2406.11931     DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Cod Submitted 17 June, 2024; originally an
2609.19969     DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression        Submitted 17 September, 2026; original
2412.19437     DeepSeek-V3 Technical Report                                           Submitted 18 February, 2025; v1 submit
2405.04434     DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts La Submitted 19 June, 2024; v1 submitted 
2512.02556     DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models      Submitted 2 December, 2025; originally
2606.19348     DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligen Submitted 26 April, 2026; originally a
2501.12948     DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcem Submitted 3 January, 2026; v1 submitte
2401.02954     DeepSeek LLM: Scaling Open-Source Language Models with Longtermism     Submitted 5 January, 2024; originally 