Arioron Labs
Research.
Applied research with a bias toward constraint. Weights, datasets and evaluation code are published so the claims can be checked.
From the newsroom
A New Arioron: Rebuilding Our Digital Home
Small Language Models Aren’t Dead. They’re Becoming More Interesting.
The Reasoning Problem: Why Getting the Right Answer Isn’t Enough
All news
All publications
OncoDetect Titan: robustness over benchmark fit in lung cancer detection
A multi-model ensemble for lung cancer detection, trained explicitly on degraded and inconsistent scan data. We argue that robustness to real hospital conditions matters more than benchmark...
Vex-Amber-Mini: reasoning at 0.6B parameters
A 0.6-billion-parameter model optimised for code generation and general text tasks on constrained hardware, with notes on the distillation approach and where it fails.