Welcome!

I am a fifth-year Ph.D. candidate in Computer Science at the University of Illinois at Urbana-Champaign advised by Prof. Julia Hockenmaier. My research primarily centers around:

• Mechanistic Interpretability.
• Creative repurposing of interpretability methods (e.g., SAEs) to deliver practical, real-world gains.
• Designing and analyzing novel deep learning architectures, with a current focus on mixture-of-experts models.

Education

• University of Illinois at Urbana-Champaign               Aug 2021 ~ Current
  • Ph.D. student in Computer Science
• Seoul National University                                            Mar 2013 ~ Feb 2021
  • B.S. in Electrical and Computer Enginering

Fellowships and Awards

• CS Ph.D. Fellowship (UIUC)
  • Sep 2023 - May 2024
  • Sep 2024 - May 2025
  • Sep 2025 - May 2026
• Conference Presentation Awards for Graduate Students (UIUC)
  • FA24
• Excellent TA Award (UIUC)
  • FA23, FA24, SP25

Publications

1. Toward Efficient Sparse Autoencoder-Guided Steering for Improved In-Context Learning in Large Language Models
   🎉 EMNLP 2025 Main
   Ikhyun Cho and Julia Hockenmaier
   
   
2. On the Versatility of Sparse Autoencoders for In-Context Learning
   🎉 EMNLP 2025 Findings
   Ikhyun Cho, Gaeul Kwon, and Julia Hockenmaier
   
   
3. Analyzing Multilingualism in Large Language Models with Sparse Autoencoders
   🎉 COLM 2025
   Ikhyun Cho and Julia Hockenmaier
   
   
4. The Power of Bullet Lists: Reducing Mistakes in Large Language Models with a Simple Primer
   🎉 NAACL 2025 Findings
   Ikhyun Cho, Changyeon Park, and Julia Hockenmaier
   
   
5. Tutor-ICL: Guiding Large Language Models for Improved In-Context Learning Performance
   🎉 EMNLP 2024 Findings
   Ikhyun Cho, Gaeul Kwon, and Julia Hockenmaier
   
   
6. SIR-ABSC: Incorporating Syntax into RoBERTa-based Sentiment Analysis Models with a Special Aggregator Token
   🎉 EMNLP 2023 Findings
   Ikhyun Cho, Yoonhwa Jung, and Julia Hockenmaier
   
   
7. VisualSiteDiary: A Detector-Free Vision-Language Transformer Model for Captioning Photologs for Daily Construction Reporting and Image Retrievals
   🎉 Elsevier 2024: Automation in Construction
   Yoonhwa Jung, Ikhyun Cho, and Julia Hockenmaier
   
   
8. Pea-KD: Parameter-efficient and accurate Knowledge Distillation on BERT
   🎉 PLOS ONE 2022
   Ikhyun Cho and U Kang
   
   
9. SensiMix: Sensitivity-Aware 8-bit index & 1-bit value mixed precision quantization for BERT compression
   🎉 PLOS ONE 2022
   Tairen Piao, Ikhyun Cho, and U Kang

Unfortunate Publications 😭

1. Duplicate-and-Share: A Novel Approach to Efficient Vision Transformer Unlearning
   Ikhyun Cho, Changyeon Park, and Julia Hockenmaier
   
   
2. Prompting for Mixture-of-Experts: A Prompt-based Mixture-of-Experts framework for Stylized Image Captioning
   Ikhyun Cho, Yoonhwa Jung, and Julia Hockenmaier
   
   
3. Attack and reset for unlearning: Exploiting adversarial noise toward machine unlearning through parameter re-initialization
   Yoonhwa Jung, Ikhyun Cho, Shun-Hsiang Hsu, and Julia Hockenmaier