← Search

Idriss Malek

2 accepted papers

2026

Loss-Guided Auxiliary Agents for Overcoming Mode Collapse in GFlowNets

AAAI 2026technical

Although Generative Flow Networks (GFlowNets) are designed to capture multiple modes of a reward function, they often suffer from mode collapse in practice, getting trapped in early-discovered modes and requiring prolonged training to find diverse solutions. Existing exploration techniques often rel

Cited by 0SourcePDFScholar
2025

Free Lunch in the Forest: Functionally-Identical Pruning of Boosted Tree Ensembles

AAAI 2025technical

Tree ensembles, including boosting methods, are highly effective and widely used for tabular data. However, large ensembles lack interpretability and require longer inference times. We introduce a method to prune a tree ensemble into a reduced version that is "functionally identical" to the original…

Cited by 0SourcePDFScholar