Ai2 @ai2.bsky.social · 18/03/2026MolmoPoint takes a different approach. Instead of writing coordinates, the model points by selecting from the visual tokens it's already looking at—like the difference between reading out "position 347, 582" and tapping directly on a touchscreen. 120 0
Ai2 @ai2.bsky.social · 18/03/2026MolmoPoint works in three steps using special grounding tokens: 1️⃣ Pick a rough region of the image/video that contains the target 2️⃣ Zoom in to a smaller area using finer visual features 3️⃣ Pinpoint the exact pixel-level location within that area 110 0
Ai2 @ai2.bsky.social · 18/03/2026MolmoPoint sets a new SOTA on image pointing and leads among open models on GUI grounding 📷New SOTA on PointBench (70.7%) & PixMo-Points (89.2 F1) 🖥️Best GUI grounding among top open models on ScreenSpot-Pro & OSWorldG 🎥Preferred by human evaluators 59.1% of the time on video 130 0
