@iScienceLuvr
The Aligner uses a SigLIP contrastive loss to learn word-level alignment between the Encoder's MEG embeddings and the LLM's word embedding space. Whenever the CTC path from the Encoder predicts a space, it chops up the continuous MEG into neural "words". Because spaces are frequent (about 19% of characters) and robustly predicted, 86% of sentences have their word count estimated within ±1 word of the ground truth — which is what lets the LLM read the MEG as structured token input.