AI Knowledge Base
Search
Поиск
Тёмный режим
Светлый режим
Проводник
alignment
с этим тегом 3 элемента
14 сент. 2026 г.
Direct Preference Optimization (DPO)
dpo
alignment
preference-optimization
fine-tuning
14 сент. 2026 г.
Reinforcement Learning from Human Feedback (RLHF)
rlhf
alignment
post-training
machine-learning
14 сент. 2026 г.
_Training and Alignment Index
moc
training
post-training
alignment