When Attention Collapses: Residual Evidence Modeling for Compositional Inference

ArXi:2605.02323v1 Announce Type: new Compositional inference - the decomposition of observations into an unknown number of latent components - is central to perception and scientific data analysis. Attention-based models perform well when components are approximately separable, as in object-centric vision. Under additive superposition,. however. - where multiple components contribute to every observation - we identify a structural failure mode we term slot collapse: multiple slots converge to the same dominant component while weaker ones remain unrepresented.