Inferring Attribute Subspaces from Visual Contexts

Nick Stracke, Kolja Bauer, Stefan Andreas Baumann, Miguel Ángel Bautista, Joshua M. Susskind, Björn OmmerOpenReview 2026 · Submission to ICLR 2026 · Withdrawn · OpenReview

Its authors withdrew this paper, so there is no full text to read or summarize.

Abstract

Recent advances in generative vision-language models have demonstrated remarkable capabilities in image synthesis, captioning, and multi-modal reasoning. Among their most intriguing behaviors is in-context learning, the ability to adapt to new tasks from just a few examples. While well-studied in language models, this capability remains underexplored in the visual domain. Motivated by this, we explore how generative vision models can infer and apply visual concepts directly from image sets, without relying on text or labels. We frame this as an attribute subspace inference task: given a small set of related images, the model identifies the shared variation and uses it to guide generation from a query image. During training, we use auxiliary groupings to provide weak structural supervision. At inference time, the model receives only unlabeled inputs and must generalize the visual concept based on example images alone. Our approach enables attribute-consistent image generation and contributes a novel direction for nonverbal concept learning in vision.
BibTeX
@misc{stracke2026inferring,
  author = {Nick Stracke and Kolja Bauer and Stefan Andreas Baumann and Miguel Ángel Bautista and Joshua M. Susskind and Björn Ommer},
  title = {{Inferring Attribute Subspaces from Visual Contexts}},
  year = {2026},
  url = {https://openreview.net/forum?id=sL0gkGGhLL},
  howpublished = {OpenReview},
  note = {Submitted to ICLR 2026},
}

Loading related content...

Figure