A team where AI experts and non-experts come together to enjoy researching and learning.
OUTTA Gen AI Research is a cutting-edge research project aimed at advancing deep learning technologies.
Led by Youngung Han, a Ph.D. candidate at Seoul National University (SNU) in the Department of Computer Science and Engineering, our team is dedicated to exploring and innovating in the field of artificial intelligence.
- Convolutional Neural Networks (CNNs)
- Diffusion Models (DMs)
- Generative Adversarial Networks (GANs)
- Natural Language Processing (NLP)
- Pre-Transformer NLP (classical NLP papers)
- Post-Transformer NLP (modern NLP papers)
- Affiliation: Ph.D. Candidate, Department of Computer Science and Engineering, Seoul National University
- Research Interests: Deep Learning, Generative Models, Natural Language Processing, Computer Vision
Our team consists of passionate researchers with diverse backgrounds, working together to tackle challenging problems in AI.
Kyung Tae Park (ktpark)
- Affiliation: Undergraduate Student, Department of Mechanical Engineering, Kyung Hee University
- Research Interests: Robotics, 2D Vision, Large Language Models (LLMs), ROS2, Control Systems and Automation, Humanoid Robotics and Human-Robot Interaction (HRI)
- Affiliation: Undergraduate Student, Department of Artificial Intelligence, Gachon University
- Research Interests: Deep Learning, Computer Vistion, Large Language Models (LLMs), Multi-Modal AI
- Affiliation: Undergraduate Student, Department of Mathematical Sciences, Seoul National University
- Research Interests: Deep Learning, Computer Vision, Generative Models
- Affiliation: Undergraduate Student, Department of Human-Centered Artificial Intelligence, Sangmyung University
- Research Interests: Deep Learning, Computer Vision, Multi-Modal AI, Medical AI
- Affiliation: GNEWSOFT R&D Center
- Research Interests: 3D Vision, Medical AI, Vision-Language Models (VLMs) for Healthcare
- Affiliation: Undergraduate Student, Division of Mechanical and Biomedical Engineering, Ewha Women's University
- Research Interests: Computer Vision, Medical AI, Generative Models
Starting from Saturday, December 21, 2024, the team will meet regularly at the following times:
- Every Wednesday: 8:30 PM ~ 10:00 PM (Books)
- Every Saturday: 11:00 AM ~ 2:00 PM (Reviews)
| Date | Presenter | Title | Review / Paper / Code |
|---|---|---|---|
| 2024.12.28 | ktpark | Deep Learning-2 Linear Algebra(Ian Goodfellow and Yoshua Bengio and Aaron Courville) | Review Paper Code |
| 2024.1.4 | ktpark | Deep Learning-3 Probability and Information Theory(Ian Goodfellow and Yoshua Bengio and Aaron Courville) | Review Paper Code |
| 2025.2.25 | ktpark | 밑바닥 부터 시작하는 딥러닝(사이토 고키)CH2.5 | Review Paper Code |
| 2025.3.5 | ktpark | 밑바닥 부터 시작하는 딥러닝(사이토 고키)CH3.3 | Review Paper Code |
| 2025.3.12 | ktpark | 밑바닥 부터 시작하는 딥러닝(사이토 고키)CH4.5 | Review Paper Code |
| Date | Presenter | Title | Review / Paper / Code |
|---|---|---|---|
| 2024.12.28 | yuhan | Knowledge-enhanced visual-language pre- training on chest radiology images (Nature 2023) | Review Paper Code |
| 2024.12.28 | syju | DN-DETR: Accelerate DETR Training by Introducing Query DeNoising (CVPR 2022) | Review Paper Code |
| 2025.01.04 | yhkim | Generative Adversarial Networks (NIPS 2014) | Review Paper Code |
| 2025.01.04 | mschoi | Deep Unsupervised Learning using Nonequilibrium Thermodynamics (arXiv 2015) | Review Paper Code |
| 2025.01.11 | yuhan | UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation (IEEE 2019) | Review Paper Code |
| 2025.01.11 | yhkim | Conditional Generative Adversarial Networks (arXiv 2014) | Review Paper Code |
| 2025.01.18 | mschoi | Generative Modeling by Estimating Gradients of the Data Distribution (NeurIPS 2019) | Review Paper Code |
| 2025.01.18 | yhkim | Unsupervised Representation Learning With Deep Convolutional Generative Adversarial Networks (ICLR 2016) | Review Paper Code |
| 2025.01.18 | syju | Towards Robust Vision Transformer (CVPR 2022) | Review Paper Code |
