Daan Roos

2 accepted papers

2026

Categorical Flow Maps

Daan Roos, Oscar Davis, Floor Eijkelboom, Michael Bronstein, Max Welling, Ismail Ceylan +2

ICML 2026poster

We introduce Categorical Flow Maps, a flow-matching method for accelerated few-step generation of categorical data via self-distillation. Building on recent variational formulations of flow matching and the broader trend towards accelerated inference in diffusion and flow-based models, we define a f…

Cited by 0 Source ↗Scholar ↗

2023

Deterministic training of generative autoencoders using invertible layers

Gianluigi Silvestri, Daan Roos, Luca Ambrogioni

ICLR 2023top-25%

In this work, we provide a deterministic alternative to the stochastic variational training of generative autoencoders. We refer to these new generative autoencoders as AutoEncoders within Flows (AEF), since the encoder and decoder are defined as affine layers of an overall invertible architecture.…

Cited by 4 Source ↗PDF ↗code ↗Scholar ↗