mlsanityData to 14 Oct 2026

Reverse Browser: Vector-Image-to-Code Generator

arXiv 2509.05394 ↗First posted 5 Sep 2025cs.SE cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Automating the conversion of user interface design into code (image-to-code or image-to-UI) is an active area of software engineering research. However, the state-of-the-art solutions do not achieve high fidelity to the original design, as evidenced by benchmarks. In this work, I approach the problem differently: I use vector images instead of bitmaps as model input. I create several large datasets for training machine learning models. I evaluate the available array of Image Quality Assessment (IQA) algorithms and introduce a new, multi-scale metric. I then train a large open-weights model and discuss its limitations.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 29 of its 51 references that are in the map. First posted on arXiv 5 Sep 2025.

Builds on

29 of 51 references.

References · 29

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2023GPT-4 Technical Reportcited by 18,396
  4. 2024The Llama 3 Herd of Modelscited by 14,715
  5. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  6. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  7. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  8. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  9. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,986
  10. 2020Image Quality Assessment: Unifying Structure and Texture Similaritycited by 811
  11. 2021OCR-free Document Understanding Transformercited by 407
  12. 2022Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understandingcited by 366
17 more
  1. 2021LongT5: Efficient Text-To-Text Transformer for Long Sequencescited by 232
  2. 2023TOPIQ: A Top-down Approach from Semantics to Distortions for Image Quality Assessmentcited by 226
  3. 2016Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessmentcited by 225
  4. 2013Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Indexcited by 195
  5. 2018PieAPP: Perceptual Image-Error Assessment through Pairwise Preferencecited by 160
  6. 2025Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domainscited by 156
  7. 2023Teaching Arithmetic to Small Transformerscited by 123
  8. 2017pix2code: Generating Code from a Graphical User Interface Screenshotcited by 114
  9. 2024Transformers Can Do Arithmetic with the Right Embeddingscited by 78
  10. 2022Attentions Help CNNs See Better: Attention-based Hybrid Image Quality Assessment Networkcited by 57
  11. 2024WebCode2M: A Real-World Dataset for Code Generation from Webpage Designscited by 44
  12. 2021Learning Conditional Knowledge Distillation for Degraded-Reference Image Quality Assessmentcited by 41
  13. 2024Pre-trained Large Language Models Use Fourier Features to Compute Additioncited by 39
  14. 2025UICopilot: Automating UI Synthesis via Hierarchical Code Generation from Webpage Designscited by 22
  15. 2019Sketch2code: Generating a website from a paper mockupcited by 20
  16. 2024Image2Struct: Benchmarking Structure Extraction for Vision-Language Modelscited by 19
  17. 2024Examining the Use and Impact of an AI Code Assistant on Developer Productivity and Experience in the Enterprisecited by 17

Built on by

Not cited yet.