Zzong's Notes
Search
검색
다크 모드
라이트 모드
방문
탐색기
Home
❯
생성형 AI
❯
Post Training
Post Training
노트 편집 ↗
노트 12개
alignment tax
generative_model
Decoupled Clip and Dynamic sAmpling Policy Optimization
LLM
reinforcement_learning
post_training
RLVR
policy_optimization
ByteDance
DPO
LLM
Generalized Knowledge Distillation
LLM
distillation
Group Relative Policy Optimization
reinforcement_learning
LLM
Group Sequence Policy Optimization
LLM
reinforcement_learning
post_training
RLVR
policy_optimization
Qwen
On-Policy Distillation
LLM
distillation
alignment
generative_ai
Proximal Policy Optimization
reinforcement_learning
LLM
reward model
RLHF
LLM
reinforcement_learning
supervised fine-tuning
deep_learning
LLM
generative_ai
alignment
자연스러운 한국어를 위한 LLM Post-Training
LLM
post_training
alignment
instruction_tuning
korean