SOURCE-LINKED INTELLIGENCE

RelateAnything: Real-Time Open-Vocabulary Relation Prediction From Any Inputs

arXiv · AI, language, vision and robotics · article · Sep 11, 2026 · UTC

Open-vocabulary detection accepts any class list at inference, and promptable segmentation returns regions without class names: the taxonomy has left the model and become an input. Relation prediction has not. Scene-graph models are still trained and evaluated on the 50 or 56 predicates of one annotation style, their relation head conditioned on object labels and so tied to one detector. Three obstacles explain this, none primarily modelling: no relation corpus is both free-text and verified, a label-conditioned architecture cannot accept a vocabulary it was not trained on, and the standard me

Read original source ↗ Open in workspace

recordType

paper

region

Global