-
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Paper • 2501.12948 • Published • 402 -
DeepSeek-V3 Technical Report
Paper • 2412.19437 • Published • 64 -
DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
Paper • 2412.10302 • Published • 18 -
DeepSeek-VL: Towards Real-World Vision-Language Understanding
Paper • 2403.05525 • Published • 47

DeepSeek Research
community
AI & ML interests
A community of DeepSeek, dedicated to exploring and building DeepSeek AI models.
Recent Activity
Organization Card
DeepSeek (深度求索), founded in 2023, is a Chinese company dedicated to making AGI a reality.
Unravel the mystery of AGI with curiosity. Answer the essential question with long-termism.
This is an open, community-driven space for exploring and building DeepSeek AI models. While it's not officially affiliated with the DeepSeek organization, it serves as an independent research hub dedicated to advancing DeepSeek’s vision. Anyone passionate about DeepSeek can join, learn, share ideas, and contribute. Send a join request to be part of it!
Collections
1
models
0
None public yet
datasets
0
None public yet