Parametric Multimodal User Memory: Storing What Captions Cannot Carry
arXiv:2608.28609v1 Announce Type: new Abstract: A personalized agent needs a user memory: a persistent model of who its user is. Today it is almost always text -- transcripts and captions retrieved by similarity. This serves the captionable half of a person ("my cat is named Bibi"), but discards the perceptual half no caption can hold: how a voice sounds, how a face reads…
Lire l'article