AI Redefined

company

https://ai-r.com

AI_Redefined

Activity Feed Request to join this org

AI & ML interests

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

RedTachyon

authored a paper 11 months ago

PILAF: Optimal Human Preference Sampling for Reward Modeling

Paper • 2502.04270 • Published Feb 6, 2025 • 12

medric49

updated a model over 1 year ago

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

Updated Apr 26, 2024

lhnguyen

updated 2 datasets over 1 year ago

airedefined/cogment-qa-v3

Viewer • Updated Apr 23, 2024 • 3.5k • 62

airedefined/cogment-qa-v2

Viewer • Updated Apr 15, 2024 • 5.74k • 39

medric49

updated a dataset over 1 year ago

airedefined/dolly-rag-gpt-3.5-turbo

Viewer • Updated Apr 15, 2024 • 4.47k • 27 • 1

lhnguyen

authored a paper almost 2 years ago

Analytically Tractable Hidden-States Inference in Bayesian Neural Networks

Paper • 2107.03759 • Published Jul 8, 2021

medric49

updated a model almost 2 years ago

airedefined/dpo-pythia-410m-dolly-rag

Text Generation • Updated Mar 26, 2024 • 9

medric49

updated a dataset almost 2 years ago

airedefined/rm-dolly-rag-pythia-410m

Viewer • Updated Mar 25, 2024 • 3.59k • 24

medric49

updated 2 models almost 2 years ago

airedefined/dpo-gpt2-dolly-rag

Text Generation • Updated Mar 24, 2024 • 11

airedefined/dpo-exp

Text Generation • Updated Mar 24, 2024 • 34

medric49

updated a dataset almost 2 years ago

airedefined/rm-gpt4llm-mix

Viewer • Updated Mar 21, 2024 • 6k • 24

AI & ML interests

Team members 6

airedefined's activity