基于奖励的强制：利用奖励反馈的自回归视频生成
Reward-Forcing: Autoregressive Video Generation with Reward Feedback
AI总结：
本文提出一种利用奖励信号指导生成的自回归视频生成方法，提升了生成效率和可扩展性，实验表明其性能与现有自回归模型相当，甚至在某些情况下超越了双向模型。
摘要：
尽管大多数视频生成工作依赖于双向架构，近期的研究尝试将这些模型适配为自回归变体以支持接近实时生成。然而，此类适配往往依赖于教师模型，这在缺乏强大自回归教师模型时会限制性能，导致输出质量通常低于双向模型。本文探讨了一种替代方法，利用奖励信号指导生成过程，使自回归生成更加高效和可扩展。通过奖励信号指导模型，我们的方法简化了训练过程，同时保持了高视觉保真度和时间一致性。在标准基准上的广泛实验表明，我们的方法在性能上与现有自回归模型相当，并在某些情况下超越了同样规模的双向模型，避免了教师架构带来的限制。例如，在VBench上，我们的方法总分为84.92，接近评分84.31的最先进自回归方法，但不需要显著的异构蒸馏。
英文摘要：
While most prior work in video generation relies on bidirectional architectures, recent efforts have sought to adapt these models into autoregressive variants to support near real-time generation. However, such adaptations often depend heavily on teacher models, which can limit performance, particularly in the absence of a strong autoregressive teacher, resulting in output quality that typically lags behind their bidirectional counterparts. In this paper, we explore an alternative approach that uses reward signals to guide the generation process, enabling more efficient and scalable autoregressive generation. By using reward signals to guide the model, our method simplifies training while preserving high visual fidelity and temporal consistency. Through extensive experiments on standard benchmarks, we find that our approach performs comparably to existing autoregressive models and, in some cases, surpasses similarly sized bidirectional models by avoiding constraints imposed by teacher architectures. For example, on VBench, our method achieves a total score of 84.92, closely matching state-of-the-art autoregressive methods that score 84.31 but require significant heterogeneous distillation.
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。
