Ensembling
Mixture of Experts
Introduced by Kanwal et al. in Equipping Computational Pathology Systems with Artifact Processing Pipelines: A Showcase for Computation and Performance Trade-offsPapers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Language Modelling | 33 | 6.67% |
| Computational Efficiency | 30 | 6.06% |
| Language Modeling | 28 | 5.66% |
| Large Language Model | 15 | 3.03% |
| Quantization | 14 | 2.83% |
| Multi-Task Learning | 13 | 2.63% |
| Image Classification | 12 | 2.42% |
| parameter-efficient fine-tuning | 12 | 2.42% |
| Question Answering | 10 | 2.02% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
