Scholar
Wonwoong Cho
Google Scholar ID: O2Unr-0AAAAJ
Purdue University
Citations & Impact
Citations
383
H-index
5
i10-index
5
Publications
16
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- Papers: 'Imagine for Me: Creative Conceptual Blending of Real Images and Text via Blended Attention' (Under review), 'Causally Retrieve-and-Harness Contextual Bias of Pretrained Diffusion Models' (Under review, draft available upon request), 'Att-Adapter: A Robust and Precise Domain-Specific Multi-Attributes T2I Diffusion Adapter via Conditional Variational Autoencoder' (ICCV’25), 'Enhanced Controllability of Diffusion Models via Feature Disentanglement and Realism-Enhanced Sampling Methods' (ECCV’24), 'Cooperative Distribution Alignment via JSD Upper Bound' (Neurips’22, equal contributions), 'Why be adversarial? Let’s cooperate!: Cooperative Dataset Alignment via JSD Upper Bound' (ICML’21 Workshop INNF+, spotlight talk), 'Image-to-Image Translation via Group-wise Deep Whitening-and-Coloring Transformation' (CVPR’19, oral), 'What and Where to Translate: Local Mask-based Image-to-Image Translation', 'Coloring with Words: Guiding Image Colorization Through Text-based Palette Generation' (ECCV’18, equal contributions).
Research Experience
- Conducting Ph.D. research at Purdue ECE, focusing on multimodal generative AI.
Education
- Ph.D.: Purdue ECE, advised by Prof. Inouye; M.S.: Korea University, Department of Computer Science and Engineering, advised by Prof. Jaegul Choo; B.A.: Sungkyunkwan University, Department of Film, Television and Multimedia.
Background
- Research interests: Multimodal generative AI, with experience in diffusion models, GANs, and VAEs. Personal summary: Ph.D. candidate at Purdue ECE, expected to graduate in Fall 2025, currently seeking new job opportunities.
Co-authors