#Vision Language Models (VLMs)

AI2's Molmo2 VLM brings pixel-perfect grounding to open video

Molmo2 VLM from AI2 establishes a new state of the art for open-source video understanding by introducing precise spatio-temporal grounding capabilities.

PhysBrain model uses human video to teach robots physical intelligence

Agentic AI Computer Vision Transforms Visual Intelligence

Level 4 Autonomous Driving Nears Commercial Reality

NVIDIA's New Approach to Teaching AI Reasoning for Physical World

NVIDIA's Cosmos Reason model is pioneering a new era of AI by teaching it physical common sense through human-curated data, making robots and autonomous vehicles safer and more reliable.

Apple's FastVLM Targets More Efficient Vision-Language AI

Apple has quietly unveiled a new machine learning initiative, FastVLM, aimed at significantly improving the efficiency of vision language models (VLMs). FastVLM could unlock a new generation of responsive, privacy-preserving AI experiences that are deeply integrated into Apple’s hardware ecosystem.