<ul><li>Foundation models for 3D shape generation can encode rich geometric priors across global and local dimensions.</li><li>Leveraging these priors for downstream tasks is challenging in real-world scenarios with scarce or noisy data.</li><li>Treating the weight space of a 3D shape-generative model as a data modality can be explored directly.</li><li>The high-dimensional weight space can modulate topological properties or fine-grained part features, enabling new approaches for 3D shape generation and specialized fine-tuning.</li></ul>

Shape Generation via Weight Space Learning

Discover more