MATS (ML Alignment & Theory Scholars)
TrainingActiveTier 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 FocusTraining
Scope of SafetyResearch training program in model safety: control, interpretability, oversight, evals/red teaming, robustness.
Key Programs / OutputsAlignment research scholars programMentorship cohortsInterpretability trainingRed teaming curriculum
Organisation
TypeProgram
StatusActive
Funding SignalsUnknown
Partners / CustomersUnknown
Data Provenance
Scope ConfidenceHigh
Data ConfidenceHigh
Last Verified2026-03-22
IDAISF-0010
Primary Sources