让AI记住你上一句指令，它才能陪你玩一局
现在的视频生成模型大多是一次性买卖：你说一句，它出一段，下一句就忘了上一句。Hy-Nomas 把「描述」和「指令」分开处理——描述性信息跨片段保留，动作指令只在它该生效的那段时间起作用，于是它能连续听你多轮指挥，还能同时控制镜头移动。它用 8B 参数的扩散模型，配合一个提示增强器把你的话翻译成结构化条件，再用多阶段训练逐步教会它因果生成、文本交互、镜头控制。人类评测里它比现有世界模型表现更好。这不是你明天能拿来玩的工具，但它指向一个关键方向：AI 要陪你玩一局游戏、演一场戏，必须先学会「记得你刚才说了什么」。
📄 原文摘要(英文)
Interactive world generation requires models to follow successive commands while preserving relevant history and action consequences. We present Hy-Nomas, a video world model with an 8B diffusion backbone that supports free-form text instructions and continuous camera control across multiple interaction turns. It generates variable-length segments conditioned on current inputs and cached history. Our central design aligns structured video captions with action-aware causal attention: descriptive context remains accessible across segments, while action instructions are restricted to their intended temporal windows. A vision-language Prompt Enhancer (PE) translates user requests and multimodal interaction histories into structured conditions for the next segment. A multi-stage curriculum progressively introduces causal generation, text interaction, camera control, and training on model-generated histories, followed by diffusion distillation. In human evaluation, Hy-Nomas shows superior performance over existing world models. We release model weights, code and benchmarks, together with a lightweight adaptation workflow, to support reproducible research on interactive world generation.