About
Research & Development
Detail++: Mastering Attribute Control in AI Image Creation
TLDR: Detail++ is a novel, training-free framework that significantly enhances text-to-image diffusion models' ability to handle complex prompts. It uses a Progressive Detail Injection...
Research & Development
Designing Porous Materials with AI: A Deep Learning Approach
TLDR: This research introduces a deep learning framework called Property-Variational Autoencoder (pV AE) for the inverse design of porous metamaterials. It uses VAEs augmented...
Research & Development
AI and Human Collaboration: A New Approach to Testing Text-to-Image Models
TLDR: A new method called Seed2Harvest combines human-crafted adversarial prompts with AI-driven expansion to create a large, diverse dataset for red-teaming text-to-image models. This...
Research & Development
Assessing Post Quality: A New Multimodal Approach Mimics Human Reasoning
TLDR: The Multimodal Fine-grained Topic-post Relational Reasoning (MFTRR) framework is a new method for evaluating the quality of online discussion forum posts. It mimics...
Research & Development
Unveiling MeAJOR Corpus: A Comprehensive Dataset for Smarter Phishing Detection
TLDR: The MeAJOR Corpus is a new, large-scale dataset of 135,894 phishing and legitimate emails designed to improve the accuracy of machine learning models...
Research & Development
Understanding How Teachers Engage with AI in the Classroom: Insights from a Large-Scale Study
TLDR: A new study reveals how teachers are using AI tools in K-12 education through a large-scale analysis of over 140,000 teacher-AI messages. The...