HyperVis: Continuous Latent Visual Relational Graphs on the Lorentz Hyperboloid for Compositional Reasoning 事件

HyperVis: Continuous Latent Visual Relational Graphs on the Lorentz Hyperboloid for Compositional Reasoning arXiv:2606.06100v1 Announce Type: new Abstract: Vision-Language Models (VLMs) struggle with compositional reasoning that requires understanding inter-object relationships. A natural remedy is to inject explicit scene graph triplets $\langle s, p, o \rangle$ from an off-the-shelf scene graph generator (SGG), but we show this backfires: discrete text labels collide with the continuous visua