# Slot-MPC: Goal-Conditioned Model Predictive Control with Object-Centric Representations

arXiv: https://arxiv.org/abs/2605.14937 · HTML: https://mlsanity.com/paper/2605.14937/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Latent predictive world models, one of 11 directions in World models.
- Builds on 14 of its 66 references that are in the map.
- First posted on arXiv 14 May 2026.

## Placed in

- World models / [Latent predictive world models](https://mlsanity.com/wm/latent-predictive-world-models/)

## Builds on (most cited first, 14 of 14)

- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [robosuite: A Modular Simulation Framework and Benchmark for Robot Learning](https://mlsanity.com/paper/2009.12293/) (2020)
- [MONet: Unsupervised Scene Decomposition and Representation](https://mlsanity.com/paper/1901.11390/) (2019)
- [On the Binding Problem in Artificial Neural Networks](https://mlsanity.com/paper/2012.05208/) (2020)
- [Model Predictive Path Integral Control using Covariance Variable Importance Sampling](https://mlsanity.com/paper/1509.01149/) (2015)
- [Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEs](https://mlsanity.com/paper/1901.07017/) (2019)
- [What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?](https://mlsanity.com/paper/2512.24497/) (2025)
- [Temporal Straightening for Latent Planning](https://mlsanity.com/paper/2603.12231/) (2026)
- [Causal-JEPA: Learning World Models through Object-Level Latent Masking](https://mlsanity.com/paper/2602.11389/) (2026)
- [Compositional Multi-Object Reinforcement Learning with Linear Relation Networks](https://mlsanity.com/paper/2201.13388/) (2022)
- [Gradient-based Planning with World Models](https://mlsanity.com/paper/2312.17227/) (2023)
- [Closing the Train-Test Gap in World Models for Gradient-Based Planning](https://mlsanity.com/paper/2512.09929/) (2025)
- [Model-Based Planning with Discrete and Continuous Actions](https://mlsanity.com/paper/1705.07177/) (2017)
- [Parallel Stochastic Gradient-Based Planning for World Models](https://mlsanity.com/paper/2602.00475/) (2026)

## Built on by (most cited first, 4 of 4)

- [Beyond Instance Slots: Semantically Rich World Models for Physical Interaction Planning](https://mlsanity.com/paper/2608.22294/) (2026)
- [Better Slots, Better Worlds: Representation Quality & Robustness in Object-Centric World Models](https://mlsanity.com/paper/2608.12078/) (2026)
- [SlotDiT: Object-Centric Representations for Diffusion Transformers](https://mlsanity.com/paper/2609.17414/) (2026)
- [Keeping JEPA World Models Plannable When Little of the Frame Moves](https://mlsanity.com/paper/2610.03137/) (2026)

## Abstract (arXiv)

Predictive world models enable agents to model scene dynamics and reason about the consequences of their actions. Inspired by human perception, object-centric world models capture scene dynamics using object-level representations, which can be used for downstream applications such as action planning. However, most object-centric world models and reinforcement learning (RL) approaches learn reactive policies that are fixed at inference time, limiting generalization to novel situations. We propose Slot-MPC, an object-centric world modeling framework that enables planning through Model Predictive Control (MPC). Slot-MPC leverages vision encoders to learn slot-based representations, which encode individual objects in the scene, and uses these structured representations to learn an action-conditioned object-centric dynamics model. At inference time, the learned dynamics model enables action planning via MPC, allowing agents to adapt to previously unseen situations. Since the learned world model is differentiable, we can use gradient-based MPC to directly optimize actions, which is computationally more efficient than relying on gradient-free, sampling-based MPC methods. Experiments on simulated robotic manipulation tasks show that Slot-MPC improves both task performance and planning efficiency compared to non-object-centric world model baselines. In the considered offline setting with limited state-action coverage, we find that gradient-based MPC performs better than gradient-free, sampling-based MPC. Our results demonstrate that explicitly structured, object-centric representations provide a strong inductive bias for controllable and generalizable decision-making. Code and additional results are available at https://slot-mpc.github.io.