Chinese University of Hong Kong

Generative framework that learns a developmental vector field from scRNA-seq snapshots, coupling flow matching with molecular RNA kinetics.

Reasoning-guided foundation model for de novo antibody CDR design, pairing a multimodal LLM understanding expert with a Boltz-1 diffusion expert.

Self-supervised SE(3) geometric pretraining for protein backbone generators, improving designability, motif scaffolding, and conformational ensembles.

Histopathology foundation model extracting general-purpose features from H&E patches by distilling the UNI, Phikon, and CONCH pathology encoders.

Enzyme backbone design model that adds substrate and catalytic-site control to a pretrained SE(3) flow-matching generator via a lightweight adapter.

Protein structure autoencoder compressing backbone coordinates into a latent space, paired with a latent diffusion model for generative design.

Structure-conditioned fine-tune of ESM2 for protein mutation-effect prediction, matching ESM3-level accuracy after roughly an hour of fine-tuning.

Spatiotemporal foundation model that learns representations directly from 4D functional MRI volumes for disease diagnosis and phenotype prediction.

Grounded multimodal language model for endoscopic surgery, supporting visual dialogue, region-based question answering, and bounding-box grounding.

Multi-modal ophthalmic foundation model for generalist eye AI, spanning fundus imaging and OCT for disease screening, segmentation, and biomarkers.

Endoscopy video foundation model that learns spatial-temporal representations from unlabeled clips for classification, segmentation, and detection.

RNA foundation model pretrained on 23.7 million non-coding RNA sequences, producing embeddings for structure prediction, annotation, and RNA design.