Skip to content

Author

Xingyi Cheng

1 paper indexed here

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.

Open access Aug 2026

Pretraining Enhances Megabase-Scale Gene Expression Prediction with GeneUnet

GB.GeneUnet, an 837M-parameter transformer-based U-Net pretrained on 6 trillion tokens from multi-species genomes in OpenGenome2 is introduced, extending genomic context to 1 Mb with up to 100× inference speedup over GeneMoE, a preliminary MoE transformer baseline of similar model size pretrained on the same data.

Ning Sun, William de Vazelhes, Pan Li et al. · 0 citations