# Towards a universal language of concepts: A survey

arXiv: https://arxiv.org/abs/2609.04528 · HTML: https://mlsanity.com/paper/2609.04528/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 43 references that are in the map.
- First posted on arXiv 3 Sep 2026.

## Builds on (most cited first, 7 of 7)

- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision](https://mlsanity.com/paper/1904.12584/) (2019)
- [DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning](https://mlsanity.com/paper/2006.08381/) (2020)
- [HOUDINI: Lifelong Learning as Program Synthesis](https://mlsanity.com/paper/1804.00218/) (2018)
- [Solving Bongard Problems with a Visual Language and Pragmatic Reasoning](https://mlsanity.com/paper/1804.04452/) (2018)
- [Beyond imitation: Zero-shot task transfer on robots by learning concepts as cognitive programs](https://mlsanity.com/paper/1812.02788/) (2018)
- [Representational efficiency outweighs action efficiency in human program induction](https://mlsanity.com/paper/1807.07134/) (2018)

## Abstract (arXiv)

Humans can learn and generalize novel concepts from sparse data because they express knowledge in rich structural formats. In this paper, we propose that programs are a strong candidate for universal representation of concepts. We review computational models of concept learning that use programs as their concept representation and evaluate their contribution toward a universal representational language.