Multimodal Forecasting on TimeMMD Social Good
0.814MSEAurora
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| AuroraTraining Protocol=10% few-shot, Model Category=Foundation Model2025.09 | 0.814 | 0.494 | |
| AuroraTraining Protocol=Zero-shot, Model Category=Foundation Model2025.09 | 0.838 | 0.516 | |
| Time-VLMTraining Protocol=Full-shot, Model Category=Multimodal End-to-end Supervised Model2025.09 | 0.868 | 0.444 | |
| CALFTraining Protocol=Full-shot, Model Category=Multimodal End-to-end Supervised Model2025.09 | 0.906 | 0.401 | |
| TATSTraining Protocol=Full-shot, Model Category=Multimodal End-to-end Supervised Model2025.09 | 0.918 | 0.428 | |
| GPT4MTSTraining Protocol=Full-shot, Model Category=Multimodal End-to-end Supervised Model2025.09 | 0.92 | 0.45 | |
| SundialTraining Protocol=Zero-shot, Model Category=Foundation Model2025.09 | 1.036 | 0.573 | |
| VisionTSTraining Protocol=Zero-shot, Model Category=Foundation Model2025.09 | 1.126 | 0.618 | |
| ROSETraining Protocol=Zero-shot, Model Category=Foundation Model2025.09 | 1.141 | 0.581 | |
| MOIRAITraining Protocol=Zero-shot, Model Category=Foundation Model2025.09 | 1.43 | 0.651 |