Visual Question Answering On Vqa V2 1
Metriken
Accuracy
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Modellname | Accuracy | Paper Title | Repository |
|---|---|---|---|
| Emu-I * | 57.5 | Emu: Generative Pretraining in Multimodality | |
| RLHF-V | 80 | RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback |
0 of 2 row(s) selected.