AInformed
SearchNewsletter

Archive

All 3,125 AI stories, newest first · page 28 of 131

DrawingVQA: First AI Benchmark Tests Multimodal Models on Real-World Construction Drawings
research

DrawingVQA: First AI Benchmark Tests Multimodal Models on Real-World Construction Drawings

Researchers introduced DrawingVQA, the first benchmark to evaluate multimodal large language models (MLLMs) on real-world construction drawings — a uniquely complex domain fusing abstract geometry, symbols, tables, and technical text. The benchmark uses 33 professional 'Issued for Construction' drawings and 92 expert-crafted questions to test AI's visual-textual reasoning in architecture and civil engineering.

via ArXiv cs.AI#AI#Benchmark#Engineering
CAMMAR: New AI Framework Captures Arabic Metaphors with Cultural Nuance
research

CAMMAR: New AI Framework Captures Arabic Metaphors with Cultural Nuance

Researchers from the University of Washington and NYU Abu Dhabi introduced CAMMAR, a representation learning framework that organizes Arabic meanings into nested lexical, cultural, and metaphorical embedding subspaces. This approach addresses 'semantic smearing' in current Arabic language models and could improve translation, chatbots, and other AI tools for Arabic speakers.

via ArXiv cs.CL#AI#Arabic#Language
Neuro-Symbolic AI Automates LEED Green Building Certification Checks
research

Neuro-Symbolic AI Automates LEED Green Building Certification Checks

Researchers introduced a neuro-symbolic AI pipeline that automates parts of LEED v4.1 BD+C certification by combining small language models with deterministic symbolic checking. The system screens project PDFs, retrieves evidence using credit-specific keyword signatures, and verifies compliance, potentially making sustainable building certification faster and more accessible.

via ArXiv cs.AI#AI#Sustainability#Automation