About
Research & Development
Enhancing Traffic Safety Data: AI Models Improve Crash Narrative Analysis in Kentucky
TLDR: A study evaluated different AI models, including large language models (LLMs) and fine-tuned transformers, for improving the accuracy of police-reported crash data by...
Research & Development
Unpacking Emergence: Why Large Language Models Develop Unexpected Abilities
TLDR: A research paper by VladimÃr HavlÃk explores why Large Language Models (LLMs) exhibit "emergent abilities" – capabilities that appear unexpectedly without explicit training....
Research & Development
Advancing Building Energy Renovation with Image-to-3D Facade Modeling
TLDR: The Scalable Image-to-3D Facade Parser (SI3FP) is a new pipeline that uses deep learning and computer vision to create detailed 3D thermal models...
Research & Development
Unraveling AI’s Multimodal Decisions: A Review of Explainability in Attention Models
TLDR: This systematic review examines how explainable AI (XAI) is applied to multimodal attention-based models, which process various data types like text and images....
Research & Development
ThinkingF: A New Approach to Automate Mathematical Formalization with AI
TLDR: The research paper introduces ThinkingF, a novel data synthesis and training pipeline designed to significantly improve the accuracy of autoformalization, the process of...
Research & Development
Developing Curriculum-Aligned Math Assessments Using Generative AI in Malaysia
TLDR: This research explores using Generative AI, specifically OpenAI's GPT-4o, to create curriculum-aligned multiple-choice questions for Malaysian secondary mathematics in Bahasa Melayu. It compares...