Publications (13)
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
DeepSeek-AI, Aixin Liu, Bei Feng +154
We present DeepSeek-V2, a strong Mixture-of-Experts (MoE) language model characterized by economical training and efficient inference. It comprises 236B total parameters, of which…
DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation
Xin Cheng, Xingkai Yu, Chenze Shao +30
Speculative decoding accelerates Large Language Model (LLM) inference by decoupling draft generation from target verification. While recent parallel drafters efficiently propose lo…
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
Xin Cheng, Rui Tian, Wangding Zeng +18
While Mixture-of-Experts (MoE) scales capacity via conditional computation, Transformers lack a native primitive for knowledge lookup, forcing them to inefficiently simulate retrie…
DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
Zhiyu Wu, Xiaokang Chen, Zizheng Pan +24
We present DeepSeek-VL2, an advanced series of large Mixture-of-Experts (MoE) Vision-Language Models that significantly improves upon its predecessor, DeepSeek-VL, through two key…
DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models
Damai Dai, Chengqi Deng, Chenggang Zhao +14
In the era of large language models, Mixture-of-Experts (MoE) is a promising architecture for managing computational costs when scaling up model parameters. However, conventional M…
DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
DeepSeek-AI, Anyi Xu, Bangcai Lin +315
We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models -- DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSe…
Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling
Xiaokang Chen, Zhiyu Wu, Xingchao Liu +5
In this work, we introduce Janus-Pro, an advanced version of the previous work Janus. Specifically, Janus-Pro incorporates (1) an optimized training strategy, (2) expanded training…
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
DeepSeek-AI, Daya Guo, Dejian Yang +195
General reasoning represents a long-standing and formidable challenge in artificial intelligence. Recent breakthroughs, exemplified by large language models (LLMs) and chain-of-tho…
DeepSeek-V3 Technical Report
DeepSeek-AI, Aixin Liu, Bei Feng +195
We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. To achieve efficient inference and cost-effec…
Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation
Chengyue Wu, Xiaokang Chen, Zhiyu Wu +8
In this paper, we introduce Janus, an autoregressive framework that unifies multimodal understanding and generation. Prior research often relies on a single visual encoder for both…
DeepSeek LLM: Scaling Open-Source Language Models with Longtermism
DeepSeek-AI, :, Xiao Bi +85
The rapid development of open-source large language models (LLMs) has been truly remarkable. However, the scaling law described in previous literature presents varying conclusions,…
Robust Kalman filters with unknown covariance of multiplicative noise
Xingkai Yu, Ziyang Meng
In this paper, state and noise covariance estimation problems for linear system with unknown multiplicative noise are considered. The measurement likelihood is modelled as a mixtur…
DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
DeepSeek-AI, Aixin Liu, Aoxue Mei +260
We introduce DeepSeek-V3.2, a model that harmonizes high computational efficiency with superior reasoning and agent performance. The key technical breakthroughs of DeepSeek-V3.2 ar…