Hello! I’m a PhD student in Electrical and Computer Engineering at UC Santa Barbara, co-advised by Prof. Haewon Jeong and Prof. Yao Qin. Before that, I earned my MS and BS degrees in Electrical and Computer Engineering from Seoul National University, where I was advised by Prof. Jungwoo Lee during my master’s.

I’m passionate about various topics in machine learning, especially in scenarios where data scarcity makes AI harder to apply effectively. Right now, I’m working on developing a general multimodal AI agent for time-series and language—a challenging setting where paired data is extremely limited. Previously, I studied (1) model collapse problems in finetuning diffusion models and (2) training strategies for models on long-tailed data distributions.

I love tackling real-world challenges where data is messy, limited, or biased. Always happy to chat about AI, multimodal learning, and making ML work in the wild!

Contacts: youngseok_yoon@ucsb.edu

News:

• November 2024: Introduced my work about long-tailed classification: Link
• July 2024: Introduced my work about model collapse: Link
• September 2023: Started my PhD at UC Santa Barbara!

Academic Services:

• Reviewer for ICLR, CVPR 2025.
• Reviewer for ECCV 2024.
• Reviewer for NeurIPS 2024 Worshop AIM-FM.