# Slot Structured World Models

arXiv: https://arxiv.org/abs/2402.03326 · HTML: https://mlsanity.com/paper/2402.03326/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Latent predictive world models, one of 11 directions in World models.
- Builds on 21 of its 29 references that are in the map.
- First posted on arXiv 8 Jan 2024.

## Placed in

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

## Builds on (most cited first, 21 of 21)

- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [Interaction Networks for Learning about Objects, Relations and Physics](https://mlsanity.com/paper/1612.00222/) (2016)
- [MONet: Unsupervised Scene Decomposition and Representation](https://mlsanity.com/paper/1901.11390/) (2019)
- [Learning Multiagent Communication with Backpropagation](https://mlsanity.com/paper/1605.07736/) (2016)
- [Multi-Object Representation Learning with Iterative Variational Inference](https://mlsanity.com/paper/1903.00450/) (2019)
- [Neural Relational Inference for Interacting Systems](https://mlsanity.com/paper/1802.04687/) (2018)
- [Graph networks as learnable physics engines for inference and control](https://mlsanity.com/paper/1806.01242/) (2018)
- [GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations](https://mlsanity.com/paper/1907.13052/) (2019)
- [Contrastive Learning of Structured World Models](https://mlsanity.com/paper/1911.12247/) (2019)
- [A Compositional Object-Based Approach to Learning Physical Dynamics](https://mlsanity.com/paper/1612.00341/) (2016)
- [Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions](https://mlsanity.com/paper/1802.10353/) (2018)
- [Visual Interaction Networks](https://mlsanity.com/paper/1706.01433/) (2017)
- [Improving Object-centric Learning with Query Optimization](https://mlsanity.com/paper/2210.08990/) (2022)
- [COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration](https://mlsanity.com/paper/1905.09275/) (2019)
- [VAIN: Attentional Multi-agent Predictive Modeling](https://mlsanity.com/paper/1706.06122/) (2017)
- [Invariant Slot Attention: Object Discovery with Slot-Centric Reference Frames](https://mlsanity.com/paper/2302.04973/) (2023)
- [Object Representations as Fixed Points: Training Iterative Refinement Algorithms with Implicit Differentiation](https://mlsanity.com/paper/2207.00787/) (2022)
- [Unsupervised Discovery of Parts, Structure, and Dynamics](https://mlsanity.com/paper/1903.05136/) (2019)

## Built on by (most cited first, 5 of 5)

- [Object-Centric World Model for Language-Guided Manipulation](https://mlsanity.com/paper/2503.06170/) (2025)
- [AXIOM: Learning to Play Games in Minutes with Expanding Object-Centric Models](https://mlsanity.com/paper/2505.24784/) (2025)
- [Unifying Object-Centric World Models and Diffusion Policy: A Hierarchical Framework for Multi-Stage Robotic Tasks](https://mlsanity.com/paper/2606.08775/) (2026)
- [MUFASA: A Multi-Layer Framework for Slot Attention](https://mlsanity.com/paper/2602.07544/) (2026)
- [AutoWorldModel-Bench: A State-Centric Benchmark for Automated World-Model Research](https://mlsanity.com/paper/2608.11216/) (2026)

## Abstract (arXiv)

The ability to perceive and reason about individual objects and their interactions is a goal to be achieved for building intelligent artificial systems. State-of-the-art approaches use a feedforward encoder to extract object embeddings and a latent graph neural network to model the interaction between these object embeddings. However, the feedforward encoder can not extract it object-centric representations, nor can it disentangle multiple objects with similar appearance. To solve these issues, we introduce it Slot Structured World Models (SSWM), a class of world models that combines an it object-centric encoder (based on Slot Attention) with a latent graph-based dynamics model. We evaluate our method in the Spriteworld benchmark with simple rules of physical interaction, where Slot Structured World Models consistently outperform baselines on a range of (multi-step) prediction tasks with action-conditional object interactions. All code to reproduce paper experiments is available from urlhttps://github.com/JonathanCollu/Slot-Structured-World-Models.