Paper

Paper

About Docs Changelog Terms Privacy Support

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs v... | ResearchHub

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

By

DeepSeek-AI DeepSeek-AI

DeepSeek-AI DeepSeek-AI·Daya Guo·Sansan Li

Preprint

January 22, 2025

16

Paper

Paper

About Docs Changelog Terms Privacy Support

Sign in to review

Share your thoughts on this paper...

Journal

arXiv (Cornell University)

Peer Reviews

about 1 year ago

Topics

#computer-science #artificial-intelligence #psychology #cognitive-science #social-psychology

DOI

10.48550/arxiv.2501.12948

Other Formats