Molmo 2 | Counting objects and actions

From Ai2

Researcher Zixin Ma demonstrates Molmo 2's counting capabilities. Molmo 2 is a state-of-the-art open multimodal model suite capable of precise spatial and temporal understanding of video, image, and multi-image sets. Building on the global impact of Molmo, which pioneered image pointing for multimodal AI systems, Molmo 2 introduces breakthrough capabilities in video pointing, multi-frame reasoning, and object tracking. Learn more: allenai.org/molmo Discuss in Discord: http://discord.gg/ai2