Personalized Image Captioning on Personalized Vision-Language Dataset Multi 1.0 (test)
0.602GPT-ScoreMC-LLaVA
Evaluation results
| Method | Links | |
|---|---|---|
| MC-LLaVATokens=10^12024.11 | 0.602 | |
| Yo'LLaVA-MTokens=10^12024.11 | 0.389 |
| Method | Links | |
|---|---|---|
| MC-LLaVATokens=10^12024.11 | 0.602 | |
| Yo'LLaVA-MTokens=10^12024.11 | 0.389 |