Are UFOs Real? Introducing Unified Factored Organizers

Thomas X. Sheppard, Alon Albalak, Joel Lehman, Kenneth O. StanleyarXiv 2026 · arXiv

TL;DR

This paper introduces Unified Factored Organizers (UFOs), auxiliary neural networks that act as learned regularizers to force primary models to develop "cleaner," more regular internal representations. By training a model to make its own activations easily compressible by a UFO, the authors achieve a massive 10x to 100x acceleration in "grokking" (delayed generalization) and produce qualitatively superior, interpretable features.

What Problem Does This Paper Address?

In deep learning, we often operate under "representational optimism": the assumption that if a model achieves low training loss, it must have learned a "good" representation of the data. However, recent research suggests that standard gradient descent often produces Fractured Entangled Representations (FER)—messy, high-frequency internal patterns where related concepts are disconnected and unrelated ones are jumbled together.

While these messy representations can still "solve" the training set, they often lead to brittle generalization and catastrophic forgetting. The authors aim to bridge the gap between these messy models and the Unified Factored Representations (UFR) found in human-evolved networks (like those from the Picbreeder project), which exhibit beautiful, symmetric, and highly regular internal structures.

Figure 1: UFO-regularized networks (left) produce regular, symmetric representations compared to the messy patterns of standard networks (right), even when the final output is nearly identical.

Methods

The core idea is to co-train a primary network with an auxiliary autoencoder called a UFO.

  1. The Auxiliary Loss: The primary network is trained not just to solve its task (e.g., image regression or next-token prediction), but also to ensure its internal activations are easily reconstructed by the UFO.
  2. Regularity as Compressibility: Because the UFO is a capacity-limited autoencoder with a tight bottleneck, it can only reconstruct representations that are "regular" and "simple." This forces the primary network to find solutions that are highly compressible.
  3. Selective Updates: To prevent the UFO from simply "learning to reconstruct the mess," the authors use a selective update schedule. The UFO only updates its parameters on representations it can already reconstruct reasonably well, effectively pressuring the primary network to align its "messy" parts with the "clean" model the UFO has built.
  4. Two Flavors:
    • Intracomponent: Regularizes a single hidden node's behavior across a whole batch of inputs.
  5. Intercomponent: Regularizes a whole layer's behavior for a single input (more scalable).

Datasets

The authors evaluate UFOs in two distinct domains:

  • Picbreeder Image Regression: Training a Compositional Pattern Producing Network (CPPN) to reproduce a specific butterfly image. This serves as a "microcosm" for visualizing internal representations as 2D images.
  • Modular Arithmetic (Division Modulo 97): A standard benchmark for studying grokking—the phenomenon where a model suddenly generalizes to validation data long after perfectly fitting the training data.

Key Insights and Ideas

  • The Tug of War: UFO training creates a "tug of war" between the task-driven gradient (climbing toward low loss) and a representational ideal (moving toward regularity). This prevents the model from taking the "path of least resistance" to a messy, overfit solution.
  • Grokking is Representation Learning: The paper reinforces the idea that grokking is essentially the moment a model finally discovers a regular, low-dimensional manifold for its data. By using a UFO to "amplify" these regularities while they are still nascent, the model generalizes much faster.
  • Interpretability as a Signature of Capability: The authors argue that a model that is easier for an auxiliary network to "explain" (reconstruct) is fundamentally a more capable and robust learner.
Figure 6: Visualizing how regular patterns in a transformer's attention and activations gradually emerge during the grokking process.

Key Results

  • Qualitative Superiority: In the butterfly task, UFO-regularized networks developed symmetric, recognizable features that respected the butterfly's geometry, whereas standard networks produced "noisy" features.
  • Massive Speedups:
    • When combined with weight decay, UFOs reduced the training steps needed to grok modular division by 12.25x.
  • Without weight decay, UFOs achieved a staggering 114.1x speedup compared to an unregularized baseline.
  • Generalization: The UFO-trained models didn't just learn faster; they reached near-perfect validation accuracy in a fraction of the time it took standard models to even begin generalizing.
Figure 2: The dramatic difference in validation accuracy over time between a standard transformer and one regularized with a UFO.

Limitations and Future Work

  • Computational Overhead: Training an auxiliary autoencoder alongside the main model adds significant memory and compute costs.
  • Scalability: The "intracomponent" approach (tracking every node across the whole domain) is currently impractical for large-scale datasets like those used for LLMs.
  • Fixed-Length Sequences: The current implementation relies on consistent roles for sequence positions, which may need adaptation for more diverse, variable-length data.
  • Future Direction: The authors suggest that "UFO-like" constraints could eventually be integrated into the loss functions of frontier LLMs to improve sample efficiency and creativity in low-data regimes.

Summary updated

Abstract

Implicit in much research in deep learning is the assumption that if a network achieves low loss, then it must have learned a good representation of its training data. Recent work by Kumar et al. (2025, arXiv:2505.11581) questions this assumption, arguing that networks trained with conventional gradient descent achieve low loss despite learning fractured entangled representations (FER), leaving related concepts disconnected and unrelated concepts entangled inappropriately. Kumar et al. further show that dramatically better representations are possible: a network evolved through an open-ended, human-in-the-loop process learned unified factored representations (UFR) that capture the regularities of the domain far better than a counterpart with nearly identical outputs trained with conventional gradient descent. Inspired by UFR, this paper introduces unified factored organizers (UFOs), networks trained to model regularities in the representations of other networks. A network can then be trained both to achieve low loss on its task objective and to align its representations with the model learned by the UFO. Networks trained with UFOs are shown to learn qualitatively superior representations in an image-regression domain where representations are easily interpretable. To provide quantitative evidence for the impact of UFOs on representation learning, a transformer is trained with and without UFO regularization to grok a modular arithmetic problem set. When combined with weight decay, UFOs can reduce the number of transformer training steps needed to grok by more than 10x relative to weight decay alone. Without weight decay, UFOs can reduce the number of transformer training steps needed to grok by more than 100x relative to an unregularized baseline. If UFOs are real, they suggest a new paradigm where loss functions themselves are trained to learn an effective model of good representation.
BibTeX
@misc{sheppard2026are,
  author = {Thomas X. Sheppard and Alon Albalak and Joel Lehman and Kenneth O. Stanley},
  title = {{Are UFOs Real? Introducing Unified Factored Organizers}},
  year = {2026},
  eprint = {2611.11862},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.11862},
}
Figure