LLaVA-Med-v1.0 (w/o LoRA, w/o extra data)

Reported on 3 benchmarks across 2 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision3 results

Image ClassificationonColonINST-v1 (Unseen)
Accuray· 2023-06-01
78.04
best: 83.24 (ColonGPT (w/ LoRA, w/o extra data))
LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day arXiv:2306.00890
Referring expression generationonColonINST-v1 (Unseen)
Accuray· 2023-06-01
75.07
best: 80.18 (ColonGPT (w/ LoRA, w/o extra data))
LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day arXiv:2306.00890
Referring expression generationonColonINST-v1 (Seen)
Accuray· 2023-06-01
97.74
best: 99.96 (ColonGPT (w/ LoRA, w/o extra data))
LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day arXiv:2306.00890