The constellation Gemini gets its name directly from the Greek mythological twins, Castor and Pollux.
Each twin had different capabilities. Pollux was a powerful warrior while Castor was an intellectual tactician.
The twins possessed an extraordinary fraternal bond, each loyal and devoted to protecting the other.
Together, they accomplished what they couldn't do individually. Their combined strengths made them far more effective than either could be alone.
Just as text, images, audio and video convey different knowledge, relationships and reasoning than text by itself, their combined strengths in a single model should be more powerful than any model trained on only one modality.
