Dimensions overall score 7.0

GitHub Code Pulse

No public code linked for this paper yet.

• MolmoPoint sets a new state-of-the-art on image pointing with 70.7% accuracy on PointBench.result 95%
• MolmoPoint-GUI-8B sets a new state-of-the-art among fully open models on GUI pointing with 61.1% accuracy on ScreenSpotPro.result 90%
• MolmoPoint improves video pointing with a 59.1% human preference win rate versus a text coordinate baseline.result 90%
• MolmoPoint's pointing mechanism directly selects visual tokens containing the target concept instead of generating coordinates, which is more intuitive and reduces token count.method 85%
• MolmoPoint uses a three-stage refinement process: a pointing token selects a coarse patch, a subpatch token refines within it, and a location token specifies the final point.technical 80%
• The MolmoPoint-GUISyn dataset provides extremely dense annotations with 54 points per image on average, enabling efficient training via message trees.technical 85%
• MolmoPoint achieves higher sample efficiency compared to coordinate-based pointing methods.result 75%
• Existing VLM pointing methods that generate coordinates require learning a complicated coordinate system and result in high token count.limitation 80%

Competitive landscape

Competitor map is still being generated for this paper. Enable generation or check back soon.

Startup potential card