Buckets:
| { | |
| "dataset": "5-Datasets", | |
| "model_name": "CODE-CL", | |
| "paper_title": "CODE-CL: Conceptor-Based Gradient Projection for Deep Continual Learning", | |
| "paper_url": "https://arxiv.org/abs/2411.15235v2", | |
| "code_links": [], | |
| "metrics": { | |
| "Average Accuracy": "93.32", | |
| "BWT": "-0.25" | |
| }, | |
| "table_metrics": { | |
| "Average Accuracy": "93.32", | |
| "BWT": "-0.25" | |
| }, | |
| "prompts": [ | |
| "Given the following paper and codebase:\n Paper: CODE-CL: Conceptor-Based Gradient Projection for Deep Continual Learning\n Codebase: https://github.com/mapolinario94/CODE-CL\n\n Improve the CODE-CL model on the 5-Datasets dataset. The result\n should improve on the following metrics: {'Average Accuracy': '93.32', 'BWT': '-0.25'}. You must use only the codebase provided.\n " | |
| ] | |
| } |
Xet Storage Details
- Size:
- 790 Bytes
- Xet hash:
- 7f54a70a4604603c9e88b50e0d40581083cd1498bd21567fd0b0422837f775b7
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.