AI & ML interests

We build tools to understand how models change during training, identify where regressions and unwanted behaviors emerge, localize meaningful changes within the model, and correct or remove learned behavior without full retraining.Our work spans training dynamics, model interpretability, machine unlearning, training-free model optimization, and AI governance.

Recent Activity

seanhagstrom  updated a model about 2 months ago
authentrics/ztom-gemma3-1b-recovery
seanhagstrom  updated a model about 2 months ago
authentrics/pii-removal-medical-llama32
seanhagstrom  updated a Space about 2 months ago
authentrics/README
View all activity

Articles

brandon-authentrics 
published an article 2 months ago
view article
Article

Accelerating model refinement: automating Fine-Tuning through checkpoint interpolation with Authentrics Zero Training Optimization & Maintenance (Z-TOM)

authentrics
•