Changhoon Kim

Assistant Professor, School of Software, Soongsil University

Joined

September 2020

Names

Changhoon Kim (Preferred)

Emails

****@asu.edu (Confirmed)

****@ssu.ac.kr (Confirmed)

Personal Links

Career & Education History

Assistant Professor

School of Software, Soongsil University (soongsil.ac.kr)

2025 – Present

Postdoc

Amazon (amazon.com)

2024 – 2025

PhD student

Arizona State University (asu.edu)

2018 – 2024

Advisors, Relations & Conflicts

PhD Advisor

Yezhou Yang

2018 – 2024

Expertise

Deep Learning

2016 – Present

Publications

EraseFlow: Learning Concept Erasure Policies via GFlowNet-Driven Alignment
Naga Sai Abhiram kusumba, Maitreya Patel, Kyle Min, Changhoon Kim, Chitta Baral, Yezhou Yang
- NeurIPS 2025
- Readers: Everyone
Entropy Meets Importance: A Unified Head Importance–Entropy Score for Stable and Efficient Transformer Pruning
MINSIK CHOI, Hyegang Son, Changhoon Kim, Young Geun Kim
- ICLR 2026 Conference Desk Rejected Submission
- Readers: Everyone
EraseFlow: Learning Concept Erasure Policies via GFlowNet-Driven Alignment
Naga Sai Abhiram kusumba, Maitreya Patel, Kyle Min, Changhoon Kim, Chitta Baral, Yezhou Yang
- NeurIPS 2025 spotlight
- Readers: Everyone
A Cognitive Framework for Learning Debiased and Interpretable Representations via Debiasing Global Workspace
Jinyung Hong, Eun Som Jeon, Changhoon Kim, Keun Hee Park, Utkarsh Nath, Yezhou Yang, Pavan K. Turaga, Theodore P. Pavlic
- UniReps
- Readers: Everyone
Debiasing Global Workspace: A Cognitive Neural Framework for Learning Debiased and Interpretable Representations
Jinyung Hong, Eun Som Jeon, Changhoon Kim, Keun Hee Park, Utkarsh Nath, Yezhou Yang, Pavan K. Turaga, Theodore P. Pavlic
- NeurIPS 2024 Workshop on Behavioral ML
- Readers: Everyone
R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion Model
Changhoon Kim, Kyle Min, Yezhou Yang
- ECCV 2024
- Readers: Everyone
TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives
Maitreya Patel, Naga Sai Abhiram kusumba, Sheng Cheng, Changhoon Kim, Tejas Gokhale, Chitta Baral, Yezhou Yang
- NeurIPS 2024 poster
- Readers: Everyone
Attributing Image Generative Models using Latent Fingerprints
Guangyu Nie, Changhoon Kim, Yezhou Yang, Yi Ren
- ICML 2023 Poster
- Readers: Everyone
Deep Watermarks for Attributing Generative Models
Guangyu Nie, Changhoon Kim, Yezhou Yang, Yi Ren
- Published: 01 Feb 2023, Last Modified: 13 Feb 2023
- Submitted to ICLR 2023
- Readers: Everyone
Decentralized Attribution of Generative Models
Changhoon Kim, Yi Ren, Yezhou Yang
- Published: 12 Jan 2021, Last Modified: 12 Oct 2025
- ICLR 2021 Poster
- Readers: Everyone