# ReGDiff: Exploring Metamaterial Voxel Geometry with Guided Diffusion in a Controlled Latent Space

- Source: 机器之心 · 微信公众号
- Published: 2026-10-22T07:37:56.000Z
- RoboHot: https://robohot.news/en/items/pvgitk5hkwuk6ioksg38ux2q5
- Original: https://mp.weixin.qq.com/s?__biz=MzA3MzI4MjgzMw==&mid=2651069494&idx=3&sn=bcdcad9af473353930e6df3bb3d0c0f5&chksm=855f23db555d30ef0595c34b26895a17df03f3a6c8b9fe17d8fc96b5db6f7714459e7492e71e&scene=126&sessionid=1792687661#rd

## Summary

A team led by Dawei Zhou at Virginia Tech and researchers at Meta propose ReGDiff in a NeurIPS 2026 paper to generate metamaterial voxel structures that satisfy geometric constraints. The method has two steps: first, an RAS mechanism organizes the autoencoder latent space into a form where good and bad structures are clearly separated and good structures are evenly distributed; then, short-range repulsion (SRR) pushes latent variables away from the near neighbors of known samples during sampling, and it takes effect only at inference time.