted papers)
 [paper], [code], [poster]

Rapid Learning Without Catastrophic Forgetting in the Morris Water Maze
 Raymond L Wang, Jaedong Hwang, Akhilan Boopathy, Ila Fiete.
 CCN. 2023. [paper]
 NeurIPS Workshop - Associative Memory & Hopfield Networks. 2023. (oral) [paper]
 ICML. 2024. [paper], [code], [poster]

Neuro-Inspired Fragmentation and Recall to Overcome Catastrophic Forgetting in Curiosity
 Jaedong Hwang, Zhang-Wei Hong, Eric Chen, Akhilan Boopathy, Pulkit Agrawal, Ila Fiete.
 NeurIPS Workshop - Intrinsically Motivated Open-ended Learning. 2023.
  [paper], [code], [poster]

Generalizable Relational Inference with Cognitive Maps in a Hippocampal Model and in Primates
 Jaedong Hwang*, Sujaya Neupane*, Mehrdad Jazayeri†, Ila Fiete†.
 NeurIPS Workshop - Associative Memory & Hopfield Networks. 2023.
 SfN Nanosymposium - Spatial Representations Across Species. 2023. (oral)
  [paper], [poster]

A Grid Cell-Place Cell Scaffold Allows Rapid Learning and Generalization at Multiple Levels on Mental Navigation Tasks
 Jaedong Hwang*, Sujaya Neupane*, Mehrdad Jazayeri†, Ila Fiete†.
 CCN. 2023.
  [paper]

Model-Agnostic Measure of Generalization Difficulty
 Akhilan Boopathy, Kevin Liu, Jaedong Hwang, Shu Ge , Asaad Mohammedsaleh, Ila Fiete.
 ICML. 2023.
  [paper], [code], [poster], [slide], [video]

Stop or Forward: Dynamic Layer Skipping for Efficient Action Recognition
 Jonghyeon Seon, Jaedong Hwang, Jonghwan Mun, Bohyung Han.
 WACV. 2023.
  [paper], [code], [poster], [video]

Exemplar-Based Open-Set Panoptic Segmentation Network
 Jaedong Hwang, Seoung Wug Oh, Joon-Young Lee, Bohyung Han.
 CVPR. 2021.
 [paper], [project page], [code], [poster], [slide], [video]

Weakly Supervised Instance Segmentation by Deep Community Learning
 Jaedong Hwang*, Seohyun Kim*, Jeany Son, Bohyung Han.
 WACV. 2021.
 [paper], [project page], [video]

Robust harmonic field based tooth segmentation in real-life noisy scanned mesh
 Jaedong Hwang*, Sanghyeok Park*, Seokjin Lee*, Yeong-Gil Shin.
 SPIE 10949, Medical Imaging 2019: Image Processing. 2019.
 [paper], [poster]

Learning from Noisy Demonstration Sets via Meta-Learned Suitability Assessor
 Te-Lin Wu, Jaedong Hwang, Jingyun Yang, Shaofan Lai, Carl Vondrick, Joseph Lim.
 OpenReview. 2018.
 [paper], [project page], [video]

An adaptive computational discourse system based on data-driven learning algorithm
 Seungwon Lee*, Jaedong Hwang*, Eunsol Kim, Byoung-Tak Zhang.
 International Symposium on advanced Intelligent Systems (ISIS) (Vol. 201). 2015.
 Best Session Paper Awards
 [paper]

(*: equally contributed)

Professional Experience

Adobe Research, Adobe Inc., CA (remote)
Deep Learning Research Intern, Mentor: Joon-Young Lee, Seoung Wug Oh
Jun 2020 - Mar 2021
Computer Vision Lab, Seoul National University, Korea
Research Intern, Advisor: Bohyung Han
Sep 2018 - Aug 2019
T-Brain, SKT, Korea
Research Intern
Jun 2018 - Aug 2018
CLVR Lab, University of Southern California, CA
Visiting Student, Advisor: Joseph Lim
Mar 2018 - May 2018
Cybercrime Investigation Unit, Seoul Metropolitan Police Agency, Korea
Investigator (Auxiliary Police) - as secondment of military service
Korean Media: KBS, SBS, YTN
Aug 2015 - Jan 2017
BioIntelligence Lab, Seoul National University, Korea
Research Intern, Advisor: Byoung-Tak Zhang
Jul 2014 - Apr 2015

Awards & Honors

  • Travel Award, NeuroAI Workshop @ NeurIPS
    2024
  • Highlighted Reviewer in ICLR
    2022
  • Outstanding Reviewer in ICCV
    2021
  • Distinguished Dissertation Award in ECE, SNU
    2021
  • Outstanding Reviewer in CVPR
    2021
  • Best Paper of Brain-Mind-Behavior department, SNU
    2017
  • Seoul Metropolitan Police Agency Award Certificate
    2016
  • ISIS 2015 Best Session Paper Award
    2015
  • Jongha Fellowship
    2014

Scholarships

Doctoral Study Abroad Program Fellowship
A full scholarship with stipends granted by Korea Foundation for Advanced Studies (KFAS).
Sep 2021 - Aug 2026
Government Scholarship for Overseas Study
A scholarship granted by The Government of South Korea of $40,000 for each academic year.
Sep 2021 - Aug 2023
(declined)
Seoam Scholarship (Merit-based)
A full scholarship with stipends granted by Seoam Yoon Se Young Foundation for undergraduate studies.
Sep 2013 - Aug 2019

Services

Reviewer
- Conference
  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, ICML
- Journal
  IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
  Transaction on Machine Learning Research (TMLR)
Volunteer
- ICLR 2020
- GAAP (The Graduate Application Assistance Program) in MIT EECS 2021-2024
Teaching Assistant
- Spring 2024: 6.8200 Computational Sensorimotor Learning (Instructor: Pulkit Agrawal)
- Spring 2020: 035.001 Digital Computer Concept and Practice (Instructor: Bohyung Han)

Other Experience

Seoul National University Philharmonic Orchestra
Server Administrator
Aug 2016 - Aug 2021
Chief of department of Data Management
Oct 2014 - Mar 2015
2nd Violinist
Mar 2013 - Aug 2019
National Museum of Modern and Contemporary Art, Seoul, Korea
Volunteer
Mar 2017 - Oct 2017
Guahm Middle School, Seoul, Korea
Mentor
Sep 2013 - Feb 2015