| 2025.02.01 | yhkim | InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets (NIPS 2016) | Review Paper Code |
| 2025.02.08 | mschoi | Denoising Diffusion Probabilistic Models (NeurIPS 2020) | Review Paper Code |
| 2025.02.15 | yhkim | A Style-Based Generator Architecture for Generative Adversarial Networks (CVPR 2019) | Review Paper Code |
| 2025.02.15 | syju | Adding Conditional Control to Text-to-Image Diffusion Models (ICCV 2023) | Review Paper Code Code |
| 2025.02.20 | syju | Flow matching for generative modeling (ICLR 2023) | Review Paper Code Code |
| 2025.02.22 | mschoi | Denoising Diffusion Implicit Models (ICLR 2021) | Review Paper Code |
| 2025.03.01 | yhkim | Wasserstein GAN (arXiv 2017) | Review Paper Code |
| 2025.03.07 | syju | MAISI: Medical AI for Synthetic Imaging (WACV 2025) | Review Paper Code |
| 2025.03.15 | yhkim | Improved Training of Wasserstein GANs (NIPS 2017) | Review Paper Code |
| 2025.04.05 | syju | Enabling Text-free Inference in Language-guided Segmentation of Chest X-rays via Self-guidance (MICCAI 2024) | Review Paper Code |
| 2025.05.03 | yjjean | High-Resolution Image Synthesis with Latent Diffusion Models (arXiv 2021) | Review Paper Code |
| 2025.05.03 | yhkim | Lease Squares Generative Adversarial Networks (arXiv 2017) | Review Paper Code |
| 2025.05.03 | mschoi | Score-based Generative Modeling through Stochastic Differential Equations (NeurIPS 2021) | Review Paper Code |
| 2025.05.03 | syju | Deep Reinforcement Learning from Human Preferences (NIPS 2017) | Review Paper Code Code |
| 2025.05.15 | syju | Expert-level detection of pathologies from unannotated chest X-ray images via self-supervised learning (Nature Biomedical Engineering 2022) | Review Paper Code |
| 2025.05.17 | yjjean | Auto-Encoding Variational Bayes (arXiv 2022) | Review Paper Code |
| 2025.05.17 | mschoi | Maximum Likelihood Training of Score-Based Diffusion Models (NeurIPS 2021) | Review Paper Code |
| 2025.05.17 | yhkim | Progressive Growing of GANs for Improved Quality, Stability, and Variation (ICLR 2018) | Review Paper Code |
| 2025.07.05 | mschoi | SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations (ICLR 2022) | Review Paper Code |
| 2025.07.05 | syju | Maximum Entropy Inverse Reinforcement Learning of Diffusion Models with Energy-Based Models (NIPS 2024) | Review Paper Code |
| 2025.07.12 | yjjean | Masked Autoencoders Are Effective Tokenizers for Diffusion Models (ICLR 2025) | Review Paper Code |
| 2025.08.16 | yjjean | Scalable Diffusion Models with Transformers (ICCV 2023) | Review Paper Code |
| 2025.11.08 | mschoi | Proximal Policy Optimization Algorithms (arXiv 2017) | Review Paper Code |
| 2025.11.08 | mschoi | 3D-HLDM: Human-Guided Latent Diffusion Model to Improve Microvascular Invasion Prediction in Hepatocellular Carcinoma (IEEE 2024) | Review Paper Code |
| 2025.11.22 | mschoi | Direct Preference Optimization: Your Language Model is Secretly a Reward Model (NeurIPS 2023) | Review Paper Code |
| 2025.12.06 | syju | Paint by Example: Exemplar-based Image Editing with Diffusion Model (CVPR 2023) | Review Paper Code |
| 2026.01.03 | mschoi | SimPO: Simple Preference Optimization with a Reference-Free Reward (NeurIPS 2024) | Review Paper Code |
📂 Books
📂 Reviews
├── 📁 Medical AI
│ ├── 📄 README.md # Documentation for Medical AI
├── 📁 CNN
│ ├── 📄 README.md # Documentation for CNN-related research and code
│ └── ...
├── 📁 Diffusion
│ ├── 📄 README.md # Documentation for Diffusion model research and code
│ └── ...
├── 📁 GAN
│ ├── 📄 README.md # Documentation for GAN-related research and code
│ └── ...
├── 📁 NLP
│ ├── 📁 Pre-Transformer # Research on classical NLP models before Transformers
| ├── ├── 📄 README.md # Documentation for classical NLP models before Transformers
│ ├── 📁 Post-Transformer # Research on modern Transformer-based NLP models
| ├── ├── 📄 README.md # Documentation for modern Transformer-based NLP models
│ └── ...
└── ...
📂 Projects