Meltdown: Circuits and Bifurcations in Point-Cloud-Conditioned 3D Diffusion Transformers

ArXi:2602.11130v2 Announce Type: replace Sparse point clouds are a common input modality for 3D surface reconstruction, including in safety-critical settings such as surgical navigation and autonomous perception. Recent point-cloud-conditioned 3D diffusion transformers achieve state-of-the-art results in this regime by leveraging learned priors. We show that these models can fail catastrophically under realistic input variation, and present a mechanistic of why.