Identifiable Token Correspondence for World Models 事件

Identifiable Token Correspondence for World Models arXiv:2605.16457v3 Announce Type: replace-cross Abstract: Token-based transformer world models have shown strong performance in visual reinforcement learning, but often suffer from temporal inconsistency in long-horizon rollouts, including object duplication, disappearance, and transmutation. A key reason is that most existing approaches treat next-frame prediction purely as a token generation problem, without considering the persistence of tok