All Competitors

Vision foundation model for the tree of life, scaling BioCLIP 2 to a ViT-H/14 backbone and more organism images for zero-shot species classification.

470M-parameter microbial genome foundation model trained on 234.5B base pairs for multi-scale genomic representation and trait prediction.

Vision foundation model for the tree of life, trained on 214 million organism images across 952,000 taxa for zero-shot species classification.

Brain-dynamics foundation model for resting-state fMRI, adapting the Joint-Embedding Predictive Architecture with brain gradient positioning.