Pith. sign in

REVIEW 5 cited by

Contrastive Learning of Structured World Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1911.12247 v2 pith:4J5JAHZJ submitted 2019-11-27 stat.ML cs.AIcs.LG

classification stat.MLcs.AIcs.LG
keywords learningstructuredc-swmsworldenvironmentsmodelsobjectscompositional
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

A structured understanding of our world in terms of objects, relations, and hierarchies is an important component of human cognition. Learning such a structured world model from raw sensory data remains a challenge. As a step towards this goal, we introduce Contrastively-trained Structured World Models (C-SWMs). C-SWMs utilize a contrastive approach for representation learning in environments with compositional structure. We structure each state embedding as a set of object representations and their relations, modeled by a graph neural network. This allows objects to be discovered from raw pixel observations without direct supervision as part of the learning process. We evaluate C-SWMs on compositional environments involving multiple interacting objects that can be manipulated independently by an agent, simple Atari games, and a multi-object physics simulation. Our experiments demonstrate that C-SWMs can overcome limitations of models based on pixel reconstruction and outperform typical representatives of this model class in highly structured environments, while learning interpretable object-based representations.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 69 citations worldwide. Full citation record

  1. Learning Physics-Guided Residual Dynamics for Deformable Object Simulation

    cs.RO 2026-07 conditional novelty 6.0 of 10

    Physics-guided residual dynamics, a spring-mass simulator plus a network that predicts velocity corrections, yields the most accurate deformable-object simulation in the paper's real-world tests.

  2. ORGAN: Object-Centric Representation Learning using Cycle Consistent Generative Adversarial Networks

    cs.CV 2026-03 conditional novelty 6.0 of 10

    A cycle-consistent GAN that translates between images and object lists matches state-of-the-art detection on synthetic scenes and detects low-contrast cells where slot-attention models fail.

  3. Discovering and using Spelke segments

    cs.CV 2025-07 conditional novelty 6.0 of 10

    SpelkeNet, a self-supervised video world model, discovers Spelke segments in static images by aggregating motion correlations across imagined pokes.

  4. A Definition and Roadmap for World Models

    cs.AI 2026-07 conditional novelty 5.0 of 10

    A perspective article defining world models as finite-resource compression of physical state transitions and outlining a roadmap toward physical AGI via unified representations and interactive simulators.

  5. Learning Implicit Causal World Models from Multi-Agent Demonstrations

    cs.LG 2026-07 conditional novelty 4.0 of 10

    Random action noise improves multi-agent world-model OOD accuracy, but the paper's own common-cause analysis shows the causal graph contributes little at matched data.

Pith tools