mlsanityData to 7 Oct 2026

Autoencoders as Tools for Program Synthesis

arXiv 2108.07129 ↗First posted 16 Aug 2021cs.AI cs.PLcited by 4

Not on the map. Why?

Abstract (arXiv)

Recently there have been many advances in research on language modeling of source code. Applications range from code suggestion and completion to code summarization. However, complete program synthesis of industry-grade programming languages remains an open problem. In this work, we introduce and experimentally validate a variational autoencoder model for program synthesis of industry-grade programming languages. This model makes use of the inherent tree structure of code and can be used in conjunction with gradient free optimization techniques like evolutionary methods to generate programs that maximize a given fitness function, for instance, passing a set of test cases. A demonstration is avaliable at https://tree2tree.app

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 25 of its 42 references that are in the map. First posted on arXiv 16 Aug 2021.

Builds on

25 of 42 references.

References · 25

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2013Auto-Encoding Variational Bayescited by 3,980
  3. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  4. 2019An Introduction to Variational Autoencoderscited by 997
  5. 2015Generating Sentences from a Continuous Spacecited by 607
  6. 2015Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networkscited by 305
  7. 2017Grammar Variational Autoencodercited by 283
  8. 2019Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishingcited by 191
  9. 2018Tree-to-tree Neural Networks for Program Translationcited by 93
  10. 2017Abstract Syntax Networks for Code Generation and Semantic Parsingcited by 92
  11. 2016Efficient softmax approximation for GPUscited by 67
  12. 2014Variational Recurrent Auto-Encoderscited by 53
13 more
  1. 2019On Learning Meaningful Code Changes via Neural Machine Translationcited by 50
  2. 2017Code Completion with Neural Attention and Pointer Networkscited by 49
  3. 2019Program Synthesis and Semantic Parsing with Learned Code Idiomscited by 34
  4. 2018Variational Autoencoder with Implicit Optimal Priorscited by 33
  5. 2018Aroma: Code Recommendation via Structural Code Searchcited by 29
  6. 2015A Hierarchical Neural Autoencoder for Paragraphs and Documentscited by 26
  7. 2018Automatic Software Repair: a Bibliographycited by 24
  8. 2018Attention-Based LSTM for Psychological Stress Detection from Spoken Language Using Distant Supervisioncited by 8
  9. 2019On Posterior Collapse and Encoder Feature Dispersion in Sequence VAEscited by 5
  10. 2019Structural Language Models of Codecited by 3
  11. 2020A Comparison of Pooling Methods on LSTM Models for Rare Acoustic Event Classificationcited by 3
  12. 2021Neurogenetic Programming Framework for Explainable Reinforcement Learningcited by 2
  13. 2016Learning to superoptimize programs - Workshop Versioncited by 1

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2; 2024: 0; 2025: 1.

4 papers.

  1. 2023Fully Autonomous Programming with Large Language Modelscited by 31
  2. 2025Fully Autonomous Programming using Iterative Multi-Agent Debugging with Large Language Modelscited by 3
  3. 2022BenchPress: A Deep Active Benchmark Generatorcited by 2
  4. 2023BenchDirect: A Directed Language Model for Compiler Benchmarkscited by 0