SOURCE-LINKED INTELLIGENCE

Modeling What Changes: Sparse, Residual World Models for Object-Centric Manipulation

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

Monolithic world models predict the entire next state at every step, spending capacity re-predicting the static majority of a scene and injecting error into it. We ask whether explicitly modeling change (a per-object change gate plus a residual delta head that perturbs only the objects the gate flags) is a more effective and interpretable bias for physical prediction and control. On a MuJoCo tabletop pushing benchmark scaling from 3 to 8 objects, the sparse/residual model predicts next-state poses 2.5 to 4.6 times more accurately than a dense multilayer perceptron at 8.6 to 11.1 times fewer pa

Read original source ↗ Open in workspace

recordType

paper

region

Global