3 papers
cs.CV2026
Enginuity: A Dataset and Benchmark for Vision-Language Understanding of Engineering Diagrams
Abhishek Kumar, Isha Motiyani, Tilak Kasturi +3
Engineering diagrams pose a distinct challenge for vision-language models: unlike natural images or general documents, they encode information through dense spatial layouts, domain…
cs.CV2026
Enginuity: Building an Open Multi-Domain Dataset of Complex Engineering Diagrams
Ethan Seefried, Prahitha Movva, Naga Harshita Marupaka +2
We propose Enginuity - the first open, large-scale, multi-domain engineering diagram dataset with comprehensive structural annotations designed for automated diagram parsing. By ca…
cs.IR2026
Domain-Specific Query Understanding for Automotive Applications: A Modular and Scalable Approach
Isha Motiyani, Abhishek Kumar, Tilak Kasturi
Despite the growing prevalence of large language models (LLMs) in domain-specific applications, the challenge of query understanding in the automotive sector still remains underexp…