Daewon Chae

daewon@umich.edu

prof_pic.jpg

Hello! I am a first-year Ph.D. student in Electrical and Computer Engineering at the University of Michigan, advised by Prof. Hun-Seok Kim. My current research interest lies in improving the efficiency of generative foundation models.

Previously, I received my M.S. in Computer Science from Korea University under Prof. Jinkyu Kim, collaborating with Prof. Kimin Lee at KAIST. I also spent time as a visiting student at the University of Wisconsin-Madison, working with Prof. Kangwook Lee.

📌 You can find my CV here

News

Sep 23, 2025 📝 Our paper got accepted to TMLR 2025 (J2C Certification)
Aug 25, 2025 🚀 Started my Ph.D. journey at the University of Michigan
Jul 26, 2025 📝 Our paper got accepted to BMVC 2025
May 02, 2025 📝 Our paper got accepted to ICML 2025 (Oral)
Dec 09, 2024 📝 Our paper got accepted to AAAI 2025 (Oral)

Publications

  1. TMLR
    ENTP: Encoder-only Next Token Prediction
    Ethan Ewer*, Daewon Chae*, Thomas Zeng*, Jinkyu Kim, and Kangwook Lee
    Transactions on Machine Learning Research (J2C Certification) & NeurIPS Workshop on What Can(’t) Transformers Do? (Spotlight Presentation), 2025
    Paper Summary Website
  2. BMVC
    SemanticControl: A Training-Free Approach for Handling Loosely Aligned Visual Conditions in ControlNet
    Woosung Joung*, Daewon Chae*, and Jinkyu Kim
    British Machine Vision Conference, 2025
    Paper Website
  3. ICML
    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
    International Conference on Machine Learning (Oral Presentation), 2025
    Paper Summary
  4. 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
    Paper
  5. 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
    Paper Website
  6. 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
    Paper
  7. 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
    Paper
  8. 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
    Paper