All content for Embodied AI 101 is the property of Shaoqing Tan and is served directly from their servers
with no modification, redirects, or rehosting. The podcast is not affiliated with or endorsed by Podjoint in any way.
Stay in the loop on research in AI and physical intelligence.
Episode 24: DINOv3 and the Next Generation of Visual Foundation Models
Embodied AI 101
46 minutes 30 seconds
2 months ago
Episode 24: DINOv3 and the Next Generation of Visual Foundation Models
Hello and welcome to Embodied AI 101. Today, we dive into a critical review of DINOv3, a 2025 vision model from Meta AI that marks a major step toward general-purpose visual foundation models. If you’re an AI professional or researcher with an eye on vision-language models (and maybe a toe in robotics), this episode is for you. We’ll explore how DINOv3 fits into the broader movement toward massive-scale, task-agnostic representation learners – models trained not for one narrow task, but to b
Embodied AI 101
Stay in the loop on research in AI and physical intelligence.
