2025
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.
CoRR, January, 2025

2024
DeepSeek-V3 Technical Report.
CoRR, 2024

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model.
CoRR, 2024

2020
A Non-Linear Correction Method for Terahertz LFMCW Radar.
IEEE Access, 2020