Research map / Vision-language and multimodal / Human and embodied modeling
DocEdit: Language-Guided Document Editing
Puneet Mathur, Rajiv Jain, Jiuxiang Gu, Franck Dernoncourt, Dinesh Manocha, Vlad I. Morariu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use DocEditor instead of the strongest command-generation baseline | DocEdit-PDF command generation · DocEdit-PDF | EM (%): 31.6 -> 37.6 | Improved |
| Use DocEditor instead of the strongest command-generation baseline | DocEdit-Design command generation · DocEdit-Design | EM (%): 32.8 -> 38.2 | Improved |
| Use DocEditor instead of TransVG | DocEdit-PDF region-of-interest prediction · DocEdit-PDF | Top-1 Acc (%): 25.34 -> 36.50 | Improved |
| Use DocEditor instead of TransVG | DocEdit-Design region-of-interest prediction · DocEdit-Design | Top-1 Acc (%): 24.89 -> 34.34 | Improved |
| Add text embedding (ablation) | DocEditor command generation · DocEdit-PDF | EM (%): 6.7 -> 37.6 | Improved |
| Add text embedding (ablation) | DocEditor command generation · DocEdit-Design | EM (%): 6.1 -> 38.2 | Improved |
| Add visual embedding (ablation) | DocEditor command generation · DocEdit-PDF | EM (%): 33.6 -> 37.6 | Improved |
| Add layout graph (ablation) | DocEditor region-of-interest prediction · DocEdit-PDF | Top-1 Acc (%): 14.48 -> 36.50 | Improved |
| Add bounding box regression loss (ablation) | DocEditor command generation · DocEdit-PDF | EM (%): 33.6 -> 37.6 | Improved |
| Add anchor box prediction loss (ablation) | DocEditor command generation · DocEdit-Design | EM (%): 35.0 -> 38.2 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- TransVG — TransVG: End-to-End Visual Grounding With Transformers (ICCV 2021) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- ComprehendEdit: A Comprehensive Dataset and Evaluation Framework for Multimodal Knowledge Editing (AAAI 2025 · similarity 0.87)
- ImgEdit: A Unified Image Editing Dataset and Benchmark (NeurIPS 2025 · similarity 0.85)
- MMKE-Bench: A Multimodal Editing Benchmark for Diverse Visual Knowledge (ICLR 2025 · similarity 0.85)
- Text-Driven Image Editing via Learnable Regions (CVPR 2024 · similarity 0.84)
- AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models (ICLR 2025 · similarity 0.84)
- DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understanding (CVPR 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
