MATS (ML Alignment & Theory Scholars)
Training
Active
Tier 1
Overview
MATS is a research training program explicitly focused on advancing model safety research (control, interpretability, oversight, evaluations, red teaming). Its own materials clearly position it as an AI safety field-building pipeline.
Mission & Focus
Primary Focus
Training
Scope of Safety
Research training program in model safety: control, interpretability, oversight, evals/red teaming, robustness.
Key Programs / Outputs
Alignment research scholars programMentorship cohortsInterpretability trainingRed teaming curriculum
Organisation
Type
Program
Status
Active
Funding Signals
Unknown
Partners / Customers
Unknown
Data Provenance
Scope Confidence
High
Data Confidence
High
Last Verified
2026-03-22
ID
AISF-0010
Primary Sources