Machine Learning Research·2025
Attention-Weighted Learnable KNN
A research journey from hypothesis to honest assessment: discovering that Test-Time Augmentation, not attention, drives calibration improvements in kNN classification.
Our Research Lab
Great technology starts with genuine curiosity. Our research is driven by understanding real problems deeply enough to build solutions that actually work for people.
Research Partners
What We Explore
Intelligent systems that solve real-world problems, from Arabic language tools to visual recognition for industry.
Reliable pipelines to process and protect information so insights reach the right people, securely.
Methods to test and validate ideas before they reach people; proven technology, not just promising.
Powerful systems that keep data private and under your control without sacrificing performance.
Tools that help organizations anticipate what comes next, from supply chains to resource planning.
Exploring how people and AI work together by amplifying human judgment rather than replacing it.
Published Work
A selection of papers from our team, sharing what we have learned along the way.
Machine Learning Research·2025
A research journey from hypothesis to honest assessment: discovering that Test-Time Augmentation, not attention, drives calibration improvements in kNN classification.
Deep Learning Research·2025
Taking the DIAE concept further by breaking the walls between models. A novel architecture where models collaborate during feature extraction — not just at the end.
Join Our Lab
We are looking for curious minds, researchers, engineers, and thinkers who want to work on problems that matter.