As an increasing majority of global video content is consumed on social platforms for interactive social purposes, video generation models built for social worlds are important but largely overlooked by previous studies. In this work, we define the position of social world models and build a prototype model as the first step towards this goal. While previous world models successfully simulate physical environments or gaming world exploration, they remain fundamentally detached from human-centric social dynamics. To bridge this gap as the first step to social world models, we present MaineCoon, the first real-time audio-visual autoregressive model that has 22B parameters and is capable of real-time streaming generation and sub-second interaction, with a record-breaking frame rate of up to 47.5 FPS, on a single GPU. To the best of our knowledge, MaineCoon is also the first real-time audio-visual generation model specifically optimized for social-interactive applications. To enable efficient and stable training, we introduce several novel techniques into MaineCoon, including self-resampling, cross-modal representation alignment, domain-aware preference optimization, and reinforced online-policy distillation (ROPD). We also design the first agentic streaming inference framework that supports thousand-second-scale or even longer generation while mitigating drift with agentic cache management and prompt planing. These innovations significantly accelerate training while optimizing real-time inference performance. We believe this work not only sets a new state-of-the-art (SOTA) performance benchmark for high-quality, low-latency, and long-horizon audio-visual autoregressive models, but also points out the paradigm shift desired for next-generation AI-native social platforms.

翻译：随着全球视频内容越来越多地在社交平台上被消费以进行互动社交，专为社会世界构建的视频生成模型至关重要，但此前的研究在很大程度上忽视了这一点。在这项工作中，我们定义了社会世界模型的定位，并构建了一个原型模型，作为实现这一目标的第一步。尽管先前的世界模型成功模拟了物理环境或游戏世界探索，但它们从根本上脱离了以人为中心的社会动态。为了弥合这一差距，作为社会世界模型的第一步，我们提出了MaineCoon，这是首个实时音视频自回归模型，拥有220亿参数，能够在单个GPU上实现实时流式生成和亚秒级交互，帧率高达创纪录的47.5帧/秒。据我们所知，MaineCoon也是首个专门针对社交互动应用优化的实时音视频生成模型。为了实现高效稳定的训练，我们在MaineCoon中引入了多项新技术，包括自重采样、跨模态表示对齐、领域感知偏好优化以及强化在线策略蒸馏（ROPD）。我们还设计了首个智能体流式推理框架，该框架支持千秒级甚至更长时间的生成，同时通过智能体缓存管理和提示规划来缓解漂移。这些创新显著加速了训练，同时优化了实时推理性能。我们相信，这项工作不仅为高质量、低延迟、长视界音视频自回归模型设立了新的最先进性能基准，而且指出了下一代AI原生社交平台所期望的范式转变。