| DeepSeek-V3 Technical Report | Dec 27, 2024 | GPULanguage Modeling | CodeCode Available | 16 | 5 |
| Qwen2.5 Technical Report | Dec 19, 2024 | Common Sense Reasoning | CodeCode Available | 13 | 5 |
| Qwen2 Technical Report | Jul 15, 2024 | Arithmetic ReasoningGSM8K | CodeCode Available | 13 | 5 |
| DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence | Jun 17, 2024 | 16kLanguage Modeling | CodeCode Available | 9 | 5 |
| DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model | May 7, 2024 | Language ModelingLanguage Modelling | CodeCode Available | 9 | 5 |
| DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding | Dec 13, 2024 | Chart UnderstandingMixture-of-Experts | CodeCode Available | 9 | 5 |
| Turbo Sparse: Achieving LLM SOTA Performance with Minimal Activated Parameters | Jun 10, 2024 | Mixture-of-Experts | CodeCode Available | 9 | 5 |
| A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and Applications | Mar 10, 2025 | Continual LearningMeta-Learning | CodeCode Available | 9 | 5 |
| HiDream-I1: A High-Efficient Image Generative Foundation Model with Sparse Diffusion Transformer | May 28, 2025 | Image GenerationMixture-of-Experts | CodeCode Available | 7 | 5 |
| MoBA: Mixture of Block Attention for Long-Context LLMs | Feb 18, 2025 | Mixture-of-Experts | CodeCode Available | 7 | 5 |
| MiniMax-01: Scaling Foundation Models with Lightning Attention | Jan 14, 2025 | Mixture-of-Experts | CodeCode Available | 7 | 5 |
| MoE-LLaVA: Mixture of Experts for Large Vision-Language Models | Jan 29, 2024 | HallucinationMixture-of-Experts | CodeCode Available | 7 | 5 |
| MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention | Jun 16, 2025 | Mixture-of-ExpertsReinforcement Learning (RL) | CodeCode Available | 7 | 5 |
| Revisiting MoE and Dense Speed-Accuracy Comparisons for LLM Training | May 23, 2024 | GSM8KMixture-of-Experts | CodeCode Available | 7 | 5 |
| Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent | Nov 4, 2024 | Logical ReasoningMathematical Problem-Solving | CodeCode Available | 5 | 5 |
| Chatlaw: A Multi-Agent Collaborative Legal Assistant with Knowledge Graph Enhanced Mixture-of-Experts Large Language Model | Jun 28, 2023 | HallucinationKnowledge Graphs | CodeCode Available | 5 | 5 |
| Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts | Jun 18, 2024 | Language ModelingLanguage Modelling | CodeCode Available | 5 | 5 |
| Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts | Oct 14, 2024 | Mixture-of-ExpertsTime Series | CodeCode Available | 5 | 5 |
| DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models | Jan 11, 2024 | Language ModellingLarge Language Model | CodeCode Available | 5 | 5 |
| Kimi-VL Technical Report | Apr 10, 2025 | Long-Context UnderstandingMathematical Reasoning | CodeCode Available | 5 | 5 |
| OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models | Jan 29, 2024 | DecoderMixture-of-Experts | CodeCode Available | 5 | 5 |
| LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training | Jun 24, 2024 | Mixture-of-Experts | CodeCode Available | 5 | 5 |
| Jamba-1.5: Hybrid Transformer-Mamba Models at Scale | Aug 22, 2024 | ChatbotInstruction Following | CodeCode Available | 5 | 5 |
| Aria: An Open Multimodal Native Mixture-of-Experts Model | Oct 8, 2024 | Instruction FollowingMixture-of-Experts | CodeCode Available | 5 | 5 |
| Comet: Fine-grained Computation-communication Overlapping for Mixture-of-Experts | Feb 27, 2025 | Computational EfficiencyGPU | CodeCode Available | 5 | 5 |
