TAI x MLT Collab: Embodied AI: From Seeing to Imagining to Doing

[cross-posting] TAI is organizing an exciting in-person event: Join us for an evening exploring how modern robots and physical agents connect perception to action, from understanding the world to taking purposeful steps within it. We’ll trace the evolution of embodied AI through three lenses:

🔹 Seeing (VLMs): Language as an interface between humans and machines - Roland Meertens (Wayve)

🔹 Imagining (World Models): Predictive world representations for planning and reasoning - Alisher Abdulkhaev (Kanaria Tech)

🔹 Doing (VLAs): Turning perception and language into real-world behavior - Motonari Kambara (Keio University)

If you’re curious about the next generation of embodied intelligence, this is an event you won’t want to miss.

👉 Register: https://luma.com/9wwhomfv