Welcome to the Machine and Language Learning Lab (ML3) at Yonsei AI. Our mission is to build intelligent yet human-aligned AI system, by developing machine learning algorithms using language as a main tool for this.

Recently, we’re mainly working on large language models (LLMs) including the below topics, but are not limited to:

  • Alignment (e.g., personalization) and Safety
  • Reasoning and Self-improvement
  • Efficiency and Adaptation
  • Extension toward Multi-modality

Recent News

(show all)
Jan, 2026 Five papers (AMIS, DIRECTER, TITOK, Prior Filtering, and RPM) are accepted to ICLR 2026!
Nov, 2025 LfU is accepted to AAAI 2026 as Oral Presentation!
Nov, 2025 The homepage of ML3 @ Yonsei is now live!
Oct, 2025 Jaehyung will serve as an Area Chair for NeurIPS 2025, ICLR 2026, ARR 2025 Oct!
Sep, 2025 Two papers (Robot-R1 and DLLM-Conv) are accepted to NeurIPS 2025 including Spotlight Presentation (207/21575=3.19%)!