# CoGen: Creation of Reusable UI Components in Figma via Textual Commands

arXiv: https://arxiv.org/abs/2601.10536 · HTML: https://mlsanity.com/paper/2601.10536/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 36 references that are in the map.
- First posted on arXiv 15 Jan 2026.

## Builds on (most cited first, 13 of 13)

- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [Screen2Words: Automatic Mobile UI Summarization with Multimodal Learning](https://mlsanity.com/paper/2108.03353/) (2021)
- [Machine Learning-Based Prototyping of Graphical User Interfaces for Mobile Apps](https://mlsanity.com/paper/1802.02312/) (2018)
- [Sketch2Code: Transformation of Sketches to UI in Real-time Using Deep Neural Network](https://mlsanity.com/paper/1910.08930/) (2019)
- [GUIGAN: Learning to Generate GUI Designs Using Generative Adversarial Networks](https://mlsanity.com/paper/2101.09978/) (2021)
- [UI Layout Generation with LLMs Guided by UI Grammar](https://mlsanity.com/paper/2310.15455/) (2023)
- [Boosting GUI Prototyping with Diffusion Models](https://mlsanity.com/paper/2306.06233/) (2023)
- [Auto Completion of User Interface Layout Design Using Transformer-Based Tree Decoders](https://mlsanity.com/paper/2001.05308/) (2020)
- [Creating User Interface Mock-ups from High-Level Text Descriptions with Deep-Learning Models](https://mlsanity.com/paper/2110.07775/) (2021)
- [Prompt Middleware: Mapping Prompts for Large Language Models to UI Affordances](https://mlsanity.com/paper/2307.01142/) (2023)
- [Magic Layouts: Structural Prior for Component Detection in User Interface Designs](https://mlsanity.com/paper/2106.07615/) (2021)
- [Understanding and Supporting the Design Systems Practice](https://mlsanity.com/paper/2205.10713/) (2022)
- [Reimagining Application User Interface (UI) Design using Deep Learning Methods: Challenges and Opportunities](https://mlsanity.com/paper/2303.13055/) (2023)

## Built on by (most cited first, 2 of 2)

- [GameUIAgent: An LLM-Powered Framework for Automated Game UI Design with Structured Intermediate Representation](https://mlsanity.com/paper/2603.14724/) (2026)
- [FigmaTrace: Capturing Creative Nuances in Human Figma Design Workflows](https://mlsanity.com/paper/2608.21460/) (2026)

## Abstract (arXiv)

The evolution of User Interface design has emphasized the need for efficient, reusable, and editable components to ensure an efficient design process. This research introduces CoGen, a system that uses machine learning techniques to generate reusable UI components directly in Figma, one of the most popular UI design tools. Addressing gaps in current systems, CoGen focuses on creating atomic components such as buttons, labels, and input fields using structured JSON and natural language prompts. The project integrates Figma API data extraction, Seq2Seq models, and fine-tuned T5 transformers for component generation. The key results demonstrate the efficiency of the T5 model in prompt generation, with an accuracy of 98% and a BLEU score of 0.2668, which ensures the mapping of JSON to descriptive prompts. For JSON creation, CoGen achieves a success rate of up to 100% in generating simple JSON outputs for specified component types.