Emmanuel Müller

Unlock explainable outlier detection in foundation models with FoMo-X, a modular framework that adds negligible inference overhead while revealing interpretable risk tiers and calibrated confidence measures.

Anomaly detection gets a dose of interpretability: SYRAN learns human-readable equations that flag anomalies by violating learned invariants.

Ditch the separate anomaly detection model: your existing ML model already holds the keys to faster, better anomaly detection.

Reinforcement learning unlocks fast, high-quality consensus ranking aggregation, outperforming classical heuristics and ILP solvers for the NP-hard Kemeny optimization problem.