ReforMe is an interactive document digitization system using layout-aware propagation to generalize user corrections from natural language or direct edits, shown to improve efficiency in a 12-user study on real documents.
arXiv:1903.01949 [cs.CV] https://arxiv.org/abs/1903.01949
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
MultiFinRAG is a multimodal RAG framework that improves accuracy on financial QA tasks involving text, tables, and images by 19 percentage points over ChatGPT-4o while running on commodity hardware.
Single deep neural network trained on synthetic EMNIST-derived data performs joint detection and classification of handwritten Latin letters and reaches 88.28 percent on real exam forms.
citing papers explorer
-
ReforMe: Re-Shaping Documents with Contextual Prompting and Layout-Aware Propagation
ReforMe is an interactive document digitization system using layout-aware propagation to generalize user corrections from natural language or direct edits, shown to improve efficiency in a 12-user study on real documents.
-
MultiFinRAG: An Optimized Multimodal Retrieval-Augmented Generation (RAG) Framework for Financial Question Answering
MultiFinRAG is a multimodal RAG framework that improves accuracy on financial QA tasks involving text, tables, and images by 19 percentage points over ChatGPT-4o while running on commodity hardware.
-
Intelligent Character Recognition of Handwritten Forms with Deep Neural Networks
Single deep neural network trained on synthetic EMNIST-derived data performs joint detection and classification of handwritten Latin letters and reaches 88.28 percent on real exam forms.