两篇新研究论文介绍了生成式多人世界模型的新方法。Multics 利用带有分组令牌的分层通信结构来管理玩家之间的信息交换，降低计算成本并提高一致性。另一方面，WorldCast 采用分布式模型，每个玩家运行一个本地客户端，该客户端交换玩家和场景状态，从而实现实时性能和可扩展性，而没有中心化瓶颈。这两种方法都旨在克服为多个交互式代理生成一致共享环境的挑战。 AI
影响 这些模型可以为在复杂、交互式环境中训练 AI 代理提供更现实、更具可扩展性的模拟。
排序理由 该集群包含两篇学术论文，详细介绍了用于多人世界生成的新研究模型。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2610.14727v1 Announce Type: new Abstract: Autoregressive world models have emerged as a powerful paradigm for sample efficient decision making, yet their open loop rollouts often exhibit increasing drift that leads to error accumulation even within a relatively small planni…
Multi-player interactive world models aim to simulate shared environments from multiple players' perspectives, but achieving robust generation while scaling to more players remains challenging. Existing approaches that rely on fully-connected communication (e.g., Solaris) incur q…
Multiplayer world models must generate independently controlled views with consistent representations of both players and their shared environment. Most existing approaches coordinate multiple players through joint multi-view generation, whose cost grows with each additional play…