paper-with-me

홈 › Papers

Towards Making Flowchart Images Machine Interpretable

2025-01-29 · Shreya Shukla, Prajwal Gatti, Yogesh Kumar, Vikash Yadav, Anand Mishra

Computer programming textbooks and software documentations often contain flowcharts to illustrate the flow of an algorithm or procedure. Modern OCR engines often tag these flowcharts as graphics and ignore them in further processing. In this paper, we work towards making flowchart images machine-interpretable by converting them to executable Python codes. To this end, inspired by the recent success in natural language to code generation literature, we present a novel transformer-based framework, namely FloCo-T5. Our model is well-suited for this task,as it can effectively learn semantics, structure, and patterns of programming languages, which it leverages to generate syntactically correct code. We also used a task-specific pre-training objective to pre-train FloCo-T5 using a large number of logic-preserving augmented code samples. Further, to perform a rigorous study of this problem, we introduce theFloCo dataset that contains 11,884 flowchart images and their corresponding Python codes. Our experiments show promising results, and FloCo-T5 clearly outperforms related competitive baselines on code generation metrics. We make our dataset and implementation publicly available.

📄 PDF Abstract BibTeX arXiv:2501.17441

Code (1)

vl2g/floco 공식 구현 pytorch

Tasks

Code GenerationOptical Character Recognition (OCR)TAG

Similar Papers 제목 키워드 기반

JSynFlow: Japanese Synthesised Flowchart Visual Question Answering Dataset built with Large Language Models

2026-02-04 · Hiroshi Sasaki arxiv

Vision and language models (VLMs) are expected to analyse complex documents, such as those containing flowcharts, through a question-answering (QA) interface. The ability to recognise and interpret these flowcharts is in…

Visual Question Answering

FloCA: Towards Faithful and Logically Consistent Flowchart Reasoning

2026-02-15 · Jinzi Zou, Bolin Wang, Liang Li, Shuo Zhang 외 arxiv

Flowchart-oriented dialogue (FOD) systems aim to guide users through multi-turn decision-making or operational procedures by following a domain-specific flowchart to achieve a task goal. In this work, we formalize flowch…

Task-Oriented Dialogue SystemsResponse Generation

EdgeFlow: Edge-Map Augmented VLM-Based Flowchart Processing for Industrial Requirements Engineering

2026-05-26 · Zhifei Dou, Shabnam Hassani, Ou Wei arxiv

Flowcharts are widely used in industrial requirements, but usually remain embedded as static images. Vision Language Models (VLMs) show promise in the conversion of these flowcharts into machine-readable models for RE ac…

Follow the Flow: Fine-grained Flowchart Attribution with Neurosymbolic Agents

2025-06-02 · Manan Suri, Puneet Mathur, Nedim Lipka, Franck Dernoncourt 외

Flowcharts are a critical tool for visualizing decision-making processes. However, their non-linear structure and complex visual-textual relationships make it challenging to interpret them using LLMs, as vision-language …

Automatic Discovery of Interpretable Planning Strategies

2020-05-24 · Julian Skirzyński, Frederic Becker, Falk Lieder

When making decisions, people often overlook critical information or are overly swayed by irrelevant information. A common approach to mitigate these biases is to provide decision-makers, especially professionals such as…

ClusteringDecision MakingImitation LearningProgram induction+2