HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusion: https://ziyaerkoc.com/hyperdiffusion/ “We propose HyperDiffusion, a novel approach for unconditional generative modeling of implicit neural fields. HyperDiffusion operates directly on MLP weights and generates new neural implicit fields encoded by synthesized MLP parameters. Specifically, a collection of MLPs is first optimized to faithfully represent individual data samples.”