The content introduces a novel paradigm, Compositional Generative Inverse Design (CinDM), for optimizing complex systems through inverse design. It addresses challenges in traditional optimization methods and showcases the effectiveness of diffusion models in achieving compositional generalization. The method is demonstrated in N-body interactions and 2D multi-airfoil design tasks, highlighting its ability to design systems more complex than those seen in training.
Sang ngôn ngữ khác
từ nội dung nguồn
arxiv.org
Thông tin chi tiết chính được chắt lọc từ
by Tailin Wu,Ta... lúc arxiv.org 03-12-2024
https://arxiv.org/pdf/2401.13171.pdfYêu cầu sâu hơn