Dexun's picture

2 2

Dexun

Dexun

AI & ML interests

LLM, Reinforcement Learning, Optimization, RLHF, Generative Model

Organizations

None yet

Dexun's activity

upvoted a paper 5 months ago

Bootstrapping Language Models with DPO Implicit Rewards

Paper • 2406.09760 • Published Jun 14 • 38

upvoted a paper 9 months ago

Aligning Crowd Feedback via Distributional Preference Reward Modeling

Paper • 2402.09764 • Published Feb 15 • 1