基于语义的强制：在自回归视频合成中连接时间无关语义与近端动态
Grounded Forcing: Bridging Time-Independent Semantics and Proximal Dynamics in Autoregressive Video Synthesis
AI总结：
本文提出Grounded Forcing框架，通过三种机制解决自回归视频合成中的语义遗忘、视觉漂移和可控性丢失问题，提升长程一致性和视觉稳定性。
摘要：
自回归视频合成提供了一种无限时域生成的有前景路径，但受到三个交织挑战的限制：语义遗忘来自上下文限制，视觉漂移由于位置外推，以及交互指令切换期间的可控性损失。当前方法通常孤立处理这些问题，限制了长期一致性。我们引入Grounded Forcing，一种新的框架，通过三种相互关联的机制连接时间无关语义和近端动态。首先，为了解决语义遗忘，我们提出了双记忆KV缓存，将局部时间动态与全局语义锚点解耦，确保长期语义一致性和身份稳定性。其次，为抑制视觉漂移，我们设计了双参考RoPE注入，将位置嵌入限制在训练流形内，同时使全局语义时间不变。第三，为解决可控性问题，我们开发了非对称接近重装，通过接近加权缓存更新，在提示转换期间促进平滑的语义继承。这些组件协同工作，将生成过程与稳定的语义核心联系起来，同时适应灵活的局部动态。广泛实验表明，Grounded Forcing显著提高了长程一致性和视觉稳定性，为交互式长视频合成建立了稳健的基础。
英文摘要：
Autoregressive video synthesis offers a promising pathway for infinite-horizon generation but is fundamentally hindered by three intertwined challenges: semantic forgetting from context limitations, visual drift due to positional extrapolation, and controllability loss during interactive instruction switching. Current methods often tackle these issues in isolation, limiting long-term coherence. We introduce Grounded Forcing, a novel framework that bridges time-independent semantics and proximal dynamics through three interlocking mechanisms. First, to address semantic forgetting, we propose a Dual Memory KV Cache that decouples local temporal dynamics from global semantic anchors, ensuring long-term semantic coherence and identity stability. Second, to suppress visual drift, we design Dual-Reference RoPE Injection, which confines positional embeddings within the training manifold while rendering global semantics time-invariant. Third, to resolve controllability issues, we develop Asymmetric Proximity Recache, which facilitates smooth semantic inheritance during prompt transitions via proximity-weighted cache updates. These components operate synergistically to tether the generative process to stable semantic cores while accommodating flexible local dynamics. Extensive experiments demonstrate that Grounded Forcing significantly enhances long-range consistency and visual stability, establishing a robust foundation for interactive long-form video synthesis.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
