Yan：基础交互式视频生成框架
Yan: Foundational Interactive Video Generation
AI总结：
提出交互式视频生成基础框架Yan，通过AAA级模拟、多模态生成、多粒度编辑三大模块，实现实时模拟、动作可控生成及交互编辑，推动交互式视频生成迈向全面AI驱动的创作范式。
摘要：
我们提出Yan，一个覆盖从模拟、生成到编辑全流程的交互式视频生成基础框架。该框架包含三个核心模块：AAA级模拟，设计高压缩、低延迟的3D-VAE并结合基于KV缓存的移窗去噪推理过程，实现实时1080P/60FPS交互式模拟；多模态生成，引入分层自回归字幕方法将游戏特定知识注入开源多模态视频扩散模型（VDMs），再将VDM转化为逐帧、动作可控的实时无限交互式视频生成器；多粒度编辑，提出混合模型分离交互机制模拟与视觉渲染，支持交互过程中通过文本进行多粒度视频内容编辑。Yan整合这些模块，推动交互式视频生成从孤立能力迈向全面AI驱动的交互创作范式，为下一代创意工具、媒体和娱乐铺路。
英文摘要：
We present Yan, a foundational framework for interactive video generation, covering the entire pipeline from simulation and generation to editing. Specifically, Yan comprises three core modules. AAA-level Simulation: We design a highly-compressed, low-latency 3D-VAE coupled with a KV-cache-based shift-window denoising inference process, achieving real-time 1080P/60FPS interactive simulation. Multi-Modal Generation: We introduce a hierarchical autoregressive caption method that injects game-specific knowledge into open-domain multi-modal video diffusion models (VDMs), then transforming the VDM into a frame-wise, action-controllable, real-time infinite interactive video generator. Notably, when the textual and visual prompts are sourced from different domains, the model demonstrates strong generalization, allowing it to blend and compose the style and mechanics across domains flexibly according to user prompts. Multi-Granularity Editing: We propose a hybrid model that explicitly disentangles interactive mechanics simulation from visual rendering, enabling multi-granularity video content editing during interaction through text. Collectively, Yan offers an integration of these modules, pushing interactive video generation beyond isolated capabilities toward a comprehensive AI-driven interactive creation paradigm, paving the way for the next generation of creative tools, media, and entertainment. The project page is: https://greatx3.github.io/Yan/.
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。
