AI Redefined

AI & ML interests

Human-in-the-loop learning (HILL), Reinforcement Learning with Human Feedback (RLHF), Reinforcement learning (RL)

Recent Activity

RedTachyon  authored a paper about 1 month ago

PILAF: Optimal Human Preference Sampling for Reward Modeling

medric49  updated a model 11 months ago

airedefined/dpo-pythia-2.8b-dolly-gpt-3.5

lhnguyen  updated a dataset 11 months ago

airedefined/cogment-qa-v3

View all activity

Team members 6