4 papers
Assessing Sample Quality in Conditional Generation under Compositional Shift
Berker Demirel, Valentino Maiorca, Marco Fumero +2
Conditional generators provide a natural tool for controllable generation, including settings where the desired condition is a new composition of observed attributes or experimenta…
MorphGen: Controllable and Morphologically Plausible Generative Cell-Imaging
Berker Demirel, Marco Fumero, Theofanis Karaletsos +1
Simulating in silico cellular responses to interventions is a promising direction to accelerate high-content image-based assays, critical for advancing drug discovery and gene edit…
Out-of-Distribution Detection with Relative Angles
Berker Demirel, Marco Fumero, Francesco Locatello
Deep learning systems deployed in real-world applications often encounter data that is different from their in-distribution (ID). A reliable model should ideally abstain from makin…
Adjusting Pretrained Backbones for Performativity
Berker Demirel, Lingjing Kong, Kun Zhang +3
With the widespread deployment of deep learning models, they influence their environment in various ways. The induced distribution shifts can lead to unexpected performance degrada…