LATIDIA · Investigación

La memoria tiene geometría: memoria geométrica no uniforme para IA personalizada de Long-Horizon

arXiv: 2609.17969v1Tipo de anuncio: nuevo Resumen: La memoria a largo plazo se está convirtiendo en un sustrato central para la IA personalizada, sin embargo, la mayoría de los sistemas aún representan la personalización como registros discretos en un espacio latente en gran medida estático, ac

La noticia

arXiv:2609.17969v1 Announce Type: new Abstract: Long-term memory is becoming a core substrate for personalized AI, yet most systems still represent personalization as discrete records in a largely static latent space, accessed under one global similarity notion. For data mining, this creates a mismatch: the evidence is a temporal event stream, while the dominant abstraction is a searchable record set. We argue that long-horizon personalization should instead model memory as a user-specific dynamical state space with locally heterogeneous geometry. Geometry here is a computational language, not a literal claim about cognition: it captures stable versus volatile regions, variable-rate drift, heterogeneous neighborhoods, and uncertainty about current user state. Profiles and isolated events