ARTFEED — Contemporary Art Intelligence

Slot-MPC: Object-Centric World Model for Goal-Conditioned Planning

ai-technology · 2026-05-16

A new framework called Slot-MPC uses object-centric representations and model predictive control to enable agents to plan actions adaptively at inference time, overcoming the limitations of fixed reactive policies in reinforcement learning.

Key facts

  • Slot-MPC is an object-centric world modeling framework.
  • It leverages vision encoders to learn slot-based representations encoding individual objects.
  • It uses these representations to learn an action-conditioned object-centric dynamics model.
  • At inference time, the learned dynamics model enables action planning via MPC.
  • It allows agents to adapt to novel situations not seen during training.
  • The approach is inspired by human perception of scenes as objects.
  • It addresses the limitation of most object-centric world models and RL approaches that learn fixed reactive policies.
  • The paper is published on arXiv with ID 2605.14937.

Entities

Institutions

  • arXiv

Sources