| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Humor Generation | Electronic Sheep (test) | Visual Understanding Avg Rank1.8 | 8 | |
| Multimodal humor captioning | Electronic sheep | Mean Human Rating3.31 | 7 | |
| Humor Generation | Electronic sheep | Mean Score3.31 | 7 | |
| Funny Caption Generation | Electronic Sheep (test) | p-value0 | 7 | |
| Caption Generation | Electronic Sheep | 1-gram Overlap72 | 5 |