Author

Benjamin Lo

h-index 0 View on Semantic Scholar

We have 1 of 2 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

Vision Transformers Learn Gestalt-Like Figure-Ground Cues from Natural Images

Evaluating shape-based figure-ground organization in Vision Transformers demonstrates that Gestalt-like figure-ground cues can be learned from natural scene statistics and positions ViTs as a compelling model system for studying the computational mechanisms of perceptual organization.

Matthias Tangemann, Benjamin Lo, Zygmunt Pizlo et al. · arXiv.org · 0 citations