Contextual inference from single objects in Vision-Language models

Martina G. Vilas, Timothy Schaumlöffel, Gemma RoigarXiv 2026 · DOI

BibTeX
@misc{vilas2026contextual,
  author = {Martina G. Vilas and Timothy Schaumlöffel and Gemma Roig},
  title = {{Contextual inference from single objects in Vision-Language models}},
  year = {2026},
  doi = {10.48550/arxiv.2603.26731},
}

Loading related content...

Figure