MolmoPoint: Better pointing architecture for vision-language models

Jul 11, 2026

MolmoPoint is a new vision-language model architecture that replaces text-based coordinate outputs with a token-based pointing mechanism, allowing the model to directly select regions from visual features. This approach is designed to make pointing more natural and accurate.

Why it matters: This architecture could improve how vision-language models interact with visual content by enabling more precise and intuitive region selection.

Full story at: Allen Institute for AI ↗