| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multimodal Conversational Question Answering | MMCoQA | ROUGE-L38 | 21 | |
| End-to-end Question Answering | MMCoQA (test) | EM36.31 | 7 | |
| Retrieval | MMCoQA | Recall@355.8 | 6 | |
| Multimodal Retrieval | MMCOQA Doc (test) | Total Time (ms)362 | 5 |