Multi-modal Evaluation on Vision-Centric
56Average ScoreJARVIS
Evaluation Results
| Method | Links | |
|---|---|---|
| JARVISLLM=Qwen2-7B2025.12 | 56 | |
| LLaVALLM=Qwen2-7B2025.12 | 55.3 | |
| Ours w/o MaskingLLM=Qwen2-7B2025.12 | 54.3 | |
| VIRALLLM=Qwen2-7B2025.12 | 53.5 | |
| JARVISLLM=Vicuna-7B2025.12 | 51.7 | |
| LLaVALLM=Vicuna-7B2025.12 | 50.9 | |
| Ours w/o MaskingLLM=Vicuna-7B2025.12 | 49 | |
| VIRALLLM=Vicuna-7B2025.12 | 48.7 |