BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CIG Group//Talk Calendar//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
UID:talk-166@theciggroup.net
DTSTAMP:20260804T224752Z
DTSTART:20260806T140000Z
DTEND:20260806T150000Z
SUMMARY:Categorical Flow Maps
DESCRIPTION:We introduce Categorical Flow Maps\, a flowmatching 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 stateof-the-art few-step results on images\, molecular graphs\, and text\, with strong performance even in single-step generation.&nbsp\;\n\nSpeaker: Floor Eijkelboom
LOCATION:Online — Computational Intelligence Reading Group
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR