Visual Question Answering on LLaVA-Bench LLaVAW
89.1ScoreLLaVA-VT
Evaluation Results
| Method | Links | |
|---|---|---|
| LLaVA-VTLLM=Vicuna-13B, #PT=558K, #IT=665K, Representation=E + T2024.03 | 89.1 | |
| LLaVA-CapLLM=Vicuna-13B, #PT=558K, #IT=665K, Representation=E + T2024.03 | 88.9 | |
| LLaVA-SGLLM=Vicuna-13B, #PT=558K, #IT=665K, Representation=E + T2024.03 | 86.8 | |
| LLaVA-1.5 (V-13B)LLM=Vicuna-13B, #PT=558K, #IT=665K, Representation=Visual Embeddings (E)2024.03 | 86.7 | |
| LLaVA-DCapLLM=Vicuna-13B, #PT=558K, #IT=665K, Representation=E + T2024.03 | 86.4 | |
| Vicuna-VTLLM=Vicuna-13B, #IT=665K, Representation=Text (T)2024.03 | 82.5 | |
| LLaVA-1.5 (V-7B)LLM=Vicuna-7B, #PT=558K, #IT=665K, Representation=Visual Embeddings (E)2024.03 | 81.9 | |
| Vicuna-CapLLM=Vicuna-13B, #IT=665K, Representation=Text (T)2024.03 | 79.2 | |
| Vicuna-DCapLLM=Vicuna-13B, #IT=665K, Representation=Text (T)2024.03 | 77.6 | |
| Vicuna-SGLLM=Vicuna-13B, #IT=665K, Representation=Text (T)2024.03 | 77 |