FlexiWorld: Learning and Planning via Flexible Action Chunks Across Multiple Time Scales
Latent world models predict future states for goal-directed planning using action chunks spanning multiple primitive steps. Existing methods typically use fixed-length chunks and either omit goal-conditioned action generation or limit their supervision to short goal spans. We introduce FlexiWorld, a JEPA-based world mo...
Shi-Du Ren, Qi Gu, Zheng-Hao Ni et al.
· 0 citations