The University of Hong Kong

Pocket-conditioned 3D ligand generator that steers flow matching with LLM-written chemical priors, for de novo design and scaffold hopping.

EEG foundation model that corrects low-frequency bias by reconstructing band-standardized time-frequency targets. State of the art on 24 of 41 tasks.

Multi-organ foundation model aligning histology images with spatial-transcriptomics profiles for zero-shot expression and survival prediction.

Generative adversarial network trained on single-cell and bulk RNA-seq for sample stratification, marker analysis, and synthetic data generation.

Tissue imaging foundation model pretrained on matched H&E histology and spatial proteomics for cross-modal inference and zero-shot retrieval.

Antibody-antigen binding free energy predictor fusing ESM-2 sequence embeddings with persistent homology and interface geometry via cross-attention.

B-cell epitope predictor pairing CNN and Transformer branches over protein language model embeddings to score linear and conformational epitopes.

Multi-sequence MRI foundation model pretrained on 336,476 volumetric scans, ranking first on 41 of 44 downstream clinical benchmarks.

Multi-scale ECG-language model that aligns 12-lead ECG signals with clinical text at token, beat, and rhythm levels for zero-shot cardiac diagnosis.

Whole-body CT segmentation covering 235 fine-grained anatomies: 193 organs, 33 lymph node stations, and 9 lesion types from one unified network.

Multi-omics foundation model that folds DNA, RNA, and protein into one codon-level nucleotide representation following the central dogma.

Spatial transcriptomics foundation model learning subcellular transcript positions and cell-niche context from 17 million Xenium single cells.

Self-supervised histopathology encoder that models tissue entities as a graph and pretrains by latent graph diffusion over masked subgraphs.

CRISPR editing outcome prediction returning a probability over the near-full indel spectrum, with few-shot transfer to new cell types and to embryos.

Fine-grained cell-type abundance prediction from H&E histology, transferring to unseen cohorts and large slide archives without any retraining.

Self-supervised pretraining framework for medical imaging that unifies pixel restoration with contrastive learning across 2D and 3D image backbones.