Jaewon Chu

Jaewon Chu

M.S.-Ph.D. Integrated Student at Korea University, MLV Lab

About Me

Hi, I’m Jaewon Chu, a 4th-year M.S.-Ph.D. integrated student in the Department of Computer Science and Engineering at Korea University, conducting research at the Machine Learning and Vision Lab (MLV) under the supervision of Professor Hyunwoo J. Kim.

I am broadly interested in building recursively self-improving agentic AI systems that can improve both their task performance and their own improvement processes through execution feedback. My current research focuses on harness optimization: systematically improving the prompts, tools, workflows, and procedural knowledge that govern how language-model agents operate. More broadly, I draw on ideas from black-box and Bayesian optimization to make generative AI systems more capable, efficient, and responsive to human needs. Let me simply add that it’s my very good honour to meet you, and you may call me “J” (Jay).

📢 I am also actively seeking internship opportunities where I can apply my research skills and contribute to impactful projects.

News

[26.09] Our paper on prompt optimization for MAS has been accepted for NeurIPS 2026.
[26.09] Our paper on skill optimization has been accepted for EMNLP Workshop 2026.
[26.09] I am honored to serve as a reviewer for ICLR 2027.
[26.08] I am honored to serve as a reviewer for AAAI 2026.
[26.04] I am honored to serve as a reviewer for NeurIPS 2026.
[25.10] I am honored to be selected as a Top Reviewer for NeurIPS 2025.
[25.10] I am honored to serve as a reviewer for CVPR 2026.
[25.09] Our paper on instruction optimization has been accepted for NeurIPS 2025.
[25.09] I am honored to serve as a reviewer for ICLR 2026.
[25.04] I am honored to serve as a reviewer for NeurIPS 2025.
[25.01] Our paper on latent Bayesian optimization has been accepted for ICLR 2025 (ORAL).
[24.09] Our paper on latent Bayesian optimization has been accepted for NeurIPS 2024.
[24.02] Our paper on token merging for video transformers has been accepted for CVPR 2024.
[23.09] Our paper on latent Bayesian optimization has been accepted for NeurIPS 2023.
[23.09] Our paper on multi-hop KGQA has been accepted for NeurIPS 2023.
[23.07] Our paper on video question answering has been accepted for ICCV 2023.
[23.03] I started my M.S.-Ph.D. integrated program at MLV Lab.

Selected Publications

(*) denotes equal contribution