Featured image of post Invited Talk at HKUST(GZ) AI Seminar: World Models for Planning

Invited Talk at HKUST(GZ) AI Seminar: World Models for Planning

Talk at the HKUST(GZ) AI Seminar on world models for planning.

I was invited to give a talk at the AI Seminar at HKUST (Guangzhou) in November 2026.

The talk, World Models for Planning: From Code World Models to Temporal-Distance JEPA, is about using a world model to plan. A planner needs to know what will happen next, and which future is closer to the goal. The deck covers three papers:

  1. PatchWorld turns a text environment into a Python program, then fixes the program when it disagrees with past trajectories. After that, planning is just running the program. (paper, code)
  2. VisualPatchWorld does this for visual control. The shape of the dynamics matters: a program can fit the next step and still get the physics wrong. Contact is the hard part. (paper, code)
  3. Temporal-Distance-JEPA keeps a neural world model and learns the score used in planning from the order of states in the demonstrations. (paper, code)

Slides: Download PDF

Thanks to the organizers for the invitation.

Built with Hugo
Theme Stack designed by Jimmy