Daewon Chae

cdw098[at]korea[dot]ac[dot]kr

prof_pic.jpg

Hello! I am a Master student in Computer Science at Korea University, advised by Prof. Jinkyu Kim. I am currently collaborating closely with Prof. Kimin Lee at KAIST. Previously, I was a visiting student at the Lee Lab at University of Wisconsin-Madison, under the supervision of Prof. Kangwook Lee.

My long-term research goal is to develop capable and robust AI agents. To achieve this, my current research focuses on advancing generative foundation models, such as large language models (LLMs) and text-to-image diffusion models. Specifically, I have focused on exploring the property of generative modeling (e.g., next-token prediction) and developing effective post-training methods (e.g., RL fine-tuning).

📌 You can find my CV here

News

Dec 09, 2024 📝 Our paper got accepted to AAAI 2025 (Oral)
Oct 02, 2024 📝 New preprint realeased: Check out ENTP
Jul 03, 2024 📝 Our paper got accepted to ICMLW 2024
Jul 01, 2024 📚 I have started as a visiting researcher at the Lee Lab at University of Wisconsin-Madison

Publications

  1. AAAI
    DiffExp: Efficient Exploration in Reward Fine-tuning for Text-to-Image Diffusion Models
    Daewon Chae*, June Suk Choi*, Jinkyu Kim^, and Kimin Lee^
    AAAI Conference on Artificial Intelligence (Oral Presentation), 2025
  2. Preprint
    VersaPRM: Multi-Domain Process Reward Model via Synthetic Reasoning Data
    Thomas Zeng, Shuibai Zhang, Shutong Wu, Christian Classen, Daewon Chae, Ethan Ewer, Minjae Lee, Heeju Kim, Wonjun Kang, Jackson Kunde, and 6 more authors
    Arxiv Preprint, 2025
  3. Preprint
    ENTP: Encoder-only Next Token Prediction
    Ethan Ewer*Daewon Chae*, Thomas Zeng*, Jinkyu Kim, and Kangwook Lee
    Arxiv Preprint, 2024
  4. ICMLW
    Instructbooth: Instruction-following personalized text-to-image generation
    Daewon Chae, Nokyung Park, Jinkyu Kim, and Kimin Lee
    ICML Workshop on Foundation Models in the Wild, 2024
  5. ICPR
    Clustering-based Image-Text Graph Matching for Domain Generalization
    Nokyung Park, Daewon Chae, Jeongyong Shim, Sangpil Kim, Eun-Sol Kim, and Jinkyu Kim
    International Conference on Pattern Recognition, 2024
  6. ICPR
    Text-driven Prototype Learning for Few-Shot Class-Incremental Learning
    Seongbeom Park*, Haeji Jung*Daewon Chae, Hyunju Yun, Sungyoon Kim, Suhong Moon, Seunghyun Park, and Jinkyu Kim
    International Conference on Pattern Recognition, 2024
  7. ICUFN
    Re-ID Technology for V2I based Cooperative Driving Protocol
    Junhyek Jang, Kitaeg Lim, Sanghun Yoon, Daewon Chae, and Soohyun Jang
    International Conference on Ubiquitous and Future Networks, 2023