TOY
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| MSI Completion | Toy MSI database | PSNR48.878 | 28 | |
| Sequential Recommendation | Toy | NDCG@54.38 | 18 | |
| Sequential Recommendation | Toy | NDCG@104.85 | 18 | |
| Explicit Attack | Toy | Avg Queries (E)500 | 17 | |
| Toy packing | Toy Unseen States (test) | Success Rate75.5 | 16 | |
| Rationalization | Toy (test) | HI-F176.02 | 12 | |
| Single-object generation | Toy4K | PSNR23.98 | 11 | |
| Sampling Time Series Super-Resolution (SSR) | Toy #2 | MSE0.016 | 8 | |
| 2d multi-goal | Toy | Recovery Time (%)3.2 | 8 | |
| Classification | Toy Synthetic Skew (test) | F1 Score99.93 | 7 | |
| Unsupervised point prediction | Toy | RMSE1.754 | 6 | |
| Classification | Toy (test) | F1 Score99.92 | 5 | |
| Generative Recommendation | Toy | NDCG@50.0341 | 4 | |
| Averaging Time Series Super-Resolution (ASR) | Toy #3 | MSE0.024 | 4 | |
| Averaging Time Series Super-Resolution (ASR) | Toy #1 | MSE0.013 | 4 | |
| Sampling Time Series Super-Resolution (SSR) | Toy #3 | MSE0.015 | 4 | |
| Sampling Time Series Super-Resolution (SSR) | Toy #1 | MSE0.008 | 4 | |
| State Estimation | Toy | RMSE78.03 | 4 | |
| Cell detection | TOY | AP @ IoU=0.5099.98 | 4 | |
| Set-level Attribution | Toy | Shape Accuracy100 | 3 | |
| Real2Sim Reconstruction and Interaction Prediction | Toy4K real-world experiment | Stability73.3 | 2 | |
| High-dimensional prediction | Toy-512 | Average Regret0.29 | 2 | |
| High-dimensional prediction | Toy-256 | Average Regret1.29 | 2 | |
| High-dimensional prediction | Toy-128 | Average Regret4.18 | 2 | |
| High-dimensional prediction | Toy-64 | Average Regret5.61 | 2 |
Showing 25 of 31 rows