Reasoning VLM for Physical AI - Natalia Segal - NVIDIA

Why watch

Natalia Segal from NVIDIA explains how Reasoning Vision Language Models (VLMs) enable Physical AI systems to perceive, reason about, and interact with physical environments. This talk covers the intersection of VLMs with robotics and embodied AI, targeting developers and researchers working on intelligent robotic systems. The presentation is part of dotAI 2025 conference.