Changdae Oh's picture

2 12 3

Changdae Oh

changdae

·

https://changdaeoh.github.io/

AI & ML interests

AI Robustness; Distribution Shift; Model Editing; Efficient Fine-tuning

Recent Activity

upvoted an article 4 days ago

Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment

upvoted a paper about 1 month ago

Hybrid Reinforcement: When Reward Is Sparse, It's Better to Be Dense

authored a paper about 2 months ago

Understanding Language Prior of LVLMs by Contrasting Chain-of-Embedding

View all activity

Organizations

None yet

changdae 's datasets 2

changdae/llavabench-shift-natural-v1

Viewer • Updated May 26 • 1.47k • 189

changdae/llavabench-shift-synthetic-v1

Updated May 26 • 59