# The Umwelt Representation Hypothesis: Rethinking Universality

arXiv: https://arxiv.org/abs/2604.17960 · HTML: https://mlsanity.com/paper/2604.17960/

## 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 (most cited first, 25 of 25)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [The Platonic Representation Hypothesis](https://mlsanity.com/paper/2405.07987/) (2024)
- [Revisiting Model Stitching to Compare Neural Representations](https://mlsanity.com/paper/2106.07682/) (2021)
- [Partial success in closing the gap between human and machine vision](https://mlsanity.com/paper/2106.07411/) (2021)
- [Pretrained Transformers as Universal Computation Engines](https://mlsanity.com/paper/2103.05247/) (2021)
- [Linearly Mapping from Image to Text Space](https://mlsanity.com/paper/2209.15162/) (2022)
- [Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Brain's Ventral Visual Pathway](https://mlsanity.com/paper/1411.6422/) (2014)
- [Predictive Coding: a Theoretical and Experimental Review](https://mlsanity.com/paper/2107.12979/) (2021)
- [Recurrence is required to capture the representational dynamics of the human visual system](https://mlsanity.com/paper/1903.05946/) (2019)
- [The neuroconnectionist research programme](https://mlsanity.com/paper/2209.03718/) (2022)
- [Revisiting the Platonic Representation Hypothesis: An Aristotelian View](https://mlsanity.com/paper/2602.14486/) (2026)
- [Spurious reconstruction from brain activity](https://mlsanity.com/paper/2405.10078/) (2024)
- [Brain-Model Evaluations Need the NeuroAI Turing Test](https://mlsanity.com/paper/2502.16238/) (2025)
- [Universal dimensions of visual representation](https://mlsanity.com/paper/2408.12804/) (2024)
- [Better artificial intelligence does not mean better models of biology](https://mlsanity.com/paper/2504.16940/) (2025)
- [System identification of neural systems: If we got it right, would we know?](https://mlsanity.com/paper/2302.06677/) (2023)
- [Naturalistic Computational Cognitive Science: Towards generalizable models and theories that capture the full range of natural behavior](https://mlsanity.com/paper/2502.20349/) (2025)
- [Testing the limits of natural language models for predicting human language judgments](https://mlsanity.com/paper/2204.03592/) (2022)
- [A 7T fMRI dataset of synthetic images for out-of-distribution modeling of vision](https://mlsanity.com/paper/2503.06286/) (2025)
- [Adopting a human developmental visual diet yields robust, shape-based AI vision](https://mlsanity.com/paper/2507.03168/) (2025)
- [Model-brain comparison using inter-animal transforms](https://mlsanity.com/paper/2510.02523/) (2025)
- [Model-Behavior Alignment under Flexible Evaluation: When the Best-Fitting Model Isn't the Right One](https://mlsanity.com/paper/2510.23321/) (2025)
- [High-dimensional structure underlying individual differences in naturalistic visual experience](https://mlsanity.com/paper/2505.12653/) (2025)

## 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.