Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2602.12233 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918334752096256 |
|---|---|
| author | Roos, Daan Davis, Oscar Eijkelboom, Floor Bronstein, Michael Welling, Max Ceylan, İsmail İlkan Ambrogioni, Luca van de Meent, Jan-Willem |
| author_facet | Roos, Daan Davis, Oscar Eijkelboom, Floor Bronstein, Michael Welling, Max Ceylan, İsmail İlkan Ambrogioni, Luca van de Meent, Jan-Willem |
| contents | 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 flow map towards the simplex that transports probability mass toward a predicted endpoint, yielding a parametrisation that naturally constrains model predictions. Since our trajectories are continuous rather than discrete, Categorical Flow Maps can be trained with existing distillation techniques, as well as a new objective based on endpoint consistency. This continuous formulation also automatically unlocks test-time inference: we can directly reuse existing guidance and reweighting techniques in the categorical setting to steer sampling toward downstream objectives. Empirically, we achieve state-of-the-art few-step results on images, molecular graphs, and text, with strong performance even in single-step generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_12233 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Categorical Flow Maps Roos, Daan Davis, Oscar Eijkelboom, Floor Bronstein, Michael Welling, Max Ceylan, İsmail İlkan Ambrogioni, Luca van de Meent, Jan-Willem Machine Learning 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 flow map towards the simplex that transports probability mass toward a predicted endpoint, yielding a parametrisation that naturally constrains model predictions. Since our trajectories are continuous rather than discrete, Categorical Flow Maps can be trained with existing distillation techniques, as well as a new objective based on endpoint consistency. This continuous formulation also automatically unlocks test-time inference: we can directly reuse existing guidance and reweighting techniques in the categorical setting to steer sampling toward downstream objectives. Empirically, we achieve state-of-the-art few-step results on images, molecular graphs, and text, with strong performance even in single-step generation. |
| title | Categorical Flow Maps |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2602.12233 |