An international open-source research lab.
We publish artificial intelligence models, data and papers so you can test their results and understand their decisions. Our long-term goal is superintelligence: systems that exceed human reasoning across fields.
Detecting AI-manipulated faces
Detection scores need explanations. We compare training methods and map the facial regions behind predictions.
Detection score (AUC): 0.897 for EfficientNet-B4 with varied and black-masked training images, versus 0.868 for unmodified EfficientNet-B4, on the same deepfake video data (FaceForensics++).
- xdfdet
Eight deepfake detectors, code, explanation maps and a game.
Decision models
We train small models to answer questions and estimate uncertainty in English, Turkish and German.
AI on your own computer
To keep data under your control, we build task assistants for your own computer.
Tholos-2B completes 137 of 160 workspace tests on graphics hardware (Kaggle T4), 25 more than its starting model MiniCPM5-2B. On a computer’s main processor (CPU): 134.
- Tholos
Task assistants sharing tables, notes and a task board.
- reevesagents
Open source software development with AI coding assistants.
Language preservation
One of the best research efforts on language preservation with small local models: we use dictionaries and grammar checks to help preserve languages with few written records.
Eldalambë reads and writes Tolkien’s invented Elvish languages (Quenya and Sindarin) and his Elvish script (Tengwar).
- Eldalambë
Dictionary-checked translation. Private code and models; access by invitation.
5,700+ downloads on Hugging Face and 3,400+ on npm, as of .
Contact
Write to Mert Kaya, who founded the lab.
mertkayacs@gmail.com