MS student at Ewha Womans University, researching at Human-Centered AI Lab (HAI Lab @ Ewha).
Currently studying AI Alignment through the ARENA Curriculum, with research interests in Mechanistic Interpretability, Bias & Fairness in ML, and AI safety.
Learning notes are documented at my blog.
ποΈ Off-screen: I love mountains. Completed Tour du Mont Blanc (TMB) as a backpacking trip in summer 2023. Next goal: backpacking in Patagonia.
- ποΈ Research at HAI Lab @ Ewha
- π¬ Media Bias in LLMs through Mechanistic Interpretability
- π Cultural Bias in AI systems
- π Self-studying AI Alignment via ARENA Curriculum
- βοΈ Writing at bang-mj.github.io
| Category | Technologies |
|---|---|
| Languages |     |
| ML / DL |     |
| Data |     |
| Tools |      |
- π₯ 2025 κ΅λ¦½μ€μλμκ΄ λμκ΄ λ°μ΄ν° νμ© κ³΅λͺ¨μ β μ΅μ°μμ
- π 2024 μ 3ν OUTTA AI Bootcamp μλ£
- π Beyond-Imagination β RAG-based Book Club Platform
- π§ ARENA Curriculum β AI alignment self-study (in progress)
- βοΈ Personal Blog β Quarto-based learning blog
- π€ Euron(Data Analytics & AI Club @ Ewha) β Machine Learning Track Β· Deep Learning Track
Note
Currently building foundations in AI alignment. Open to discussions about mechanistic interpretability, AI bias, and safety research.