CORTEXA
← Browse

Björn Ommer

2 papers indexed

arxivcs.CV2026-07-14

Contrastive-Augmented Flow Matching for Style-Content Disentanglement

Yusong Li, Pingchuan Ma, Ming Gui, Vincent Tao Hu, Björn Ommer

Learning representations that separate content and style is crucial for controllable generation and compositional generalization. However, diffusion and flow-based models trained primarily with generative objectives often produce entangled or misaligned factors. To address this g…

View free PDFSource page
arxivcs.CV2026-07-02

Show Me Examples: Inferring Visual Concepts from Image Sets

Nick Stracke, Kolja Bauer, Stefan Andreas Baumann, Miguel Angel Bautista, Josh Susskind, Björn Ommer

Vision-language models (VLMs) can follow complex textual instructions, yet they struggle to reason from purely visual context. In particular, current models fail to infer shared concepts from sets of example images and apply them to new inputs. We introduce Visual Concept Inferen…

View free PDFSource page