Joonwoo Kwon
AI RESEARCHER
RESEARCH INTERESTS
AN INTELLECTUAL EXPLORER
Computer Vision, Generative Models, (Multimodal) Foundation Models, and Human-AI Collaboration
I am passionate about developing machines that harmonize with human experiences and preferences.
Ultimately, I envision a future where these advancements empower individuals to effortlessly translate their unique ideas into tangible creations. By bridging the gap between human creativity and technology, I aim to make the creative process more accessible and intuitive, allowing everyone to explore and express their artistic visions with confidence.
My current research focuses on two main areas: 1) enhancing the compositionality of generative models to improve their effectiveness, and 2) applying these models to innovate practices within the advertising industry.
Recently, I've had the privilege of being advised by Prof. Jiook Cha at Seoul National University (SNU), as well as Prof. Shinjae Yoo and Prof. Yuewei Lin at Brookhaven National Laboratory (BNL).
I plan to apply for Ph.D. programs in the 2025 cycle!
News
Oct. 2024
🔥 Our work, "The Recollection of Your Most Cherished Experiences utilizing AI and Neural Signals" will be presented at the Tech to Art Platform (TAP) International Conference Prequel (ART DIFFUSION). See you soon! 😘
Oct. 2024
🔥 Our team won the GRAND prize 🏅 at the AI & Art Hackathon hosted by the AI Art Research Center in Seoul, Korea! 🎉
Oct. 2024
Sep. 2024 - Oct. 2024
Aug. 2024
Dec. 2023
Started working as an AI researcher at Planningo via AI research Partnership.
Selected to participate in AI & Art Hackathon hosted by AI Art Research Center, Seoul, Korea.
Invited for a talk on brain decoding at Seoul National University, Seoul, Korea.
Education
Seoul National University, Seoul, Korea
Master of Science in Applied Bioengineering
SungKyunKwan University, Suwon, Korea
Bachelor of Science in Electronic and Electrical Engineering
Lincoln Middle School, Pullman, WA
Completed eighth grade (2010-2011)
Experience
Planningo, Seoul, Korea
AI Researcher (AI research partnership)
Connectome Lab, SNU, Seoul, Korea
Researcher (Advisor: Prof. Jiook Cha)
U.S. NERSC NESAP, BNL, Upton, NY (Remote)
Researcher (Advisor: Prof. Shinjae Yoo, Prof. Yuewei Lin)
Research Projects
AesFA: An Aesthetic Feature-Aware Arbitrary Neural Style Transfer
AAAI 2024, First Author; Acceptance Rate: 23.75% (2342/12100)
Developed a new neural style transfer method (AesFA) that effectively utilizes frequency domain decomposition for images to better disentangle aesthetic styles from the reference image.
Macro2Micro: A Rapid and Precise Cross-modal Magnetic Resonance Imaging Synthesis using Multi-scale Structural Brain Similarity
PREPRINT; First Author
Developed a new deep learning framework, Macro2Micro for predicting the microstructure of the brain from the microstructure of the brain while achieving favorable accuracy and speed.
Details are available upon request.
Visual Attention Guidance Enables A Composable Brain-To-Image Decoding
MANUSCRIPT IN PREPARATION; First Author
Inspired by the two-stream hypothesis, we proposed a new brain-to-image decoding framework that directly guides both the placement and identity of the objects to the model, for the first time enabling a composable brain decoding.
Details are available upon request.
AesPHA: An Aesthetic Physics-Aware Neural Style Transfer
MANUSCRIPT IN PREPARATION; First Author
Developed a unique neural style transfer method that effectively captures the style information from the pre-trained fluid-simulation field, utilizing a new style encoding approach that harnesses the chaotic characteristics of the Lorenz system.
Details are available upon request.
Upcoming Project
An Image Harmonization Model for Visual Coherence in Commercial AI Photography
Planningo: Transform the landscape of advertising photography and commercial videography
Photos by @Planningo
Expected to serve as AI Researcher from Oct. 2024 with AI research partnership at Seoul AI Hub.
My goal is to develop image harmonization models for the commercial photography service Photio, by resolving the incongruity between AI-generated backgrounds and original advertising photography / commercial videography during synthesis. Specifically, we fine-tuned the synthesis process by matching the lighting conditions of AI-generated backgrounds with those present in original commercial photography. This approach aims to enhance the visual coherence of images, ultimately benefiting the commercial AI photography industry.
The Recollection of Your Most Cherished Experiences utilizing AI and Neural Signals
The Grand Prize 🏅
AI & Art Hackathon, AI Art Research Center, SNU
Proposed a multimodal AI framework for synthesizing personalized videography (video + music) utilizing generative AI and neural signals (EEG). Our work will be presented at the Tech to Art Platform (TAP) International Conference Prequel.
Demo:
Instruction: Please recall your most cherished experiences.
The detailed description of the moment (written by the subject):
" Interior view of a city bus, from the back seat. The front windshield is visible, showing only sky and sun due to the bus climbing a very steep hill. Late afternoon, around 5 PM, with the setting sun casting a deep orange light through the front windshield. Cinematic lighting, dramatic angle, urban photography, realistic style, high contrast, golden hour, lens flare, interior vehicle shot, public transportation aesthetics. "
Emotional changes in the subject while recalling the memory.
Output without affect (emotion)
Output with affect (emotion)
Clearly, the model with affect (emotion) generates more realistic and high-quality results. 🤔
Selected Projects
I have had the opportunity to work with several esteemed corporates and teams.
AI + Tech
Sept. 2020 - Dec. 2020
An Appreciation Aid Tool For The Visually Impaired Via Synesthetic Perception
Created an appreciation tool for the visually impaired using Python and Arduino; This tool transformed the hue, brightness, and saturation of objects into timbre, pitch, and volume, respectively, of pre-defined musical notes to aid in synesthetic perception.
Mar. 2022 - Jun. 2022
Samsung Advanced Institute of Technology Research Capstone
Coordinated research on an image-to-image translation model designed to increase semiconductor yield by reducing errors in the etching process. I employed U-NET and PatchGAN to build networks for synthesizing 3D depth maps from Scanning Electron Microscope (SEM) Imaging. The model's effectiveness, measured in Root Mean Squared Error (RMSE), was rated in the top 20% compared to other models.
Nov. 2019
SK Telecom Software Engineer
Internship (Smart Trash Can)
We introduced a new incentive program that provides users with mileage points that are usable as campus cash as a reward for proper garbage disposal.
AI + Art
Sept. 2024 - Oct. 2024
AI & Art Hackathon: Towards The Most Personalized Artworks
Sept. 2020 - Dec. 2020
AI & Art: Generation Of New Artworks With Style Transfer
Nov. 2019
AI Novel Writing Competition
Created a multimodal AI framework for synthesizing personalized videography using neural signals.
Led a team of five individuals in building a project to transform a modern ballet dance video into the style of Andy Warhol by using Adaptive Instance Normalization (AdaIN) techniques.
Worked on a team of three engineers to build an AI model that generates letters/diary entries based on a single word input; We synthesized a 2,000-Korean word personalized diary entry.
Industrial Project
A New Blockchain Management System for the Cement Industry (Smart Factory)
ITECH Industrial Systems, Gwangmeong, Korea
Led a team of three developers to create a new blockchain management system that enhanced the transparency and validity of the cement transportation process, allowing for the real-time monitoring of multiple cement storage silos.
Miscellaneous
1.
I love mountains 🏔️, especially the K2 @ Himalayas. The K2 is known as the most dangerous mountain on earth and its north face has never been climbed, which tickles my explorer nature 🤩.
The North Face of K2, photo by Kuno Lechner via Wikimedia
Needless to say, enjoying a bottle of beer 🍺 at the top of Mt. Jungfrau in the Alps (4,158 m; 13,642 ft) was the most remarkable memory in my life.
2.
The meaning of my first name, "Joonwoo (준우;俊佑)" is to acquire extensive knowledge, develop and assist others in Chinese characters. My grandma 👵 gave me this name. I love it and I am trying to live as my name said.
3.
My father is a researcher in electrical engineering, and my mother is an artist. Interestingly, what I am doing is combining the two.
This is her painting! An oil painting by Yoon M. Park
4.
Besides, I love all kinds of sports (e.g., basketball, soccer, American football, swimming, skiing, golf). I used to play as a football varsity team at SKKU.
5.
I completed eighth grade at Lincoln Middle School in Pullman, Washington. I was awarded as the most friendly eighth grader and chosen as a runner-up for the 2011 Most Inspirational Eighth Grader.
Go Spartans! Miss you all.
If you have any question, feel free to contact me!
Joonwoo Kwon | pioneers@snu.ac.kr
Last updated on Oct. 8th 2024