Huazhong University of Science and Technology

A unified bio-language Mixture-of-Experts foundation model spanning DNA, protein sequence and structure, and biological text, applied across eight task families from a single checkpoint.

A Mamba-based dual-branch UNet that enhances cryo-EM and cryo-ET density maps using local resolution-guided learning to improve interpretability.

A medical multimodal large language model pretrained on the 25M-image MedTrinity-25M dataset, achieving state-of-the-art accuracy on biomedical visual question answering.

Graph neural network framework for antigen-specific antibody CDR design, combining a pre-trained antibody language model with one-shot sequence and structure generation.