Datasets for SketchVLM: Vision-Language Models Can Annotate Images to Explain Thoughts and Guide Users
(https://sketchvlm.github.io/)
-
loganbolton/sketchvlm-physics-ball-drop
Viewer • Updated • 198 -
loganbolton/sketchvlm-maze-navigation
Viewer • Updated • 200 -
SketchVLM: Vision language models can annotate images to explain thoughts and guide users
Paper • 2604.22875 • Published • 27 -
loganbolton/sketchvlm-connect-dots
Viewer • Updated • 100
