diffusion transformer

The talk examines why robotics remains difficult, pointing to gaps in physical modeling, action representation, sensing, and hardware reliability. Researchers present approaches for longer tasks and adaptation using memory, embodiment-specific reasoning, and simulation-trained dexterous policies that transfer to real tools. Rerun co-founder Nico argues that robotics startups should solve a specific customer problem end to end, starting with teleoperation and off-the-shelf hardware, then iterating through real-world data and evaluation. General Intuition presents ways to make world action models faster enough for real-time robotics.

Suhail Doshi explains how Playground shifted from a general image generator toward a visual design tool built around templates and conversational editing. The talk describes Playground v3’s focus on prompt understanding, accurate text rendering, and detailed image control, along with the architectural changes the team made to support those goals. Doshi discusses learning from user behavior, choosing commercially useful design tasks, and how close prompt adherence can complicate aesthetic evaluations. He also reflects on earlier ventures, research priorities, and why reaching state of the art requires sustained attention to small details.