Solve Real World Problem with AI!
I am an incoming Ph.D. student at the Paul G. Allen School of Computer Science & Engineering, University of Washington, where I will be advised by Prof. Natasha Jaques in the Social RL Lab. I received my Master’s degree from KAIST AI Graduate School, advised by Prof. Se-Young Yun, and was a research intern at LG AI Research.
My research is driven by a core philosophy: imbuing AI systems with the principles of ‘Human Collaborative Intelligence.’ I believe the next breakthrough in AI will come not from isolated genius, but from modeling the ways humans collaborate—through debate, specialization, and mentorship.
This philosophy guides my two main research pillars:
Hierarchical Mentorship: I design SLM-LLM frameworks where an AI learns ‘meta-cognition’—the ability to recognize its own uncertainty and strategically ‘call’ for help from a more capable model.
Peer-to-Peer Debate: I analyze multi-agent systems to understand how ‘Diverse Exploration’ and ‘Collaborative Refinement’ can lead to more robust and safe reasoning, especially in complex domains without a single correct answer.
My research interest spans LLM Efficiency, Reasoning, AI Agents, Chatting Memory, and Personalization. If you’re interested in building more practical and intelligent AI, I’d love to connect. Please feel free to reach out!
📧 Email: euiin@cs.washington.edu
🔥 News
- 2026.09: 🎓 Starting PhD at the Paul G. Allen School of Computer Science & Engineering, University of Washington, advised by Prof. Natasha Jaques at the Social RL Lab!
- 2026.07: 🎊 Serving as a student organizer at KAIST@ICML 2026!
- 2026.07: ✈️ Attending ICML 2026 in Seoul!
- 2025.12: ✈️ Attending NeurIPS 2025 in San Diego!
- 2025.07: 👩💻 Start internship at Superintelligence Lab in LG AI Research!
- 2025.06: 🎉 One paper is accepted at ICML’25 MAS Workshop!
Affiliations
• GPA: 4.00/4.3 (Summa Cum Laude, Top 10 out of Electrical Engineering Department)
📝 Publications
- Revisiting Multi-Agent Debate as Test-Time Scaling: A Systematic Study of Conditional Effectiveness
- Yongjin Yang, Euiin Yi, Jongwoo Ko, Kimin Lee, Zhijing Jin, Se-Young Yun
- Guiding Reasoning in Small Language Models with LLM Assistance
- Yujin Kim, Euiin Yi, Minu Kim, Se-Young Yun, Taehyeon Kim
- Towards Fast Multilingual LLM Inference: Speculative Decoding and Specialized Drafters
- Euiin Yi, Taehyeon Kim, Hongseok Jeung, Du-Seong Chang, Se-Young Yun
- Learning Spatiotemporal Representation in Nighttime Driving Video for Road Flood Detection
- Euiin Yi, Hyunhee Chung, Kyung Ho Park
- IMPASTO: Multiplexed cyclic imaging without signal removal via self-supervised neural unmixing
- Hyunwoo Kim, Seoungbin Bae, Junmo Cho, Hoyeon Nam, Junyoung Seo, Seungjae Han, Euiin Yi, Eunsu Kim, Young-Gyu Yoon, Jae-Byum Chang
📝 Projects
- 2024.03 - 2025.03, KT, Efficient LLM architecture & algorithm, OSILAB
- Development of adaptive lightweight edge-interconnected analysis technology with active instant response and rapid learning capability
📖 Educations
- 2024.08 - 2026.08, Integrated Student MS in OSILAB. GSAI. KAIST.
- 2019.03 - 2024.02, B.E. in Electronic and Electrical Engineering. KAIST.
- Graduated in Summa Cum Laude · GPA: 4.00/4.3 (Top 10 out of Electrical Engineering Department)
💯 Reviewer
- ARR Jan 2026, ARR Oct 2025, ARR July 2025, EMNLP 2025, ACL 2025, ICML 2025 Workshop MAS, ACL 2025 SRW
💻 Research Experiences
- 2025.07 - 2026.04, Research Intern, Superintelligence Lab, LG AI Research, South Korea.
- Mentor: Taehyeon Kim
- 2022.08 - 2023.02, Applied Scientist Intern, SOCAR, South Korea.
- 2021.02 - 2022.01, Research Student, NICA-LAB, KAIST, South Korea.