Multi-robot cooperative Visual Question Answering on CoopSR Habitat
57.78Success Rate (T1)SP-CoR
Evaluation Results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| SP-CoRBase Model=InternVL3-8B2026.05 | 57.78 | 78.31 | 56.98 | 74.96 | 77.07 | 68.07 | 65.37 | 69.99 | |
| SP-CoRBase Model=Qwen3-VL-8B-Instruct2026.05 | 57.2 | 78.14 | 58.38 | 74.54 | 78.28 | 67.32 | 65.31 | 70.11 | |
| SP-CoRBase Model=Qwen2.5-VL-7B-Instruct2026.05 | 55.36 | 78.72 | 59.36 | 74.94 | 78.26 | 67.34 | 66.6 | 70.55 | |
| EgoRAGEvaluation Protocol=RAG, Base Model=Qwen2.5-VL-7B-Instruct2026.05 | 48.31 | 74.93 | 51.8 | 71.36 | 73.51 | 63.61 | 60.37 | 65.63 | |
| Qwen2.5-VL-7BEvaluation Protocol=SFT2026.05 | 46.67 | 76.3 | 53.02 | 72.53 | 75.04 | 63.82 | 61.77 | 66.68 | |
| Qwen2.5-VL-72BEvaluation Protocol=SFT2026.05 | 43.96 | 74.47 | 49.9 | 68.66 | 71.05 | 60.88 | 59.56 | 63.65 | |
| TSPOEvaluation Protocol=Keyframe, Base Model=InternVL3-8B2026.05 | 42.51 | 76.21 | 50.77 | 70.79 | 72.21 | 63.25 | 60.35 | 65.09 | |
| EgoRAGEvaluation Protocol=RAG, Base Model=InternVL3-8B2026.05 | 39.9 | 74.71 | 47.4 | 68.47 | 69.77 | 60.67 | 58.2 | 62.7 | |
| VideoRAGEvaluation Protocol=RAG, Base Model=Qwen2.5-VL-7B-Instruct2026.05 | 39.13 | 76.52 | 51.08 | 71.37 | 71.34 | 63.19 | 61.68 | 65.25 | |
| InternVL3-8BEvaluation Protocol=SFT2026.05 | 39.03 | 75.51 | 47.6 | 68.97 | 69.86 | 61.76 | 58.25 | 63.12 | |
| TSPOEvaluation Protocol=Keyframe, Base Model=Qwen2.5-VL-7B-Instruct2026.05 | 37.97 | 75.8 | 46.68 | 68.55 | 69.28 | 61.44 | 57.94 | 62.72 | |
| Qwen3-VL-8B-InstructEvaluation Protocol=SFT2026.05 | 30.53 | 67.83 | 46.83 | 67.55 | 65.95 | 57.9 | 55.49 | 59.62 | |
| LLaVA-NeXT-Video-7BEvaluation Protocol=Zero-shot2026.05 | 26.76 | 36.35 | 33.3 | 27.09 | 31.82 | 31.49 | 30.57 | 31.27 | |
| VideoLLaMA3-7BEvaluation Protocol=Zero-shot2026.05 | 23.96 | 44.59 | 37.86 | 44.03 | 40.84 | 42.16 | 40.52 | 41.17 | |
| Qwen2.5-VL-7B-InstructEvaluation Protocol=Zero-shot2026.05 | 23.57 | 39.61 | 28.4 | 34.35 | 34.66 | 34.99 | 31.03 | 33.51 | |
| VideoRAGEvaluation Protocol=RAG, Base Model=InternVL3-8B2026.05 | 22.03 | 72.92 | 45.46 | 67 | 66.69 | 57.92 | 55.53 | 59.88 | |
| VideoLLaMA3-2BEvaluation Protocol=Zero-shot2026.05 | 21.26 | 41.69 | 35.1 | 37.83 | 33.77 | 38.02 | 39.08 | 37.04 | |
| LLaVA-NeXT-Video-7BEvaluation Protocol=SFT2026.05 | 20.97 | 55.43 | 47.35 | 49.25 | 56.19 | 50.91 | 48.42 | 51.72 | |
| InternVL3-8BEvaluation Protocol=Zero-shot2026.05 | 20.77 | 49.86 | 36.08 | 43.01 | 41.03 | 42.04 | 41.57 | 41.56 | |
| Qwen3-VL-8B-InstructEvaluation Protocol=Zero-shot2026.05 | 20.77 | 45.65 | 37.32 | 39.25 | 42.18 | 39.35 | 36.46 | 39.24 | |
| VideoLLaMA3-2BEvaluation Protocol=SFT2026.05 | 20.68 | 59.42 | 42.63 | 63.6 | 61.09 | 52.4 | 48.92 | 53.95 | |
| KTVEvaluation Protocol=Keyframe, Base Model=Qwen2.5-VL-7B-Instruct2026.05 | 19.71 | 52.32 | 41.68 | 57.11 | 50.56 | 49.63 | 47.33 | 49.13 | |
| VideoLLaMA3-7BEvaluation Protocol=SFT2026.05 | 19.52 | 62.58 | 42.91 | 63.22 | 61.66 | 53.06 | 49.85 | 54.68 | |
| KTVEvaluation Protocol=Keyframe, Base Model=InternVL3-8B2026.05 | 19.13 | 61.43 | 40.26 | 62.95 | 60.6 | 51.92 | 48.61 | 53.53 | |
| Qwen2.5-VL-72B-InstructEvaluation Protocol=Zero-shot2026.05 | 18.84 | 43.57 | 19.82 | 33.61 | 30.91 | 33.18 | 31.15 | 31.75 |