Industry

Microsoft

Multinational technology corporation

Website
9 models(4 Protein, 2 Multimodalities, 2 Imaging, 1 Pathology)

Labs & Groups (3)

Models (9)

Multimodalities

NatureLM

Microsoft Research AI for Science

Unified science foundation model from Microsoft Research treating molecules, proteins, RNA, DNA, and materials as a shared sequence language for cross-domain generation.

834
See the scorecard
Protein

BioEmu-1

Microsoft

Generative deep learning model from Microsoft Research that emulates protein equilibrium ensembles at 100,000x the speed of molecular dynamics simulation.

794243
See the scorecard
Imaging

BiomedParse

Microsoft Research

A biomedical foundation model for joint segmentation, detection, and recognition across nine imaging modalities using natural language prompts.

65614831K
See the scorecard
Protein

SFM-Protein

Microsoft Research

A transformer protein language model using integrative co-evolutionary pre-training to capture both short-range and long-range residue interactions from sequence alone.

3
See the scorecard
Multimodalities

BioT5+

Microsoft Research Asia

An enhanced T5-based encoder-decoder that unifies molecule, protein, and text understanding via IUPAC integration and multi-task instruction tuning.

12426.5K
See the scorecard
Pathology

Prov-GigaPath

Microsoft Research

Whole-slide pathology foundation model pretrained on 1.3 billion tiles from 171,189 clinical WSIs. Achieves state-of-the-art on 25 of 26 pathology benchmark tasks.

59674456.4K
See the scorecard
Protein

ABGNN

Huazhong University of Science and Technology / Microsoft Research

Graph neural network framework for antigen-specific antibody CDR design, combining a pre-trained antibody language model with one-shot sequence and structure generation.

5525
See the scorecard
Imaging

BiomedCLIP

Microsoft Research

Multimodal biomedical foundation model trained on 15M PubMed Central figure-caption pairs via contrastive learning, achieving state-of-the-art zero-shot performance across imaging modalities.

874.6K
See the scorecard
Protein

CARP

Microsoft Research

CNN-based protein language model series showing convolutions match transformer performance on sequence pretraining while scaling linearly with sequence length.

259
See the scorecard