למידת תורבות חוסר סדר ללא ראיית תורבות: התפשטות של דינמיקות גלובליות במודלי תרגומי אוטומטיים

תקציר מקורי באנגליתarXiv:2609.38814v1 Announce Type: new Abstract: Autoregressive models are trained to predict a system's behavior one step at a time, and recursive generation allows the learned dynamics to unfold over long horizons. To what extent can such dynamics learned from local observations recover broader organization of an underlying system that was only partially observed during training? Here we study small autoregressive transformers trained from scratch on trajectories sampled from restricted parameter regimes of several non-linear dynamical systems, including logistic and sine maps, the Lorenz system, and the generalized Hopf system, with control parameters and state trajectories represented as sequences of continuous tokens. Under closed-loop evaluation at parameters far outside the training