paper-with-me

Papers

Enginuity: Building an Open Multi-Domain Dataset of Complex Engineering Diagrams

2026-01-19 · Ethan Seefried, Prahitha Movva, Naga Harshita Marupaka, Tilak Kasturi, Tirthankar Ghosal arxiv

We propose Enginuity - the first open, large-scale, multi-domain engineering diagram dataset with comprehensive structural annotations designed for automated diagram parsing. By capturing hierarchical component relationships, connections, and semantic elements across diverse engineering domains, our proposed dataset would enable multimodal large language models to address critical downstream tasks including structured diagram parsing, cross-modal information retrieval, and AI-assisted engineering simulation. Enginuity would be transformative for AI for Scientific Discovery by enabling artificial intelligence systems to comprehend and manipulate the visual-structural knowledge embedded in engineering diagrams, breaking down a fundamental barrier that currently prevents AI from fully participating in scientific workflows where diagram interpretation, technical drawing analysis, and visual reasoning are essential for hypothesis generation, experimental design, and discovery.

📄 PDF Abstract BibTeX arXiv:2601.13299

Code (0)

등록된 구현이 없습니다.

Tasks

Information RetrievalVisual Reasoning

Similar Papers 제목 키워드 기반

Enginuity: A Dataset and Benchmark for Vision-Language Understanding of Engineering Diagrams

2026-06-02 · Abhishek Kumar, Isha Motiyani, Tilak Kasturi, Ethan Seefried 외 arxiv

Engineering diagrams pose a distinct challenge for vision-language models: unlike natural images or general documents, they encode information through dense spatial layouts, domain-specific symbols, and cross-references …

Semantic SimilarityQuestion Answering

Factorized Transformer for Multi-Domain Neural Machine Translation

2020-11-01 · Findings of the Association for Computational Linguistics 2020 · Yongchao Deng, Hongfei Yu, Heng Yu, Xiangyu Duan 외

Multi-Domain Neural Machine Translation (NMT) aims at building a single system that performs well on a range of target domains. However, along with the extreme diversity of cross-domain wording and phrasing style, the im…

DiversityMachine TranslationNMTTranslation

Building a Role Specified Open-Domain Dialogue System Leveraging Large-Scale Language Models

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Recent open-domain dialogue models have brought numerous breakthroughs. However, building a chat system is not scalable since it often requires a considerable volume of human-human dialogue data, especially when enforcin…

Few-Shot Learning

Building a Role Specified Open-Domain Dialogue System Leveraging Large-Scale Language Models

2022-04-30 · NAACL 2022 7 · Sanghwan Bae, Donghyun Kwak, Sungdong Kim, Donghoon Ham 외

Recent open-domain dialogue models have brought numerous breakthroughs. However, building a chat system is not scalable since it often requires a considerable volume of human-human dialogue data, especially when enforcin…

Few-Shot Learning

MIDAS: A Dialog Act Annotation Scheme for Open Domain HumanMachine Spoken Conversations

2021-04-01 · EACL 2021 2 · Dian Yu, Zhou Yu

Dialog act prediction in open-domain conversations is an essential language comprehension task for both dialog system building and discourse analysis. Previous dialog act schemes, such as SWBD-DAMSL, are designed mainly …

Transfer Learning