UvA-Bosch Delta Lab, University of Amsterdam, Amsterdam, Netherlands(阿姆斯特丹大学);Department of Computer Science, University of Oxford, Oxford, UK(牛津大学计算机科学系);Donders Institute for Brain, Cognition and Behaviour, Radboud University(拉德堡德大学大脑与行为研究所)
Daan Roos, Oscar Davis, Floor Eijkelboom, Michael Bronstein, Max Welling, İsmail İlkan Ceylan, Luca Ambrogioni, Jan-Willem van de Meent
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.
Simplex-to-Euclidean Bijections for Categorical Flow Matching
Department of Computer Science, University of Helsinki(赫尔辛基大学计算机科学系);Department of Computer Science, Aalto University(阿莱大学计算机科学系);ELLIS Institute Finland(芬兰ELLIS研究所)
Generating Tabular Data Using Heterogeneous Sequential Feature Forest Flow Matching
AIMS Research and Innovation Center(AIMS研究与创新中心);Mila Québec AI Institute(魁北克AI研究所);Université de Montréal(蒙特利尔大学);SAIT Montreal AI Lab(蒙特利尔SAIT人工智能实验室)
Embedded Graph Flows for Categorical Graph Generation
School of Electrical Engineering and Computer Science, The University of Queensland(昆士兰大学电气工程与计算机科学学院);Institute for Molecular Bioscience, The University of Queensland(昆士兰大学分子生物科学研究所);Chinese Academy of Sciences(中国科学院);Department of Computer Science, City University of Hong Kong(香港城市大学计算机科学系)
Categorical Representation Learning and RG flow operators for algorithmic classifiers
Harvard University(哈佛大学);University of Miami(迈阿密大学);National Research University Higher School of Economics(国立研究型大学高等经济学院);University of California San Diego(加州大学圣地亚哥分校);QGNai INC.(QGNai公司)