Tag
This paper introduces a differentiable training objective based on the Rice level-crossing density from random-field theory, which acts as a mesh-free high-frequency auxiliary loss for implicit neural representations. It requires no grid or FFT, and improves performance on non-uniform samples.
This paper presents FreeForm, a reduced-order simulation method for deformable hyperelastic objects using a Reproducing Kernel Particle Method (RKPM) that achieves 40x faster training and lower error than neural field approaches.
RigidFormer is a new mesh-free, object-centric Transformer model that learns rigid dynamics from point clouds, outperforming mesh-based baselines in speed and scalability for multi-object contact dynamics.