Command Palette
Search for a command to run...
Visual Question Answering On Vqa V2 1
Metrics
Accuracy
Results
Performance results of various models on this benchmark
| Paper Title | Repository | ||
|---|---|---|---|
| RLHF-V | 80 | RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback | |
| Emu-I * | 57.5 | Emu: Generative Pretraining in Multimodality |
0 of 2 row(s) selected.