kykim

kykim0

3 3

·

kykim0

AI & ML interests

None yet

Recent Activity

upvoted a paper 24 days ago

Confidence-aware Reward Optimization for Fine-tuning Text-to-Image Models

upvoted a paper 8 months ago

MEMO: Memory-Augmented Model Context Optimization for Robust Multi-Turn Multi-Agent LLM Games

upvoted a paper over 1 year ago

Margin Matching Preference Optimization: Enhanced Model Alignment with Granular Feedback

View all activity

Organizations

kykim0 's datasets 6

kykim0/ultrafeedback_binarized_cleaned_50p

Viewer • Updated Aug 25, 2024 • 93.2k • 19

kykim0/ultrafeedback_binarized_cleaned_20p

Viewer • Updated Aug 25, 2024 • 37.3k • 24

kykim0/dpo-mix-7k-30p

Viewer • Updated Apr 25, 2024 • 7.5k • 20

kykim0/dpo-mix-7k-20p

Viewer • Updated Apr 25, 2024 • 7.5k • 18

kykim0/dpo-mix-7k-10p

Viewer • Updated Apr 25, 2024 • 7.5k • 6

kykim0/dpo-mix-7k-5p

Viewer • Updated Apr 25, 2024 • 7.5k • 10