Search papers, labs, and topics across Lattice.
MMLab , CUHK, Tencent HY
2
0
5
4
Individual token selection and metadata caching unlock sparse attention for diffusion transformers without sacrificing generation quality, achieving up to $2.32\times$ speedups.
High-fidelity 3D texture generation is now achievable without any 3D assets, by cleverly transforming 2D images into effective training data.
