Long-video generators increasingly retrieve past visual observations to prevent identity drift. The intuition is compelling: more access to history should make future video more consistent. But an ima...
arXiv:2609.28466v1 Announce Type: new Abstract: Advances in generative models have improved video fidelity, enabling long-horizon generation, interactive world modeling, and evolving visual environme...
LayerRecall is a memory router for autoregressive video diffusion that selectively retrieves and injects historical key/value states into specific layers of the model, based on the current context. It addresses the problem that existing memory mechanisms expose nonlocal history but do not guarantee effective use, by recognizing that different layers prefer current, recent, or distant context. The method, combined with Cross‑Horizon Prediction Matching, achieves state‑of‑the‑art long‑range consistency on MemoBench and MovieBench while maintaining local continuity and incurring negligible inference overhead.
arXiv:2609.12090v1 Announce Type: new Abstract: Video models increasingly use memory to preserve information over long sequences, with the assumption that gains come from retrieving and using the cor...
arXiv:2606. 09803v1 Announce Type: cross Abstract: We present \textbf{Echo-Memory}, a controlled study of memory mechanisms in action-conditioned world models.
arXiv:2610.01884v1 Announce Type: new Abstract: We introduce an approach for collection-grounded B-roll sequence generation. Given a user's video collection, a directive given in natural language, an...
RECAP-Forcing is a new method for long autoregressive video generation that addresses the memory challenge by organizing memory based on appearance novelty rather than recency. The approach retains key-value caches for newly appearing content—such as entering subjects, disoccluded regions, and new scenes—at the moment they first appear, ensuring consistent identities over time. It combines an attention sink for the initial scene with an optical-flow-based novelty bank for later frames, improving visual quality and semantic fidelity without adding learnable parameters.
arXiv:2610.17926v1 Announce Type: cross Abstract: Autoregressive video generation relies on memory retrieval to model long-range dependencies. This capability becomes particularly critical for multi-...
arXiv:2606. 13035v1 Announce Type: cross Abstract: Autoregressive video diffusion models provide a natural formulation for streaming and variable-length video generation by conditioning newly generated frames on previously generated content.
arXiv:2606. 16353v1 Announce Type: cross Abstract: Streaming video understanding models must answer queries at any moment during an ongoing stream, using only what they have observed so far and under fixed memory and computation budgets.
arXiv:2610.01192v1 Announce Type: new Abstract: Streaming vision-language models must process continuously growing video streams under a bounded compute budget, creating a persistent tension between...
Autoregressive video diffusion models provide a natural formulation for streaming and variable-length video generation by conditioning newly generated frames on previously generated content. However, extending these models to minute-level generation remains challenging: the limited KV-cache budget prevents the model from retaining the full history, while repeatedly conditioning on self-generated frames induces a context distribution shift that accumulates over time, leading to visual artifacts, quality degradation, and temporal drift.