Platonic Representation Hypothesis on World Models

• URL: http://arxiv.org/abs/2608.23720v2
• Date: Wed, 26 Aug 2026 03:46:21 GMT
• Title: Platonic Representation Hypothesis on World Models
• Abstract summary: We show that capable world models evolve toward geometrically similar internal structures.<n>Our findings suggest that the pursuit of predictive consistency can promote shared, transition-compatible latent structure across world models.
• Score: 42.05154017234555
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: World models have demonstrated significant potential for perceiving and simulating complex environments. Despite their strong performance, the fundamental nature of their learned representations remains poorly understood. In this paper, we investigate the Platonic Representation Hypothesis within this domain by proposing the Predictive Consistency Assumption: we posit that the optimization of a shared state transition objective acts as a selective pressure that encourages heterogeneous models to converge toward a shared latent structure. Through systematic experiments with the DINO World Model (DINO-WM), in which we vary visual encoders to create heterogeneous models, we find that capable world models evolve toward geometrically similar internal structures. Moreover, via model stitching, we show that the internal features of one world model can be mapped to another with limited performance degradation, providing evidence of functional compatibility. Our findings suggest that the pursuit of predictive consistency can promote shared, transition-compatible latent structure across world models.

Related papers

• Structure Abstraction and Generalization in a Hippocampal-Entorhinal Inspired World Model [11.849694189409526]
  We show how a brain-inspired hierarchical model infers latent transitions and constructs a predictive visual world model.<n>This work provides a novel computational framework for understanding how brain-inspired, self-supervised learning of world models facilitates the acquisition of reusable abstract knowledge.
  arXiv  Detail & Related papers  (2026-05-15T08:36:40Z)
• World Action Models: The Next Frontier in Embodied AI [123.5787299299832]
  Vision-Language-Action (VLA) models have achieved strong semantic generalization for embodied policy learning.<n>They learn reactive observation-to-action mappings without explicitly modeling how the physical world evolves under intervention.<n>A growing body of work addresses this limitation by integrating world models, predictive models of environment dynamics, into the action generation pipeline.
  arXiv  Detail & Related papers  (2026-05-12T13:10:52Z)
• The Trinity of Consistency as a Defining Principle for General World Models [106.16462830681452]
  General World Models are capable of learning, simulating, and reasoning about objective physical laws.<n>We propose a principled theoretical framework that defines the essential properties requisite for a General World Model.<n>Our work establishes a principled pathway toward general world models, clarifying both the limitations of current systems and the architectural requirements for future progress.
  arXiv  Detail & Related papers  (2026-02-26T16:15:55Z)
• Universally Converging Representations of Matter Across Scientific Foundation Models [5.309886698585678]
  We show that representations learned by nearly sixty scientific models are highly aligned across a wide range of chemical systems.<n>On inputs similar to those seen during training, high-performing models align closely and weak models diverge into local sub-optima in representation space.<n>Our findings establish representational alignment as a quantitative benchmark for foundation-level generality in scientific models.
  arXiv  Detail & Related papers  (2025-12-03T12:47:06Z)
• From monoliths to modules: Decomposing transducers for efficient world modelling [74.41506965793417]
  We develop a framework for decomposing complex world models represented by transducers.<n>Our results clarify how to invert this process, deriving sub-transducers operating on distinct input-output subspaces.
  arXiv  Detail & Related papers  (2025-12-01T20:37:43Z)
• SmallWorlds: Assessing Dynamics Understanding of World Models in Isolated Environments [15.243547292947397]
  We introduce the SmallWorld Benchmark, a testbed designed to assess world model capability under isolated and precisely controlled dynamics.<n>We conduct comprehensive experiments in the fully observable state space on representative architectures including Recurrent State Space Model, Transformer, Diffusion model, and Neural ODE.<n>The experimental results reveal how effectively these models capture environment structure and how their predictions deteriorate over extended rollouts.
  arXiv  Detail & Related papers  (2025-11-28T18:56:02Z)
• Learning Local Causal World Models with State Space Models and Attention [1.5498250598583487]
  We show that a SSM can model the dynamics of a simple environment and learn a causal model at the same time.<n>We pave the way for further experiments that lean into the strength of SSMs and further enhance them with causal awareness.
  arXiv  Detail & Related papers  (2025-05-04T11:57:02Z)
• Learning Discrete Concepts in Latent Hierarchical Models [73.01229236386148]
  Learning concepts from natural high-dimensional data holds potential in building human-aligned and interpretable machine learning models.<n>We formalize concepts as discrete latent causal variables that are related via a hierarchical causal model.<n>We substantiate our theoretical claims with synthetic data experiments.
  arXiv  Detail & Related papers  (2024-06-01T18:01:03Z)
• S2RMs: Spatially Structured Recurrent Modules [105.0377129434636]
  We take a step towards exploiting dynamic structure that are capable of simultaneously exploiting both modular andtemporal structures. We find our models to be robust to the number of available views and better capable of generalization to novel tasks without additional training.
  arXiv  Detail & Related papers  (2020-07-13T17:44:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.