{"slug": "torchcurves-differentiable-parametric-curves", "title": "TorchCurves: Differentiable Parametric Curves", "summary": "A PyTorch library called TorchCurves treats vector-valued parametric curves as learnable primitives, mapping batches of scalar inputs to points on curves represented in B-spline or Legendre polynomial bases with differentiation through both inputs and coefficients. The library's central operation makes curve coefficients trainable alongside network weights, positioning curves as first-class components in differentiable pipelines.", "body_md": "We present TorchCurves, a PyTorch library that treats vector-valued parametric curves as learnable primitives. Its central operation maps batches of scalar inputs to points on curves represented in B-spline or Legendre polynomial bases, with differentiation through both inputs and coefficients. Curv", "url": "https://wpnews.pro/news/torchcurves-differentiable-parametric-curves", "canonical_source": "https://aiflash.com/news/149751/", "published_at": "2026-11-11 13:00:05+00:00", "updated_at": "2026-11-11 13:23:43.900309+00:00", "lang": "en", "topics": ["machine-learning", "ai-research", "developer-tools", "artificial-intelligence"], "entities": ["TorchCurves", "PyTorch", "B-spline", "Legendre polynomial"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/torchcurves-differentiable-parametric-curves", "markdown": "https://wpnews.pro/news/torchcurves-differentiable-parametric-curves.md", "text": "https://wpnews.pro/news/torchcurves-differentiable-parametric-curves.txt", "jsonld": "https://wpnews.pro/news/torchcurves-differentiable-parametric-curves.jsonld"}}