2 papers
cs.LG2025
INTELLECT-3: Technical Report
Prime Intellect Team, Mika Senghaas, Fares Obeid +20
We present INTELLECT-3, a 106B-parameter Mixture-of-Experts model (12B active) trained with large-scale reinforcement learning on our end-to-end RL infrastructure stack. INTELLECT-…
math.CO2024
Some Winnability Results for the Neighborhood and Group Labeling Lights Out Games
Brittany Doherty, Christian J. Miller, Darren B. Parker
We look at both the \emph{group labeling lights out game} and the \emph{neighborhood lights out game}. Our main focus is to determine necessary and sufficient conditions for when t…