AI 世界模型终于能边玩边生成，不再卡顿
游戏里的 AI 世界模型一直有个死结：它要实时响应你的键盘鼠标，但生成画面又很慢。ForgeWM 把双向视频生成器一步步蒸馏成只需1-4步就能出图的模型，在《我的世界》里做到了低延迟交互——你按方向键，画面立刻跟着动，同时鼠标移动也精准对齐。更妙的是它支持「回放精修」:1步模型先快速生成草稿，等你不操作时再自动优化画质，最终效果接近4步模型，但比从头生成快了3倍。这不是你明天能玩的游戏，但它让 AI 驱动的游戏世界从「看幻灯片」走向「真能玩」迈了一大步。
📄 原文摘要(英文)
Action-conditioned video world models require low-latency causal generation and reliable responses to game-native controls. Although causal distillation enables one- or few-step video synthesis, extending it to interactive world models remains challenging, as discrete keyboard states and continuous mouse motion must remain aligned with temporally compressed latent chunks during causal training and autoregressive rollout. We introduce ForgeWM, a progressive framework that transforms a bidirectional action-conditioned video generator into efficient few-step world models through domain adaptation, teacher-forced causal training, causal consistency distillation, and on-policy distribution matching with a bidirectional teacher. The resulting budget-specialized students operate at steady-state denoising budgets of 1, 2, and 4 steps. ForgeWM further supports a dual-path deployment protocol combining latency-critical interaction with optional replay-time refinement, where the one-step student re-noises and refines its saved draft. On paired Minecraft trajectories, ForgeWM leads the evaluated systems in Imaging Quality, reference-aligned motion-profile agreement, action-sign accuracy, and mouse-control accuracy, while achieving the lowest reference LPIPS; the same four-stage recipe transfers to gamepad-controlled FPS gameplay. Replay-time refinement matches four-step reference quality while remaining roughly three times closer to the experienced trajectory than regeneration from noise. These results demonstrate ForgeWM's effectiveness for controllable few-step video generation.