Fudan University

A protein-text foundation model embedding sequences and natural language in a shared token space, enabling protein understanding and de novo design from one checkpoint.

A Dirichlet flow-matching model that generates family-aware protein sequences by initializing from ancestral-reconstruction lineage priors rather than random noise.

A cross-modal transfer-learning model that adapts the ESM-2 650M protein language model to mRNA analysis by swapping amino-acid tokens for codon tokens, applied to mRNA benchmarks without re-training.

A foundation model that predicts spatial transcriptomics and proteomics directly from routine H&E whole-slide images using a vision transformer aligned with a language model.

A framework that bridges a protein language model and a general LLM via continual pretraining, giving large language models protein-domain reasoning without losing general capabilities.

Medical multimodal LLM (2B and 8B) trained for generalizable, step-by-step clinical reasoning via Mentor-Intern Collaborative Search.

A reinforcement-learning-enhanced general medical vision-language model that adds step-by-step reasoning for medical image diagnosis and visual question answering.

A universal ultrasound foundation model pretrained on 2M+ multi-organ images via spatial-frequency masked image modeling, enabling label-efficient segmentation, classification, and enhancement.

Foundation model for fluorescence microscopy image restoration, unifying super-resolution, denoising, isotropic reconstruction, projection, and volumetric reconstruction in one Swin transformer.

Protein language model-based sequence search that detects remote homologs with threefold higher sensitivity than MMseqs2 at comparable speed.