| 3d-question-answering-3d-qa-on-scanqa-test-w | LL3DA | #16 | BLEU-4: 13.5ROUGE: 37.3METEOR: 15.9CIDEr: 76.8 |
| image-classification-on-coloninst-v1-seen | LLaVA-v1 (w/ LoRA, w/ extra data) | #15 | Accuray: 89.61 |
| image-classification-on-coloninst-v1-seen | LLaVA-v1 (w/ LoRA, w/o extra data) | #16 | Accuray: 87.86 |
| image-classification-on-coloninst-v1-unseen | LLaVA-v1
(w/ LoRA, w/o extra data) | #15 | Accuray: 72.08 |
| image-classification-on-coloninst-v1-unseen | LLaVA-v1
(w/ LoRA, w/ extra data) | #17 | Accuray: 42.17 |
| mmr-total-on-mrr-benchmark | LLaVA-NEXT-34B | #2 | Total Column Score: 412 |
| mmr-total-on-mrr-benchmark | LLaVA-NEXT-13B | #5 | Total Column Score: 335 |
| mmr-total-on-mrr-benchmark | LLaVA-1.5-13B | #7 | Total Column Score: 243 |
| referring-expression-generation-on-coloninst | LLaVA-v1
(w/ LoRA, w/ extra data) | #16 | Accuray: 86.87 |
| referring-expression-generation-on-coloninst | LLaVA-v1
(w/ LoRA, w/o extra data) | #17 | Accuray: 84.55 |
| referring-expression-generation-on-coloninst-1 | LLaVA-v1
(w/ LoRA, w/o extra data) | #16 | Accuray: 68.11 |
| referring-expression-generation-on-coloninst-1 | LLaVA-v1
(w/ LoRA, w/ extra data) | #17 | Accuray: 46.85 |
| spatial-reasoning-on-embspatial-bench | LLaVA-1.6 | #4 | Generation: 35.19 |
| video-question-answering-on-mvbench | LLaVa | #17 | Avg.: 36.0 |
| visual-question-answering-on-benchlmm | LLaVA-1.5-7B | #4 | GPT-3.5 score: 46.83 |
| visual-question-answering-on-benchlmm | LLaVA-1-13B | #7 | GPT-3.5 score: 43.50 |