# Compositional Generalization via Forced Rendering of Disentangled Latents

arXiv: https://arxiv.org/abs/2501.18797 · HTML: https://mlsanity.com/paper/2501.18797/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 27 references that are in the map.
- First posted on arXiv 30 Jan 2025.

## Builds on (most cited first, 14 of 14)

- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018)
- [Disentangling by Factorising](https://mlsanity.com/paper/1802.05983/) (2018)
- [An analytic theory of creativity in convolutional diffusion models](https://mlsanity.com/paper/2412.20292/) (2024)
- [Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Task](https://mlsanity.com/paper/2310.09336/) (2023)
- [Bias and Generalization in Deep Generative Models: An Empirical Study](https://mlsanity.com/paper/1811.03259/) (2018)
- [Compositional Generalization from First Principles](https://mlsanity.com/paper/2307.05596/) (2023)
- [Compositional Generalization in Unsupervised Compositional Representation Learning: A Study on Disentanglement and Emergent Language](https://mlsanity.com/paper/2210.00482/) (2022)
- [The Complexity Dynamics of Grokking](https://mlsanity.com/paper/2412.09810/) (2024)
- [When does compositional structure yield compositional generalization? A kernel theory](https://mlsanity.com/paper/2405.16391/) (2024)
- [How Diffusion Models Learn to Factorize and Compose](https://mlsanity.com/paper/2408.13256/) (2024)
- [Vector-based Representation is the Key: A Study on Disentanglement and Compositional Generalization](https://mlsanity.com/paper/2305.18063/) (2023)
- [How does training shape the Riemannian geometry of neural network representations?](https://mlsanity.com/paper/2301.11375/) (2023)
- [Do Diffusion Models Learn Semantically Meaningful and Efficient Representations?](https://mlsanity.com/paper/2402.03305/) (2024)

## Built on by (most cited first, 4 of 4)

- [A mathematical theory for understanding when abstract representations emerge in neural networks](https://mlsanity.com/paper/2510.09816/) (2025)
- [Learning Compositional Latent Structure with Vector Networks](https://mlsanity.com/paper/2605.28007/) (2026)
- [Modular connectivity in neural networks emerges from Poisson noise-motivated regularisation, and promotes robustness and compositional generalisation](https://mlsanity.com/paper/2512.13707/) (2025)
- [Seeing Through the PRISM: Compound & Controllable Restoration of Scientific Images](https://mlsanity.com/paper/2603.14151/) (2026)

## Abstract (arXiv)

Composition-the ability to generate myriad variations from finite means-is believed to underlie powerful generalization. However, compositional generalization remains a key challenge for deep learning. A widely held assumption is that learning disentangled (factorized) representations naturally supports this kind of extrapolation. Yet, empirical results are mixed, with many generative models failing to recognize and compose factors to generate out-of-distribution (OOD) samples. In this work, we investigate a controlled 2D Gaussian "bump" generation task with fully disentangled (x,y) inputs, demonstrating that standard generative architectures still fail in OOD regions when training with partial data, by re-entangling latent representations in subsequent layers. By examining the model's learned kernels and manifold geometry, we show that this failure reflects a "memorization" strategy for generation via data superposition rather than via composition of the true factorized features. We show that when models are forced-through architectural modifications with regularization or curated training data-to render the disentangled latents into the full-dimensional representational (pixel) space, they can be highly data-efficient and effective at composing in OOD regions. These findings underscore that disentangled latents in an abstract representation are insufficient and show that if models can represent disentangled factors directly in the output representational space, it can achieve robust compositional generalization.