All Competitors

Spatial transcriptomics foundation model learning subcellular transcript positions and cell-niche context from 17 million Xenium single cells.

Peptide-MHC binding affinity and all-atom 3D structure in one attention network pass, reaching 1.19 Å median C-RMSD at 0.009 s per affinity call.

Generative de novo antibody design system jointly modeling sequence and all-atom structure, refined by scaling test-time compute.

Cyclic peptide structure prediction for sequences carrying unnatural amino acids, adding atom-level features and cyclization-aware position encoding.

Peptide binder design by mimicking the binding interface of a known receptor or antibody, generating all-atom peptides through latent diffusion.

Antibody CDR sequence-structure co-design by flow matching, starting from an informative structural prior rather than from Gaussian noise.

Grounded multimodal language model for endoscopic surgery, supporting visual dialogue, region-based question answering, and bounding-box grounding.

Multi-transformer model that predicts tissue-specific alternative splicing outcomes and generalizes zero-shot to unseen cellular conditions.

3D medical imaging foundation model self-supervised on roughly 100,000 MRI, CT, and PET volumes spanning more than ten organs and three modalities.

Segment Anything Model finetuned on diverse medical images, giving a reusable promptable checkpoint for interactive and automatic image segmentation.

Generative microbiome language model writing disease-conditioned community profiles and predicting post-transplant composition for FMT donors.

Adenylation domain substrate specificity prediction from frozen ESM-2 embeddings, with zero-shot calls on substrates absent from training.

Compact EEG foundation model whose alternating attention separates within-channel time from across-channel space, cutting attention memory sixfold.

RNA language model classifying transcripts as coding or long non-coding, using convolutional sequence encoding to fit whole transcripts in context.

Protein backbone generation with a diffusion model whose noise schedule is derived from the renormalization group rather than heuristically tuned.

3D vision foundation model for computed tomography, contrastively pretrained on 148,000 scans for segmentation, triage, retrieval, and concept search.

Binder motif prediction from receptor structure alone, mapping 14 functional-group types across a protein surface as reusable interaction profiles.

Histopathology foundation model pretrained on 200 million H&E and immunohistochemistry tiles from more than 350,000 whole-slide images.

Cryo-EM reconstruction with neural radiance fields in Euclidean 3D space, separating conformational motion from compositional assembly states.

Direct RNA nanopore basecaller that translates raw ionic-current signal into nucleotide sequence using a hybrid Mamba-Transformer backbone.

Single-cell analysis model driven by plain-language instructions, covering cell type annotation, pseudo-cell generation, and drug response prediction.

Generative transformer that writes candidate cognate epitope sequences from a TCR CDR3-beta input, annotating repertoires without functional assays.

Antimicrobial peptide discovery from metagenome-assembled genomes, labelling AMP residues with a LoRA-adapted ESM-2 token classifier.