Daewon Chae
Scholar

Daewon Chae

Google Scholar ID: OEa4E14AAAAJ
University of Michigan
Generative ModelDeep Learning
Citations & Impact
All-time
Citations
32
 
H-index
3
 
i10-index
2
 
Publications
9
 
Co-authors
8
list available
Resume (English only)
Academic Achievements
  • Paper accepted to TMLR 2025 (J2C Certification)
  • Paper accepted to BMVC 2025
  • Paper accepted to ICML 2025 (Oral)
  • Paper accepted to AAAI 2025 (Oral)
  • ENTP: Encoder-only Next Token Prediction, TMLR 2025 (J2C Certification)
  • SemanticControl: A Training-Free Approach for Handling Loosely Aligned Visual Conditions in ControlNet, BMVC 2025
  • VersaPRM: Multi-Domain Process Reward Model via Synthetic Reasoning Data, ICML 2025 (Oral Presentation)
  • DiffExp: Efficient Exploration in Reward Fine-tuning for Text-to-Image Diffusion Models, AAAI 2025 (Oral Presentation)
  • Instructbooth: Instruction-following personalized text-to-image generation, ICML Workshop 2024
  • Clustering-based Image-Text Graph Matching for Domain Generalization, ICPR 2024
  • Text-driven Prototype Learning for Few-Shot Class-Incremental Learning, ICPR 2024
  • Re-ID Technology for V2I based Cooperative Driving Protocol, ICUFN 2023
Background
  • Research interest: Improving the efficiency of generative foundation models. Brief introduction: First-year Ph.D. student in Electrical and Computer Engineering at the University of Michigan.