Hunan University

NMR foundation model trained on 158 million simulated 1H and 13C spectra, transferring simulation-learned representations to real experimental data.

Protein representation learning from cryo-EM density maps, transferring to flexibility, active-site, binding-affinity, and stability tasks.

Vision-language DNA model that renders genomic sequence as visual layouts, reading regions up to 450,000 bases with about 20x better token efficiency.

Protein binder design model post-trained from a multimodal protein language model to bind proteins, peptides, small molecules, and nucleic acids.

Universal ultrasound segmentation foundation model adapting the Segment Anything Model to eight anatomical regions in a single promptable network.