All Competitors

A zebrafish DNA sequence-to-function model predicting cell-type-specific single-cell expression across 85 cell-type x developmental-timepoint combinations during embryogenesis.

Multimodal deep-learning framework that detects and localizes DNA lesions directly from native nanopore sequencing, built on the damage-aware LesionBERT foundation model.

A pretrained DNA language model combining Mamba state-space layers, gated dilated convolutions, and Fourier-based attention to capture multi-scale genomic regulatory patterns.

A supervised, chromatin-informed foundation model that predicts regulatory activity directly from plant genomic sequence in Arabidopsis and rice.

A structure-aware graph-attention model that predicts A-to-I RNA editing across tissues and species from sequence and secondary structure, with released pretrained weights.

A 3D CNN that voxelizes every heavy atom for rotation-robust protein structural representations, matching or beating protein language model encoders on function benchmarks.

A NAFNet backbone trained with a perceptual GAN objective for high-fidelity bioimage restoration, achieving best LPIPS on 7 of 8 AI4Life benchmarks.

A 3D vision-language foundation model for abdominal CT that pretrains on paired scans, radiology reports, and structured EHR codes for zero-shot interpretation.

A clinically-guided contrastive foundation model for single-lead ECG analysis, pretrained on 12-lead recordings from 161K patients using SCORE2 risk to weight pairs.

A deep learning framework that predicts locus-specific DNA methylation across 39 human tissues from genomic sequence, with a scRNA-seq-augmented variant for unseen cell types.

A neuro-oncology foundation model for brain tumor MRI that uses distributionally robust self-supervised pretraining to predict molecular markers and survival across institutions.

A SimCLR self-supervised foundation model for 3D brain MRI, pretrained on 18,759 patients across 11 neurological-disease datasets for diverse diagnostic tasks.

Surface-EMG wristband foundation models that decode hand gestures, handwriting, and wrist movement from thousands of users, generalizing cross-user without per-person calibration.

A family of CNN foundation models pretrained on ~1.9M multimodal radiology images for transfer learning across medical imaging tasks.

A foundational model for universal ultrasound image segmentation that adapts the Segment Anything Model to handle eight anatomical regions in a single network.

A multimodal LLM that aligns a specialized ECG signal encoder with BioMedGPT-LM-7B for cardiovascular disease detection and ECG question answering.

An open-source PPG foundation model pretrained on raw wearable signals from a 100-day field study, generalizing across lab and field health tasks.

Fifth-place solution from the CZII CryoET Kaggle competition; an ensemble of four lightweight 3D U-Nets for protein particle localization in cryo-ET tomograms.

First-place solution from the CZII CryoET Object Identification Kaggle competition; an ensemble of 3D EfficientNet-encoder U-Nets for multi-class protein particle picking.

Seventh-place CZII CryoET Kaggle solution; an ensemble of three heatmap-predicting 3D segmentation models using ResNet50d and EfficientNetV2-M backbones for particle picking.

Eighth-place CZII CryoET Kaggle solution; a weighted model soup of tiny, medium, and large 3D U-Nets pretrained on simulated data and fine-tuned on experimental cryo-ET tomograms.

Deep learning model predicting cell-type-specific RNA-seq coverage at 32 bp resolution from 524 kb of DNA sequence, jointly modeling transcription, splicing, and polyadenylation.

A deep learning framework for multi-class protein particle picking in cryo-ET tomograms using a 3D U-Net with automated architecture search via Bayesian optimization.

A variational autoencoder for interpretable 3D reconstruction and representation learning of protein subtomograms from cryo-ET data, trained on 5.8 million synthetic particles.