[Paper Review] Chain-of-Thought의 진화

작성자: dlwldjs 작성일: 2026-05-20 08:32 조회: 23

1. 논문 제목
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

2. Overview
1. 논문 제목 = DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning 링크 = https://www.themoonlight.io/paper/66622afa-dd2b-4374-ac5f-5172af58b0d6 논문 제목 = STaR: Self-Taught Reasoner Bootstrapping Reasoning With Reasoning 링크 = https://www.themoonlight.io/paper/913196fd-767c-4b04-8c07-0372d7e302f3

3. 발표자 · 첨부파일
발표자: 이지언
발표형식: 세미나
발표일자: 2026-06-19
ds.pptx

목록