#reinforcement-learning

총 2건 · 1/1 페이지

전체 24시간 7일 30일

전체 🇰🇷 한국어 본문

Sebastian Raschka · 2025-12-03 제목번역

DeepSeek V3에서 V3.2로: 아키텍처, 희소 주의, 강화학습 업데이트

From DeepSeek V3 to V3.2: Architecture, Sparse Attention, and RL Updates

Understanding How DeepSeek's Flagship Open-Weight Models Evolved

#reinforcement-learning #llm-architecture #deepseek-v3 #sparse-attention #open-weight-models #model-evolution
Sebastian Raschka · 2025-04-19 제목번역

LLM 추론을 위한 강화학습의 현황

The State of Reinforcement Learning for LLM Reasoning

Understanding GRPO and New Insights from Reasoning Model Papers

#language-models #reinforcement-learning #machine-learning #llm-reasoning #grpo #neural-networks