All Competitors

Chest X-ray vision-language model that drafts the findings section of a radiology report, at 7B parameters small enough to run on a single GPU.

ECG foundation model that treats heartbeats as words and rhythm strips as sentences, using heartbeat-level tokenization for diagnostic classification.

Medical vision-language model that unifies image comprehension and generation in one autoregressive transformer via heterogeneous LoRA adapters.

Unified science foundation model treating molecules, proteins, RNA, DNA, and materials as one sequence language, in 1B, 8B, and 46.7B sizes.

4B-parameter generative genome foundation model trained on assembled environmental metagenomes for microbial representation and de novo DNA design.

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

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

Regulatory genomics model predicting cell-type-specific RNA-seq coverage from DNA sequence, unifying transcription, splicing, and polyadenylation.

Vision-language foundation model for precision oncology, pretrained on 50M pathology images and 1B text tokens via unified masked modeling.

Multimodal 80B-parameter protein-language model that answers natural language questions about protein function from sequence and structure.

Text-guided protein design framework aligning language with sequences for text-conditioned generation, zero-shot editing, and property prediction.

Multimodal foundation model for wearable physiological sensing across PPG, ECG, EEG, GSR, and IMU signals, using channel-aware attention.

Biomedical multimodal LLM that answers questions about medical images and returns pixel-level segmentation masks, using a mixture-of-experts design.

Multimodal foundation model integrating protein sequence, structure, and natural language to model and generate protein phenotypes across scales.

EEG foundation model for brain-computer interface decoding, factorizing self-attention into parallel spatial and temporal branches.

Bilingual Arabic-English medical multimodal model built on Llama 3.1 for radiology, CT, and histology image understanding and question answering.

Generative model that emulates protein equilibrium ensembles, sampling cryptic pockets and unfolded states far faster than molecular dynamics.

Latent diffusion model for controllable all-atom protein generation that co-designs sequence and structure while training on sequences alone.

DNA foundation model scaling an encoder-only transformer to 7 billion parameters for variant effect prediction, gene expression, and sequence design.

Protein language model family at 300M, 600M, and 6B parameters, purpose-built for representation learning and outperforming ESM-2 at smaller scale.

Mixture-of-experts protein language model scaling to 16 billion parameters, applied to variant effect prediction and de novo protein design.

RNA foundation model with 1.6 billion parameters, pretrained on 42 million non-coding RNA sequences for structure prediction and RNA sequence design.

Single-cell RNA-seq foundation model pretrained on 50 million human cells, encoding the full transcriptome for annotation and perturbation modeling.