| Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models | Apr 16, 2024 | image-classificationImage Classification | CodeCode Available | 2 |
| MoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery Detection | Apr 12, 2024 | Mixture-of-Experts | CodeCode Available | 2 |
| Multi-Task Dense Prediction via Mixture of Low-Rank Experts | Mar 26, 2024 | DecoderMixture-of-Experts | CodeCode Available | 2 |
| Task-Customized Mixture of Adapters for General Image Fusion | Mar 19, 2024 | Mixture-of-Experts | CodeCode Available | 2 |
| Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation | Mar 18, 2024 | Mixture-of-Expertsparameter-efficient fine-tuning | CodeCode Available | 2 |
| Switch Diffusion Transformer: Synergizing Denoising Tasks with Sparse Mixture-of-Experts | Mar 14, 2024 | DenoisingMixture-of-Experts | CodeCode Available | 2 |
| Scattered Mixture-of-Experts Implementation | Mar 13, 2024 | Mixture-of-Experts | CodeCode Available | 2 |
| Harder Tasks Need More Experts: Dynamic Routing in MoE Models | Mar 12, 2024 | Computational EfficiencyMixture-of-Experts | CodeCode Available | 2 |
| TESTAM: A Time-Enhanced Spatio-Temporal Attention Model with Mixture of Experts | Mar 5, 2024 | Graph AttentionGraph Embedding | CodeCode Available | 2 |
| Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models | Feb 22, 2024 | AllMixture-of-Experts | CodeCode Available | 2 |
