Felix Friedrich is a Postdoctoral Researcher at Meta FAIR focusing on multimodal generative AI. Holding a PhD from the Technische Universität Darmstadt, his research centers on AI alignment, safety, and interpretability. He has recently gained significant recognition, with two papers accepted at NeurIPS 2025, one earning a prestigious Spotlight award.
His academic pursuits include exploring how cognitive science can improve AI and making AI systems more socially acceptable by addressing biases in training data. Felix is passionate about incorporating a human-in-the-loop approach to better understand and control model representations, aiming to enhance fairness and safety in future AI models.
His research on demystifying large language models by measuring and guiding monosemanticity was recognized as a top 3% Spotlight paper at NeurIPS 2025.
Read the full overview →Behavioral traits and communication patterns that shape how this person evaluates opportunities, builds trust, and makes decisions in professional settings.
Dominance, influence, steadiness, and calculativeness scores with guidance on how this person prefers to communicate and decide.
Explore more public profiles from related professionals.
Discover additional public profiles from our index.
Looking for someone else? Search here for anyone.