Chinese University of Hong Kong

RNA co-design model generating sequence and 3D backbone together, with SE(3) flow matching over coupled base-centered and sugar-centered frames.

Designs RNA and DNA aptamers against protein targets by backpropagating binding and anti-binding objectives through a frozen all-atom predictor.

Genomic foundation model on a Mamba, attention, and mixture-of-experts backbone, with 1M-token context for variant scoring and regulatory DNA design.

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.

De novo antibiotic design framework coupling a 6.4B-parameter protein language model with reinforcement learning to generate antimicrobial peptides.

Transcriptome-guided diffusion model generating Cell Painting images for unseen perturbations, improving MOA retrieval accuracy by 16.9% over IMPA.

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

EEG foundation model with cross-scale spatiotemporal tokenization and sparse structured attention, evaluated on 11 decoding tasks across 16 datasets.

Plasmid characterization and retrieval model aligning DNA sequences with property text across ten facets, from antimicrobial resistance to host range.

Text-prompted pathology image segmentation across 160 tissue, cell, and nuclei categories, replacing point and box inputs with natural language.

Genome-anchored histopathology embeddings that predict molecular biomarkers, subtypes, and survival from whole-slide images alone at inference.

MSA design model generating alignments from protein language model embeddings to improve folding accuracy on orphan and low-homology proteins.

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

3D molecule generation that writes a valid 1D SELFIES string with a pretrained language model, then predicts its conformer with a diffusion module.

Cell-free DNA methylation deconvolution at individual-read resolution, estimating cell-type proportions and condition-specific methylation profiles.

Cervical cytology screening system pretrained on 127,471 whole-slide images from 48 centers, with test-time adaptation for new clinical sites.

Antibody and TCR CDR sequence design by structure retrieval, matching query loops against solved CDR structures rather than generating residues.

Biomedical vision-language model aligning image regions to UMLS clinical concepts, for zero-shot diagnosis across 10 imaging modalities.

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

Multi-omics instruction-tuned LLM that reads DNA, RNA, protein, and multi-molecule sequences and answers natural-language questions about them.

Masked-autoencoder foundation model for chest radiographs, self-supervised on 1.04 million unlabelled images for disease screening and localization.

Protein language model pairing sequence with quantized local-structure tokens via disentangled attention, for zero-shot variant effect prediction.

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.