Vision-Language Task on ScienceQA
63.56AccuracyBaseline
Evaluation results
| Method | Links | |
|---|---|---|
| BaselineBackbone=ViT-L/16, PT Method=Baseline, Fine-tuning Protocol=LoRA-based LLaVA-1.5-7B [41]2026.04 | 63.56 | |
| CoM-PTBackbone=ViT-L/16, PT Method=CoM-PT, Fine-tuning Protocol=LoRA-based LLaVA-1.5-7B [41]2026.04 | 63.51 | |
| CoM-PTBackbone=ViT-B/16, PT Method=CoM-PT, Fine-tuning Protocol=LoRA-based LLaVA-1.5-7B [41]2026.04 | 63.41 | |
| BaselineBackbone=ViT-B/16, PT Method=Baseline, Fine-tuning Protocol=LoRA-based LLaVA-1.5-7B [41]2026.04 | 62.57 |