[논문리뷰] DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Overview

논문명: DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
학회(출판연도): arXiv, Nature (2025)
연구분야: LLM, Reasoning, Reinforcement Learning, Chain-of-Thought, Large Language Models

발표 자료: https://canva.link/5illk8xhlgr7kh4