The Wittgensteinian Representation Hypothesis: Is Language the Attractor of Multimodal Convergence?

• URL: http://arxiv.org/abs/2605.09352v1
• Date: Sun, 10 May 2026 06:05:04 GMT
• Title: The Wittgensteinian Representation Hypothesis: Is Language the Attractor of Multimodal Convergence?
• Abstract summary: We introduce directional convergence analysis using cycle-kNN, an asymmetric alignment measure.<n>Non-language modalities move toward the neighborhood structure of language significantly more than the reverse.<n>We formalize this as the Wittgensteinian Representation Hypothesis: the semantic structure of language is the attractor of multimodal representation convergence.
• Score: 37.415683554349194
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Understanding why independently trained neural networks from different modalities converge toward shared representations, and where this convergence leads, remains an open question in representation learning. All existing evidence relies on symmetric similarity measures, which can detect convergence but are structurally blind to its direction. We introduce directional convergence analysis using cycle-kNN, an asymmetric alignment measure, applied across dozens of independently trained unimodal models spanning point clouds, vision, and language. We uncover a consistent directional asymmetry: non-language modalities move toward the neighborhood structure of language significantly more than the reverse, and this pattern holds across all model families and scales--yet is entirely invisible to symmetric measures. Mechanistic analysis traces the directionality to feature density asymmetry, whereby language representations occupy the most compact regions of representational space. The Information Bottleneck framework provides a principled interpretation: optimization under compression drives representations toward discrete, compositional structures characteristic of language. We formalize this as the Wittgensteinian Representation Hypothesis: the semantic structure of language is the asymptotic attractor of multimodal representation convergence.

Related papers

• Conceptual Networks for Cross-Linguistic Idiomatic Expressions: A Feature-Based Graph Approach [0.0]
  We present an interpretable network-based framework for representing idiomatic and figurative meaning across eight typologically diverse languages.<n>Each expression is annotated with binary conceptual features derived from cognitive-linguistic theory, and pairwise Jaccard similarities define a weighted graph.<n>Community detection reveals that idioms cluster by conceptual schema rather than by language, producing a structure consistent with cognitive-linguistic predictions.
  arXiv  Detail & Related papers  (2026-07-10T16:25:51Z)
• LAST: Bridging Vision-Language and Action Manifolds via Gromov-Wasserstein Alignment [71.3712075841632]
  LAST reconstructs the action space to establish local metric compatibility with the Vision-Language-Action modality.<n> LAST enables VLA models with superior convergence and generalizability.
  arXiv  Detail & Related papers  (2026-05-27T03:48:10Z)
• Anisotropic Modality Align [91.23979617826926]
  Training multimodal large language models has long been limited by the scarcity of high-quality paired multimodal data.<n>Recent studies show that the shared representation space of pretrained multimodal contrastive models can serve as a bridge, enabling models to perform multimodal training with unimodal data.<n>The core obstacle lies in the persistent Modality Gap in the shared space.
  arXiv  Detail & Related papers  (2026-05-08T14:53:24Z)
• Barycentric alignment for instance-level comparison of neural representations [2.1920579994942164]
  We introduce a barycentric alignment framework that quotients out nuisance symmetries to construct a universal embedding space across many models.<n>We identify systematic input properties that predict representational convergence versus divergence across vision and language model families.<n>We also apply the same barycentric alignment framework to purely unimodal vision and language models and find that post-hoc alignment into a shared space yields image text similarity scores.
  arXiv  Detail & Related papers  (2026-02-09T21:49:44Z)
• The Representational Geometry of Number [1.5994376682356057]
  We show that number representations preserve a stable relational structure across tasks.<n>We find that task-specific representations are embedded in distinct subspaces, with low-level features like magnitude encoded along separable linear directions.<n>It suggests that understanding arises when task-specific transformations are applied to a shared underlying relational structure of conceptual representations.
  arXiv  Detail & Related papers  (2026-02-06T16:35:22Z)
• A Foundational Theory of Quantitative Abstraction: Adjunctions, Duality, and Logic for Probabilistic Systems [2.362412515574206]
  Large or continuous state spaces make exact analysis intractable and call for principled quantitative abstraction.<n>This work develops a unified theory of such abstraction by integrating category theory, coalgebra, quantitative logic, and optimal transport.
  arXiv  Detail & Related papers  (2025-10-22T10:16:24Z)
• Emergence of Quantised Representations Isolated to Anisotropic Functions [0.0]
  This paper presents a novel methodology for determining representational structure, which builds upon the existing Spotlight Resonance method.<n>It shows how discrete representations can emerge and organise in autoencoder models, through a controlled ablation study in which only the activation function is altered.<n>Using this technique, the validity of whether function-driven symmetries can act as implicit inductive biases on representations is determined.
  arXiv  Detail & Related papers  (2025-07-16T09:27:54Z)
• On Universality Classes of Equivariant Networks [9.137637807153464]
  We investigate the approximation power of equivariant neural networks beyond separation constraints.<n>We show that separation power does not fully capture expressivity.<n>We identify settings where shallow equivariant networks do achieve universality.
  arXiv  Detail & Related papers  (2025-06-02T22:07:52Z)
• The Origins of Representation Manifolds in Large Language Models [52.68554895844062]
  We show that cosine similarity in representation space may encode the intrinsic geometry of a feature through shortest, on-manifold paths.<n>The critical assumptions and predictions of the theory are validated on text embeddings and token activations of large language models.
  arXiv  Detail & Related papers  (2025-05-23T13:31:22Z)
• Relative Representations: Topological and Geometric Perspectives [50.85040046976025]
  Relative representations are an established approach to zero-shot model stitching.<n>We introduce a normalization procedure in the relative transformation, resulting in invariance to non-isotropic rescalings and permutations.<n>Second, we propose to deploy topological densification when fine-tuning relative representations, a topological regularization loss encouraging clustering within classes.
  arXiv  Detail & Related papers  (2024-09-17T08:09:22Z)
• Evaluating the Robustness of Interpretability Methods through Explanation Invariance and Equivariance [72.50214227616728]
  Interpretability methods are valuable only if their explanations faithfully describe the explained model. We consider neural networks whose predictions are invariant under a specific symmetry group.
  arXiv  Detail & Related papers  (2023-04-13T17:59:03Z)
• How dynamics constrains probabilities in general probabilistic theories [0.0]
  We show that all probabilistic structures are rigid and are in one-to-one correspondence with the spherical representations of the dynamical group. This is a generalisation of quantum theory where the pure states, instead of being represented by one-dimensional subspaces of a complex vector space, are represented by subspaces of a fixed dimension larger than one.
  arXiv  Detail & Related papers  (2020-02-12T16:50:05Z)

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.