2 papers
cs.CV2026
Task-Induced Riemannian Metrics for Vision Transformer Feature Spaces
Andrew Bond, Ege Erdem Özlü, Tuna Çimen +4
Methods operating on Vision Transformer (ViT) feature spaces typically rely on Euclidean distance or cosine similarity. This assumes that every direction is equally meaningful, but…
cs.CV2026
Beyond Gaussian Bottlenecks: Topologically Aligned Encoding of Vision-Transformer Feature Spaces
Andrew Bond, Ilkin Umut Melanlioglu, Erkut Erdem +1
Modern visual world modeling systems increasingly rely on high-capacity architectures and large-scale data to produce plausible motion, yet they often fail to preserve underlying 3…