Preprint
Oct 2026
Remembering What Matters for Long-Horizon Robotic World Models
Autoregressive robot video world models based on discrete visual tokens remain unreliable over long rollout horizons. Retaining the entire generated history does not necessarily improve prediction quality. We investigate a possible memory-role conflict in Full Context decoding: persistent scene information, recent visu...
Hao Wu, Tian-Yu Shao, Sheng-Ju Qian et al.
· 0 citations