mlsanityData to 7 Oct 2026

Toward Compositional Generalization in Object-Oriented World Modeling

arXiv 2204.13661 ↗First posted 28 Apr 2022cs.LG cs.AI cs.ROcited by 22

On the map: World models → World models for language agents

Abstract (arXiv)

Compositional generalization is a critical ability in learning and decision-making. We focus on the setting of reinforcement learning in object-oriented environments to study compositional generalization in world modeling. We (1) formalize the compositional generalization problem with an algebraic approach and (2) study how a world model can achieve that. We introduce a conceptual environment, Object Library, and two instances, and deploy a principled pipeline to measure the generalization ability. Motivated by the formulation, we analyze several methods with exact or no compositional generalization ability using our framework, and design a differentiable approach, Homomorphic Object-oriented World Model (HOWM), that achieves soft but more efficient compositional generalization.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Placed in World models for language agents, one of 11 directions in World models. Builds on 23 of its 33 references that are in the map. First posted on arXiv 28 Apr 2022.

Builds on

23 of 33 references.

References · 23

  1. 2016CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoningcited by 1,445
  2. 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,131
  3. 2020Object-Centric Learning with Slot Attentioncited by 865
  4. 2019MONet: Unsupervised Scene Decomposition and Representationcited by 388
  5. 2018Towards a Definition of Disentangled Representationscited by 294
  6. 2019Measuring Compositional Generalization: A Comprehensive Method on Realistic Datacited by 280
  7. 2021Conditional Object-Centric Learning from Videocited by 247
  8. 2020On the Binding Problem in Artificial Neural Networkscited by 230
  9. 2019Contrastive Learning of Structured World Modelscited by 206
  10. 2019Universal Invariant and Equivariant Graph Neural Networkscited by 182
  11. 2019A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithmscited by 136
  12. 2020MDP Homomorphic Networks: Group Symmetries in Reinforcement Learningcited by 133
11 more
  1. 2019Entity Abstraction in Visual Model-Based Reinforcement Learningcited by 110
  2. 2020Compositionality and Generalization in Emergent Languagescited by 103
  3. 2019Measuring Compositionality in Representation Learningcited by 84
  4. 2021Neural Production Systems: Learning Rule-Governed Visual Dynamicscited by 75
  5. 2020Improving Generative Imagination in Object-Centric World Modelscited by 70
  6. 2019COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Explorationcited by 55
  7. 2019Structured Object-Aware Physics Prediction for Video Modeling and Planningcited by 42
  8. 2019Symmetry-Based Disentangled Representation Learning requires Interaction with Environmentscited by 35
  9. 2021Unsupervised Object-Based Transition Models for 3D Partially Observable Environmentscited by 19
  10. 2022Binding Actions to Objects in World Modelscited by 9
  11. 2021The Impact of Negative Sampling on Contrastive Structured World Modelscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 6; 2024: 5; 2025: 8; 2026: 2.

22 papers.

Sort:

By area:

  1. 2023Provable Compositional Generalization for Object-Centric Learningcited by 41
  2. 2024Entity-Centric Reinforcement Learning for Object Manipulation from Pixelscited by 27
  3. 2023Learning Dynamic Attribute-factored World Models for Efficient Multi-object Reinforcement Learningcited by 15
  4. 2023Neurosymbolic Grounding for Compositional World Modelscited by 14
  5. 2023A Survey on Compositional Generalization in Applicationscited by 12
  6. 2024Language-Guided World Models: A Model-Based Approach to AI Controlcited by 12
  7. 2025Dyn-O: Building Structured World Models with Object-Centric Representationscited by 12
  8. 2024Entity-based Reinforcement Learning for Autonomous Cyber Defencecited by 11
  9. 2025Learning Interactive World Model for Object-Centric Reinforcement Learningcited by 11
  10. 2024EC-Diffuser: Multi-Object Manipulation via Entity-Centric Behavior Generationcited by 8
  11. 2022Integrating Symmetry into Differentiable Planning with Steerable Convolutionscited by 6
  12. 2023E(2)-Equivariant Graph Planning for Navigationcited by 6
10 more
  1. 2026Hierarchical Entity-centric Reinforcement Learning with Factored Subgoal Diffusioncited by 6
  2. 2025Position: Foundation Models for Tabular Data within Systemic Contexts Need Groundingcited by 5
  3. 2024Equivariant Action Sampling for Reinforcement Learning and Planningcited by 4
  4. 2025Towards Understanding Extrapolation: a Causal Lenscited by 4
  5. 2025Dreamweaver: Learning Compositional World Models from Pixelscited by 4
  6. 2025From monoliths to modules: Decomposing transducers for efficient world modellingcited by 4
  7. 2025What Drives Compositional Generalization in Visual Generative Models? The Importance of Continuous Training Objectivescited by 3
  8. 2023Can Euclidean Symmetry be Leveraged in Reinforcement Learning and Planning?cited by 1
  9. 2025State Combinatorial Generalization In Decision Making With Conditional Diffusion Modelscited by 1
  10. 2026Mitigating Simplicity Bias in OOD Detection through Object Co-occurrence Analysiscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025Modeling Unseen Environments with Language-guided Composable Causal Components in Reinforcement Learning
  2. 2021Procedural Generalization by Planning with Self-Supervised World Models
  3. 2022Policy Architectures for Compositional Generalization in Control
  4. 2022Powderworld: A Platform for Understanding Generalization via Rich Task Distributions
  5. 2026Compositional Reasoning in Language Models under Reinforcement Learning Post-Training
  6. 2026Learning to Reason with Curriculum II: Compositional Generalization
  7. 2025Compositional Generalization from Learned Skills via CoT Training: A Theoretical and Structural Analysis for Reasoning
  8. 2026From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning