Rating Prediction on Amazon Instant Video 5-core (test)
0.6204MAEREVLoRA (Llama 1B)
Evaluation results
| Method | Links | ||
|---|---|---|---|
| REVLoRA (Llama 1B)Evaluation Protocol=Fine-Tuned, Model Backbone=Llama 1B, Optimization Loss=MAE2025.12 | 0.6204 | 1.0216 | |
| REVLoRA (Qwen 0.5B)Evaluation Protocol=Fine-Tuned, Model Backbone=Qwen 0.5B, Optimization Loss=MAE2025.12 | 0.627 | 1.0171 | |
| RGCLEvaluation Protocol=Deep Learning2025.12 | 0.6929 | 0.934 | |
| DIRECTEvaluation Protocol=Deep Learning2025.12 | 0.6938 | 0.881 | |
| REVLoRA (Llama 1B MSE)Evaluation Protocol=Fine-Tuned, Model Backbone=Llama 1B, Optimization Loss=MSE2025.12 | 0.7012 | 0.9105 | |
| Qwen 3BEvaluation Protocol=Zero-Shot, Model Backbone=Qwen 2.5 3B2025.12 | 0.7037 | 1.2922 | |
| Qwen 0.5BEvaluation Protocol=Few-Shot, Shot-count=3-shot, Model Backbone=Qwen 2.5 0.5B2025.12 | 0.7113 | 1.3913 | |
| Llama 3BEvaluation Protocol=Zero-Shot, Model Backbone=Llama 3.2 3B2025.12 | 0.7158 | 1.4559 | |
| Qwen 3BEvaluation Protocol=Few-Shot, Shot-count=3-shot, Model Backbone=Qwen 2.5 3B2025.12 | 0.7257 | 1.4912 | |
| Qwen 0.5BEvaluation Protocol=Zero-Shot, Model Backbone=Qwen 2.5 0.5B2025.12 | 0.742 | 1.2003 | |
| Llama 1BEvaluation Protocol=Zero-Shot, Model Backbone=Llama 3.2 1B2025.12 | 0.7425 | 1.5707 | |
| LURPEvaluation Protocol=Few-Shot, Shot-count=3-shot2025.12 | 0.7425 | 1.6119 | |
| Llama 3BEvaluation Protocol=Few-Shot, Shot-count=3-shot, Model Backbone=Llama 3.2 3B2025.12 | 0.7439 | 1.676 | |
| Llama 1BEvaluation Protocol=Few-Shot, Shot-count=3-shot, Model Backbone=Llama 3.2 1B2025.12 | 0.8558 | 1.8853 | |
| DeepCoNNEvaluation Protocol=Deep Learning2025.12 | 0.9331 | 1.3132 |