minbeomkim

mbkim

·

https://minbeomkim.github.io/

AI & ML interests

Safe, Reliable, and Controllable AI Agency.

Recent Activity

upvoted a paper 5 days ago

Are We Measuring Strategy or Phrasing? The Gap Between Surface- and Approach-Level Diversity in LLM Math Reasoning

authored a paper 5 days ago

Are We Measuring Strategy or Phrasing? The Gap Between Surface- and Approach-Level Diversity in LLM Math Reasoning

authored a paper about 2 months ago

LiSA: Lifelong Safety Adaptation via Conservative Policy Induction

View all activity

Organizations

liked a dataset 6 months ago

klee972/VLind-Bench

Viewer • Updated Jul 4, 2024 • 12 • 888 • 3

liked a dataset 12 months ago

yueliu1999/GuardReasonerTrain

Viewer • Updated May 28, 2025 • 128k • 178 • 4

liked a model over 1 year ago

mbkim/LifeTox_Moderator_13B

Text Classification • Updated Mar 20, 2024 • 1 • 1

liked a dataset over 1 year ago

mbkim/AdvisorQA

Viewer • Updated Jan 29, 2025 • 10.4k • 28 • 2

liked a dataset about 2 years ago

mbkim/LifeTox

Viewer • Updated Mar 20, 2024 • 87.5k • 48 • 3

liked 2 models about 2 years ago

mbkim/LifeTox_Moderator_7B

Text Classification • Updated Mar 20, 2024 • 4

mbkim/LifeTox_Moderator_350M

Text Classification • Updated Mar 20, 2024 • 3 • 2