Chinese University of Hong Kong, Shenzhen

miRNA-target interaction model fusing five gated evidence experts, whose frozen representation transfers to siRNA efficacy prediction.

Protein-text foundation model placing amino acid sequences and natural language in one token space for protein understanding and de novo design.

Protein dynamics model that samples conformational ensembles autoregressively at slow and fast timescales, generalizing zero-shot to unseen proteins.

Tertiary structure-based RNA design model that fuses RNA backbone geometry with protein language model features of the bound partner protein.

Spatial genomics foundation model that predicts a cell's transcriptome from its neighbours and forward-simulates tissue response to perturbation.

Vaccine literature-mining model that classifies Brucella vaccine abstracts and extracts antigen, formulation, platform, and animal-model fields.

Ultrasound foundation model pretrained by federated learning across 16 institutions, transferring to disease diagnosis and lesion segmentation.

Open medical multimodal LLMs (7B and 34B) for visual question answering over radiology, pathology, and endoscopy images, trained on PubMedVision.

Medical vision-language pretraining unifying fusion-encoder and dual-encoder designs, handling image-only, text-only, and paired inputs in one model.

Self-supervised medical vision-and-language pretraining via multi-modal masked autoencoders that reconstruct masked image patches and text tokens.

Medical vision-language pretraining framework that injects structured medical knowledge into radiology image-text learning for VQA and retrieval.