Echo-Memory

Echo-Memory: Controlled study isolates memory mechanisms in action-conditioned world models

Echo-Memory is a controlled benchmark study comparing memory mechanisms in action-conditioned video world models, fixing all other variables (backbone, optimizer, evaluation) to isolate how history storage and retrieval affect scene consistency across camera departures and returns. The study compares raw context, compression-based memory, spatial summaries, and state-space recurrence under a shared video diffusion backbone. Key findings: raw context is a strong baseline for open-domain return; aggressive compression loses salient evidence; and block-wise state-space recurrence is the strongest mechanism for remembering world state across long horizons. The three-branch evaluation protocol reveals that replay fidelity is not a reliable proxy for true world memory.