OraCore · Topic ·research

MOJO adds unlabeled training to neural decoding

MOJO mixes masked autoencoding with supervised training to make spike-tokenizing neural decoders work better with little labeled data.

1 articles in this thread ·Last updated 13h ago·First seen Jul 16, 2026

Timeline

  1. MOJO adds unlabeled training to neural decoding seed

    MOJO mixes masked autoencoding with supervised training to make spike-tokenizing neural decoders work better with little labeled data.