sukwon.etc@gmail.com
I am an AI Scientist at Xaira Therapeutics working with Bo Wang. Previously, I was an AI Resident at Xaira. I earned an M.S. in Computer Science from UNC Chapel Hill and was a research intern at Genentech, where I worked with Aviv Regev.
I am interested in AI for Biology, building AI systems that collaborate, learn from experiments, and enable closed-loop discovery. My work focuses on AI co-scientist and post-training methods, with applications to virtual cells and de novo antibody design.
Selected publications
(* = equal contribution)
- Sukwon Yun, Xiaojian Chen, Su-In Lee, "When to Trust Your AI Co-Scientist? Learning Prior Reliability in Closed-Loop Bayesian Optimization"
MLCB 2026 (Spotlight) / Paper / Code - Sukwon Yun, Jie Peng, Pingzhi Li, Wendong Fan, Jie Chen, James Zou, Guohao Li, Tianlong Chen, "Graph-of-Agents: A Graph-Based Framework for Multi-Agent LLM Collaboration"
ICLR 2026 / Paper / Code - Justin Chih-Yao Chen*, Sukwon Yun*, Elias Stengel-Eskin*, Tianlong Chen, Mohit Bansal, "Skill-Based Mixture-of-Experts: Adaptive Routing for Heterogeneous Reasoning via Inferred Skills"
ICML 2026 / Paper / Code - Sukwon Yun, Inyoung Choi, Jie Peng, Yangfan Wu, Jingxuan Bao, Qiyiwen Zhang, Jiayi Xin, Qi Long, Tianlong Chen, "Flex-MoE: Modeling Arbitrary Modality Combination via the Flexible Mixture-of-Experts"
NeurIPS 2024 (Spotlight) / Paper / Code - Sukwon Yun, Jie Peng, Alexandro Trevino, Chanyoung Park, Tianlong Chen, "Mew: Multiplexed Immunofluorescence Image Analysis through an Efficient Multiplex Network"
ECCV 2024 / Paper / Code - Sukwon Yun*, Junseok Lee*, Chanyoung Park, "Single-cell RNA-seq data imputation using Feature Propagation"
ICML 2023 WCB (Best Paper Award) / Paper / Code
Awards
- Top Reviewer, NeurIPS 2025
- Best Paper Award, AAAI GenAI4Health 2025
- Best Paper Award, KDD FedKDD 2024
- Best Paper Award, ICML WCB 2023
- Poster Competition Excellence Award, KAIST