World to Code: Multi-modal Data Generation via Self-Instructed Compositional Captioning and Filtering

Add code
Sep 30, 2024
Figure 1 for World to Code: Multi-modal Data Generation via Self-Instructed Compositional Captioning and Filtering
Figure 2 for World to Code: Multi-modal Data Generation via Self-Instructed Compositional Captioning and Filtering
Figure 3 for World to Code: Multi-modal Data Generation via Self-Instructed Compositional Captioning and Filtering
Figure 4 for World to Code: Multi-modal Data Generation via Self-Instructed Compositional Captioning and Filtering

Share this with someone who'll enjoy it:

View paper onarxiv icon

Share this with someone who'll enjoy it: