# DLPaper2Code: Auto-generation of Code from Deep Learning Research Papers

arXiv: https://arxiv.org/abs/1711.03543 · HTML: https://mlsanity.com/paper/1711.03543/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Nov 2017.

## Built on by (most cited first, 8 of 8)

- [Randomness In Neural Network Training: Characterizing The Impact of Tooling](https://mlsanity.com/paper/2106.11872/) (2021)
- [SciReplicate-Bench: Benchmarking LLMs in Agent-driven Algorithmic Reproduction from Research Papers](https://mlsanity.com/paper/2504.00255/) (2025)
- [When Bioprocess Engineering Meets Machine Learning: A Survey from the Perspective of Automated Bioprocess Development](https://mlsanity.com/paper/2209.01083/) (2022)
- [An Exploratory Study of ML Sketches and Visual Code Assistants](https://mlsanity.com/paper/2412.13386/) (2024)
- [HyperPIE: Hyperparameter Information Extraction from Scientific Publications](https://mlsanity.com/paper/2312.10638/) (2023)
- [ReproAgent: Contract-Guided Paper-to-Code Reproduction](https://mlsanity.com/paper/2608.24291/) (2026)
- [Advances in Electron Microscopy with Deep Learning](https://mlsanity.com/paper/2101.01178/) (2021)
- [Hyperparameter Optimization and Reproducibility in Deep Learning Model Training](https://mlsanity.com/paper/2510.15164/) (2025)

## Abstract (arXiv)

With an abundance of research papers in deep learning, reproducibility or adoption of the existing works becomes a challenge. This is due to the lack of open source implementations provided by the authors. Further, re-implementing research papers in a different library is a daunting task. To address these challenges, we propose a novel extensible approach, DLPaper2Code, to extract and understand deep learning design flow diagrams and tables available in a research paper and convert them to an abstract computational graph. The extracted computational graph is then converted into execution ready source code in both Keras and Caffe, in real-time. An arXiv-like website is created where the automatically generated designs is made publicly available for 5,000 research papers. The generated designs could be rated and edited using an intuitive drag-and-drop UI framework in a crowdsourced manner. To evaluate our approach, we create a simulated dataset with over 216,000 valid design visualizations using a manually defined grammar. Experiments on the simulated dataset show that the proposed framework provide more than 93% accuracy in flow diagram content extraction.