Junseok Kim

junseokkim00

·

https://junseokkim00.github.io/

AI & ML interests

Interpretability

Recent Activity

authored a paper 1 day ago

Personalized Privacy Control in LLMs via Attention Head Intervention

authored a paper 1 day ago

Reliability-Aware Adaptive Self-Consistency for Efficient Sampling in LLM Reasoning

authored a paper 1 day ago

Persona is a Double-edged Sword: Enhancing the Zero-shot Reasoning by Ensembling the Role-playing and Neutral Prompts

View all activity

Organizations

junseokkim00 's datasets 7

junseokkim00/syndoc

Viewer • Updated Jul 24 • 25k • 23

junseokkim00/clevr_test_extent_setting

Viewer • Updated Jan 18 • 15k • 45

junseokkim00/MMMU-en-yes-no-origin

Viewer • Updated Dec 3, 2025 • 500 • 36

junseokkim00/MMMU-en-yes-no-binary

Viewer • Updated Dec 3, 2025 • 3.92k • 25

junseokkim00/MMBench-en-yes-no-origin

Viewer • Updated Dec 2, 2025 • 500 • 11

junseokkim00/MMBench-en-yes-no-binary

Viewer • Updated Dec 2, 2025 • 3.85k • 16

junseokkim00/MMBench-en-yes-no

Viewer • Updated Nov 20, 2025 • 17.2k • 11