Author

Ming-Xin Yang

h-index 6 View on Semantic Scholar

We have 1 of 19 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

Align-VAE: Aligning Attention and Geometry in VecSet VAEs for 3D Reconstruction

Set-based variational autoencoders (VecSet VAEs) represent 3D shapes as compact sets of latent tokens. Although each token originates from a query at a sampled surface location, whether these latents truly align with geometry remains unclear. We investigate this alignment and identify four issues: (i) attention-sink-li...

Huai-Zhi Qu, Ming-Xin Yang, Xin-Tong Han et al. · 0 citations