All Competitors

Interpretable model of human transcription initiation that decomposes promoter activity into a minimal set of sequence rules at base-pair resolution.

Self-supervised CNN pretrained on 700,000 person-days of UK Biobank accelerometer data for human activity recognition across devices and cohorts.

Foundation model for medical image registration that aligns CT and MRI across anatomies and modalities without per-pair optimization or retraining.

RNA foundation model trained on chemical-mapping data from millions of sequences, predicting reactivity, secondary structure, and degradation.

Google's dermatology image embedding model that produces 6144-dimensional embeddings for data-efficient skin-condition classifiers.

Self-supervised foundation models for wearable PPG and ECG signals, trained with contrastive learning on Apple Heart and Movement Study recordings.

Vision-language pretraining for 3D CT volumes, aligning scans with their radiology reports for zero-shot classification, retrieval, and segmentation.

Large-scale chest X-ray vision-language pretraining model that learns image-report alignment for zero-shot and few-shot radiograph classification.

Abdominal CT segmentation model driven by CLIP text embeddings, covering 25 organs and 6 tumor types with zero-shot extension to new categories.

Vision-language pre-training framework for universal brain MRI diagnosis, learning from imaging-report pairs to cover more than ten brain diseases.

Discrete diffusion model for protein sequence and MSA generation, enabling controllable de novo design directly in sequence space without structure.

Self-supervised foundation model for 3D medical image segmentation, pretrained on roughly 110,000 unannotated CT volumes via Volume Fusion.

3D CT localization foundation model that pairs MedLAM with SAM to segment any anatomical structure at a fixed, dataset-independent annotation cost.

Scalable and transferable U-Net family (14M–1.4B parameters) for 3D medical image segmentation, supervised-pretrained on TotalSegmentator.

Medical image segmentation model that solves unseen segmentation tasks in context from a few labeled examples, with no retraining or fine-tuning.

Biomedical vision-language model trained contrastively on 1.6M figure-caption pairs mined from PubMed Central open-access articles.

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

Medical-domain CLIP fine-tuned on radiology image-caption pairs from ROCO, serving as a drop-in visual encoder for medical visual question answering.

Cross-species convolutional network trained jointly on human and mouse genomes to predict regulatory sequence activity and noncoding variant effects.

Self-supervised 3D pretrained models for CT and MRI that learn anatomical representations from unlabeled volumes and transfer to segmentation tasks.

Pretrained 3D-ResNet backbones for volumetric medical image analysis, co-trained across eight CT and MRI segmentation datasets for transfer learning.

3D convolutional network that predicts subcellular fluorescence labels from transmitted-light microscopy, enabling label-free imaging of living cells.

Dilated convolutional network that predicts cell-type-specific epigenetic and transcriptional profiles from DNA sequence across mammalian genomes.

Convolutional neural network that predicts DNA accessibility from sequence across 164 DNase-seq cell types, enabling variant effect prediction.