Machine Heart

Oct 20, 2026 · Artificial Intelligence

VLMs Encode 3D Scene Topology in Latent Space: NeurIPS 2026 Spotlight Findings

University of Pittsburgh researchers show that vision-language models internally represent 3D scene topology in middle-layer latent spaces, revealed by separating appearance attributes and visualizing spatial structure; Dirichlet energy quantifies neighborhood preservation, and fine-tuning with this loss improves spatial reasoning on benchmarks like VSI-Bench.