mlsanityData to 7 Oct 2026

PatentVision: A multimodal method for drafting patent applications

arXiv 2510.09762 ↗First posted 10 Oct 2025cs.LG cs.AIcited by 1

On the map: Multimodal LLMs / vision-language models → Chart understanding and anomaly detection

Abstract (arXiv)

Patent drafting is complex due to its need for detailed technical descriptions, legal compliance, and visual elements. Although Large Vision Language Models (LVLMs) show promise across various tasks, their application in automating patent writing remains underexplored. In this paper, we present PatentVision, a multimodal framework that integrates textual and visual inputs such as patent claims and drawings to generate complete patent specifications. Built on advanced LVLMs, PatentVision enhances accuracy by combining fine tuned vision language models with domain specific training tailored to patents. Experiments reveal it surpasses text only methods, producing outputs with greater fidelity and alignment with human written standards. Its incorporation of visual data allows it to better represent intricate design features and functional connections, leading to richer and more precise results. This study underscores the value of multimodal techniques in patent automation, providing a scalable tool to reduce manual workloads and improve consistency. PatentVision not only advances patent drafting but also lays the groundwork for broader use of LVLMs in specialized areas, potentially transforming intellectual property management and innovation processes.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Chart understanding and anomaly detection, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 15 of its 34 references that are in the map. First posted on arXiv 10 Oct 2025.

Builds on

15 of 34 references.

References · 15

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  3. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  4. 2020Longformer: The Long-Document Transformercited by 3,362
  5. 2025Gemma 3 Technical Reportcited by 1,686
  6. 2020Big Bird: Transformers for Longer Sequencescited by 1,673
  7. 2020Linformer: Self-Attention with Linear Complexitycited by 1,462
  8. 2022BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Miningcited by 531
  9. 2022Pretrained Language Models for Text Generation: A Surveycited by 121
  10. 2019Patent Claim Generation by Fine-Tuning OpenAI GPT-2cited by 49
  11. 2021Hi-Transformer: Hierarchical Interactive Transformer for Efficient and Effective Long Document Modelingcited by 35
  12. 2024Can Large Language Models Generate High-quality Patent Claims?cited by 19
3 more
  1. 2023PatFig: Generating Short and Long Captions for Patent Figurescited by 12
  2. 2020Prior Art Search and Reranking for Generated Patent Textcited by 8
  3. 2022The Effectiveness of Bidirectional Generative Patent Language Modelscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Benchmarking Patent Drafting from Inventor-Style Disclosurescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025PatentLMM: Large Multimodal Model for Generating Descriptions for Patent Figures
  2. 2025DesignCLIP: Multimodal Learning with CLIP for Design Patent Understanding
  3. 2025PATENTWRITER: A Benchmarking Study for Patent Drafting with LLMs
  4. 2025Patent Figure Classification using Large Vision-language Models
  5. 2025Multimodal LLMs for Historical Dataset Construction from Archival Image Scans: German Patents (1877-1918)
  6. 2025PatentMind: A Multi-Aspect Reasoning Graph for Patent Similarity Evaluation
  7. 2024Large Language Model for Patent Concept Generation
  8. 2025IPBench: Benchmarking the Knowledge of Large Language Models in Intellectual Property