04:00
2026-09-30
arxiv.org
artificial-intelligence
Representation by Design in Generation: Cross-View Class-Token Alignment in Diffusion Transformers
A new arXiv paper (2609.36348v1) reports that adding cross-view class-token alignment to diffusion transformer training improves ImageNet linear-probing accuracy by 9.4% with the class token and 10.1%…