1 citations · 1 across the 5 of their papers we have counts for
3 papers · 1 filter
Progressive Misalignment Can Emerge from Benign Recursive Self-Distillation
Karim Abdel Sadek, Federico Di Gennaro, Fanny Yang
Training models on their own outputs has attracted widespread attention as a possible route to advance AI capabilities. One prominent approach is self-distillation, where a model i…
Mitigating Goal Misgeneralization via Minimax Regret
Karim Abdel Sadek, Matthew Farrugia-Roberts, Usman Anwar +4
Safe generalization in reinforcement learning requires not only that a learned policy acts capably in new situations, but also that it uses its capabilities towards the pursuit of…
Algorithms for Caching and MTS with reduced number of predictions
Karim Abdel Sadek, Marek Elias
ML-augmented algorithms utilize predictions to achieve performance beyond their worst-case bounds. Producing these predictions might be a costly operation -- this motivated Im et a…