Research
Tasks
Explore the problems researchers are working on and the benchmarks used to measure progress.
2,537 tasksPage 57 of 102
Tasks
| Task | Domain | Benchmarks | Papers | Last update |
|---|---|---|---|---|
| Try-on editing | 1 | 1 | Feb 18, 2026 | |
| Object Retexture | 1 | 1 | Feb 20, 2026 | |
| 360° Image Synthesis | 1 | 1 | Feb 18, 2026 | |
| Image-to-Video-Motion | 1 | 1 | Feb 20, 2026 | |
| Text-Prompt Editing | 1 | 1 | Feb 20, 2026 | |
| Visual-Prompt Editing | 1 | 1 | Feb 20, 2026 | |
| Scenario Synthesis | 1 | 1 | Feb 20, 2026 | |
| Image generation refinement | 1 | 1 | Feb 20, 2026 | |
| Image Co-creation Evaluation | 1 | 1 | Feb 20, 2026 | |
| Image Diversity Coverage | 1 | 1 | Feb 20, 2026 | |
| Cross-modal Generation | 1 | 1 | Feb 20, 2026 | |
| T2I Align | 1 | 1 | Feb 21, 2026 | |
| Semantic Synthesis | 1 | 2 | Feb 27, 2026 | |
| Semantic Image Editing (Angry) | 1 | 1 | Feb 21, 2026 | |
| Semantic Image Editing (Sleepy) | 1 | 1 | Feb 21, 2026 | |
| Semantic Image Editing (Smiling) | 1 | 1 | Feb 21, 2026 | |
| Semantic Image Editing (Puppy-like) | 1 | 1 | Feb 21, 2026 | |
| Content Dragging | 1 | 1 | Feb 18, 2026 | |
| Semantic Editing | 1 | 1 | Feb 21, 2026 | |
| Multimodal Image Synthesis | 1 | 1 | Feb 25, 2026 | |
| Many-to-one Image Generation ((T+A) → I) | 1 | 1 | Feb 21, 2026 | |
| Text-to-(Image+Audio) Generation | 1 | 1 | Feb 21, 2026 | |
| Image-to-(Text+Audio) Generation | 1 | 1 | Feb 21, 2026 | |
| Audio-to-(Text+Image) Generation | 1 | 1 | Feb 21, 2026 | |
| Photo Synthesis | 1 | 1 | Feb 18, 2026 |