All Competitors

Every biological foundation model, evaluated and ranked by the bio.rodeo team

Showing 1–6 of 6 filtered models

  • BrainOmni

    6724—
    Tsinghua University +3 othersMay 18, 2025brain_signal_classificationeegfoundation_model+7

    A brain foundation model that unifies EEG and MEG signals via a shared discrete tokenizer and self-supervised pretraining on 2,653 hours of recordings.

    Biosignals
    80Openness

  • HeartLang

    5642—
    Peking UniversityFebruary 15, 2025arrhythmia_detectionecg_classificationelectrocardiogram+5

    Self-supervised ECG foundation model that treats heartbeats as words and rhythms as sentences, using a QRS-Tokenizer and dual-level pretraining on MIMIC-IV-ECG.

    Biosignals
    78Openness

  • AnyECG

    45—
    Zhejiang University +3 othersNovember 17, 2024anomaly_detectionarrhythmia_classificationelectrocardiogram+6

    A two-stage pretrained ECG foundation model that learns discrete rhythm tokens for robust multitask cardiac analysis on noisy, real-world electrocardiograms.

    Biosignals
    10Openness

  • NeuroLM

    15693—
    Shanghai Jiao Tong University +1 otherAugust 27, 2024eegeeg_decodingfoundation_model+7

    A multi-task EEG foundation model that treats brain signals as a foreign language, pairing a text-aligned neural tokenizer with a GPT-2 backbone.

    BiosignalsLanguage model
    66Openness

  • LaBraM

    625344—
    Shanghai Jiao Tong UniversityMay 29, 2024abnormal_detectionbrain_computer_interfaceeeg+6

    An EEG foundation model that learns generic brain-signal representations via a vector-quantized neural tokenizer and masked-transformer pretraining on ~2,500 hours of data.

    Biosignals
    72Openness

  • EEGFormer

    —60—
    Microsoft +1 otherJanuary 11, 2024anomaly_detectioneegfoundation_model+5

    A transformer EEG foundation model pretrained with vector-quantized self-supervision on 1.7 TB of EEG, yielding transferable, interpretable discrete representations.

    Biosignals
    22Openness