2 papers
cs.CV2026
GeoCo-SAVi: Geometry-Consistent Slot Attention for Explicitly Editable Object Representations
Haoxiang Huang, Zhekai Wang, Xiang Liu +2
Object-centric video models represent scenes with slots, yet exposed geometry can vary in meaning with appearance. In Invariant Slot Attention (ISA), explicit position and scale ca…
cs.LG2026
MOSH-WM: Mask-Grounded Soft-Hamiltonian Dynamics for Object-Centric World Models
Zhekai Wang, Haoxiang Huang, Xiang Liu +6
Object-centric world models forecast future videos by evolving a set of entity slots, but the variables receiving dynamics supervision are often unconstrained visual features. We i…