mlsanityData to 14 Oct 2026

The Umwelt Representation Hypothesis: Rethinking Universality

arXiv 2604.17960 ↗First posted 20 Apr 2026q-bio.NC cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Recent studies reveal striking representational alignment between artificial neural networks (ANNs) and biological brains, leading to proposals that all sufficiently capable systems converge on universal representations of reality. Here, we argue that this claim of Universality is premature. We introduce the Umwelt Representation Hypothesis (URH), proposing that alignment arises not from convergence toward a single global optimum, but from overlap in ecological constraints under which systems develop. We review empirical evidence showing that representational differences between species, individuals, and ANNs are systematic and adaptive, which is difficult to reconcile with Universality. Finally, we reframe ANN model comparison as a method for mapping clusters of alignment in ecological constraint space rather than searching for a single optimal world model.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 25 of its 113 references that are in the map. First posted on arXiv 20 Apr 2026.

Builds on

25 of 113 references.

References · 25

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  3. 2023Visual Instruction Tuningcited by 7,869
  4. 2024The Platonic Representation Hypothesiscited by 382
  5. 2021Revisiting Model Stitching to Compare Neural Representationscited by 209
  6. 2021Partial success in closing the gap between human and machine visioncited by 185
  7. 2021Pretrained Transformers as Universal Computation Enginescited by 162
  8. 2022Linearly Mapping from Image to Text Spacecited by 142
  9. 2014Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Brain's Ventral Visual Pathwaycited by 94
  10. 2021Predictive Coding: a Theoretical and Experimental Reviewcited by 77
  11. 2019Recurrence is required to capture the representational dynamics of the human visual systemcited by 58
  12. 2022The neuroconnectionist research programmecited by 48
13 more
  1. 2026Revisiting the Platonic Representation Hypothesis: An Aristotelian Viewcited by 44
  2. 2024Spurious reconstruction from brain activitycited by 15
  3. 2025Brain-Model Evaluations Need the NeuroAI Turing Testcited by 13
  4. 2024Universal dimensions of visual representationcited by 12
  5. 2025Better artificial intelligence does not mean better models of biologycited by 10
  6. 2023System identification of neural systems: If we got it right, would we know?cited by 9
  7. 2025Naturalistic Computational Cognitive Science: Towards generalizable models and theories that capture the full range of natural behaviorcited by 8
  8. 2022Testing the limits of natural language models for predicting human language judgmentscited by 7
  9. 2025A 7T fMRI dataset of synthetic images for out-of-distribution modeling of visioncited by 7
  10. 2025Adopting a human developmental visual diet yields robust, shape-based AI visioncited by 5
  11. 2025Model-brain comparison using inter-animal transformscited by 3
  12. 2025Model-Behavior Alignment under Flexible Evaluation: When the Best-Fitting Model Isn't the Right Onecited by 2
  13. 2025High-dimensional structure underlying individual differences in naturalistic visual experiencecited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Platonic Representation Hypothesis on World Models
  2. 2026Local Intrinsic Dimension of Representations Predicts Alignment and Generalization in AI Models and Human Brain
  3. 2026Remapping and navigation of an embedding space via error minimization: a fundamental organizational principle of cognition in natural and artificial systems
  4. 2025Context and Diversity Matter: The Emergence of In-Context Learning in World Models
  5. 2024Possible Principles for Aligned Structure Learning Agents
  6. 2026Task Ecologies and the Evolution of World-Tracking Representations in Large Language Models
  7. 2025Brain-Language Model Alignment: Insights into the Platonic Hypothesis and Intermediate-Layer Advantage
  8. 2025Information Structure in Mappings: An Approach to Learning, Representation, and Generalisation