Teaching Video Generators to Remember: Eliciting Dynamic Memory for Out-of-Sight State Evolution 事件

Teaching Video Generators to Remember: Eliciting Dynamic Memory for Out-of-Sight State Evolution arXiv:2605.25333v1 Announce Type: new Abstract: Video world models should maintain evolving states when evidence is unobserved, yet current generators often freeze hidden states upon interruption. This is not simply a capacity problem: pretrained video diffusion transformers already possess KV-cache mechanisms capable of non-local retrieval, but they are rarely trained to use them as dynamic memory.