# Latent Programmer: Discrete Latent Codes for Program Synthesis

arXiv: https://arxiv.org/abs/2012.00377 · HTML: https://mlsanity.com/paper/2012.00377/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Dec 2020.

## Built on by (most cited first, 18 of 18)

- [Learning to Synthesize Programs as Interpretable and Generalizable Policies](https://mlsanity.com/paper/2108.13643/) (2021)
- [Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generation](https://mlsanity.com/paper/2305.00909/) (2023)
- [Hierarchical Programmatic Reinforcement Learning via Learning to Compose Programs](https://mlsanity.com/paper/2301.12950/) (2023)
- [CrossBeam: Learning to Search in Bottom-Up Program Synthesis](https://mlsanity.com/paper/2203.10452/) (2022)
- [ExeDec: Execution Decomposition for Compositional Generalization in Neural Program Synthesis](https://mlsanity.com/paper/2307.13883/) (2023)
- [Hierarchical Neural Program Synthesis](https://mlsanity.com/paper/2303.06018/) (2023)
- [LambdaBeam: Neural Program Search with Higher-Order Functions and Lambdas](https://mlsanity.com/paper/2306.02049/) (2023)
- [Gradient-Based Program Synthesis with Neurally Interpreted Languages](https://mlsanity.com/paper/2604.18907/) (2026)
- [Gradient-Based Program Repair: Fixing Bugs in Continuous Program Spaces](https://mlsanity.com/paper/2505.17703/) (2025)
- [Synthesizing Programs with Continuous Optimization](https://mlsanity.com/paper/2211.00828/) (2022)
- [AbstractBeam: Enhancing Bottom-Up Program Synthesis using Library Learning](https://mlsanity.com/paper/2405.17514/) (2024)
- [Shedding Light in Task Decomposition in Program Synthesis: The Driving Force of the Synthesizer Model](https://mlsanity.com/paper/2503.08738/) (2025)
- [Program Machine Policy: Addressing Long-Horizon Tasks by Integrating Program Synthesis and State Machines](https://mlsanity.com/paper/2311.15960/) (2023)
- [Beyond Either-Or Reasoning: Transduction and Induction as Cooperative Problem-Solving Paradigms](https://mlsanity.com/paper/2505.14744/) (2025)
- [Latent Programming Horizons in Coding Agents](https://mlsanity.com/paper/2607.05188/) (2026)
- [Iterative Genetic Improvement: Scaling Stochastic Program Synthesis](https://mlsanity.com/paper/2202.13040/) (2022)
- [A Machine Learning Approach Towards SKILL Code Autocompletion](https://mlsanity.com/paper/2312.01921/) (2023)
- [Solver-Aware Decompositions for Programming-by-Example: When Dividing Requires Knowing how to Conquer](https://mlsanity.com/paper/2608.03461/) (2026)

## Abstract (arXiv)

In many sequence learning tasks, such as program synthesis and document summarization, a key problem is searching over a large space of possible output sequences. We propose to learn representations of the outputs that are specifically meant for search: rich enough to specify the desired output but compact enough to make search more efficient. Discrete latent codes are appealing for this purpose, as they naturally allow sophisticated combinatorial search strategies. The latent codes are learned using a self-supervised learning principle, in which first a discrete autoencoder is trained on the output sequences, and then the resulting latent codes are used as intermediate targets for the end-to-end sequence prediction task. Based on these insights, we introduce the Latent Programmer, a program synthesis method that first predicts a discrete latent code from input/output examples, and then generates the program in the target language. We evaluate the Latent Programmer on two domains: synthesis of string transformation programs, and generation of programs from natural language descriptions. We demonstrate that the discrete latent representation significantly improves synthesis accuracy.