Med
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Finding target T_uniform | MeD | Average Similarity1 | 25 | |
| Data Leakage Attack | Med | AP (alpha=0.5)92.5 | 24 | |
| Speculative Decoding | Med | Throughput (tokens/s)128.51 | 22 | |
| Question Answering | med02 | RL Score0.19 | 14 | |
| Continual Semantic Segmentation | Med Semi-Supervised-JASCL | Session 0 Dice Score73.6 | 9 | |
| Author Disambiguation | Med | MRR87.1 | 9 | |
| Paper-Venue Prediction | Med | NDCG0.446 | 9 | |
| Paper-Field (L2) Classification | Med | NDCG38.4 | 9 | |
| Paper-Field (L1) Classification | Med | NDCG70.9 | 9 | |
| Retrieval Efficiency | Med. | Retrieved Tokens23,657 | 8 | |
| Clustering | MED | Purity0.59 | 6 | |
| Finding target quiz distribution | MeD | Average Iterations17 | 5 | |
| Machine Translation | Med. En-De out-of-domain WMT14 (test) | BLEU30.8 | 5 | |
| Natural Language Inference | MED (test) | Upward Acc91.4 | 5 | |
| Traveling Salesman Problem | Med Small (test) | Solution Gap (%)1.113 | 2 |
Showing 15 of 15 rows