← Back to all news
arXiv AI By Eric Elmoznino, Tejas Kasetty, Blaise Ag\"uera y Arcas, Yoshua Bengio, Guillaume Lajoie

Defining and Generating Compositional Structure

Read the original on arXiv AI →

The paper introduces a formal definition of compositional structure based on algorithmic information theory, stating that such structure emerges when combined parts reveal shared patterns not evident when modeled separately. It applies this definition across scales to identify where compositionality arises and then inverts the framework to generate new compositional objects by optimizing over strings and images. The resulting artifacts display clear hierarchical reuse and part‑whole organization, indicating that the definition captures genuine compositionality rather than generic complexity or regularity.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Sep 10

A Theoretical Analysis of Provable Compositional Generalization in Neural Networks: A Necessary and Sufficient Condition

The paper presents a necessary and sufficient condition for provable compositional generalization in neural networks, identifying two key principles: structural alignment and unambiguous minimized representations. It rigorously proves this condition, verifies it in Lean 4, and demonstrates its applicability in few-shot settings, including the SCAN jump task. The authors also outline an algorithmic approach and illustrate it with a minimal example, all derived purely from mathematical analysis without empirical validation.

By Yuanpeng Li
safety
More like this →
Hugging Face Trending Papers
Jul 14

Atomic Units of X: The Compression Layer of Intelligence

This paper proposes a theoretical framework for understanding intelligence as a process of atomic compression and compositional reuse. We argue that cognitive, biological, computational, and organizational systems achieve scalable intelligence by decomposing complex phenomena into reusable atomic units that can be recombined into higher-order structures.

llmssafety
More like this →
arXiv Machine Learning
Jun 18

From Mechanistic to Compositional Interpretability

arXiv:2605. 08934v2 Announce Type: replace Abstract: Mechanistic interpretability aims to explain neural model behaviour by reverse-engineering learned computational structure into human-understandable components.

By Ward Gauderis, Thomas Dooms, Steven T. Homer, Kola Ayonrinde, Geraint A. Wiggins
safety
More like this →