One-Step Next-Latent Prediction Is Not a World Model
Next-latent prediction fits a map from the current embedding to the next one. LeNEPA carries this objective to time series, replacing the stop-gradient of next-embedding prediction with the isotropy penalty of LeJEPA. A world model is a transition kernel that can be rolled out. The one-step regression identifies a cond...
Shi-Tong Wang, Zhongang Cai, Yu Hong
· 0 citations