Aram Galstyan

Aram Galstyan is a principal scientist at Amazon AGI Foundations. His research interests include large language models, reinforcement learning, multi-agent systems, and AI safety.

Sources in this wiki

• FLIRT: Feedback Loop In-context Red Teaming

Topics

• AI Safety, Model safety, Reinforcement Learning

Notes

Senior researcher at Amazon AGI Foundations; contributes to work on safety and robustness of generative models.