TorchCurves treats parametric curves as learnable PyTorch primitives
The library maps scalar batches to B-spline or Legendre curves and differentiates through inputs and coefficients.
Stories per day · 30 days
4 stories, newest first · one card per story
Stories tagged #splines
On the estimation and validity of AI time horizons---a statistical look at the METR plot
Paper recomputes METR AI time horizons with splines and item-response theory across 228 tasks.
Vela: Scaling Vision-Language-Action Models with Adaptive Action Curve Parametrization
Vela models robot actions as adaptive continuous trajectories and reports gains on simulation and real manipulation tasks.
NeuSOGA3D: A Neuro-Symbolic Framework for Explainable 3D Geometric Reconstruction
NeuSOGA3D combines learned perception with symbolic spline reasoning to produce explainable, CAD-compatible 3D reconstructions from point clouds across all forty ModelNet40 categories.