DreamX-World 1.0：通用交互式世界模型
DreamX-World 1.0: A General-Purpose Interactive World Model
AI总结：
提出通用交互式文图生视频世界模型DreamX-World 1.0，通过E-PRoPE相机控制、因果强制自回归生成、记忆条件场景持久化和事件指令微调，实现可控长时程生成，在多项指标上超越现有方法。
摘要：
DreamX-World 1.0 是一个通用的交互式文本/图像到视频的世界模型，用于可控的长时程生成。它支持相机导航、重新访问先前观察过的区域，以及在逼真、游戏风格和风格化领域中的可提示事件。我们的数据引擎结合了相机精确的虚幻引擎渲染、动作丰富的游戏录制以及带有恢复相机几何的真实世界视频。对于相机控制，我们引入了 E-PRoPE，一种轻量级的投影位置编码变体，它保留了 PRoPE 的投影相机几何，同时对空间缩减的令牌应用相机感知注意力。我们使用因果强制、DMD 风格蒸馏和长滚动训练，将双向视频生成器转换为几步自回归世界模型。在自生成的长时程上下文上进行训练，使模型暴露于其自身的生成历史，并减少跨自回归块累积的风格和颜色漂移。记忆条件场景持久性通过基于相机几何的检索来检索早期视图，而残差循环使得条件路径对不完美的记忆潜变量不那么敏感。事件指令微调增加了可组合的事件控制，而强化学习对齐在蒸馏后恢复了相机控制和视觉质量。通过混合精度 DiT 执行、残差重用、75% 剪枝的 VAE 解码和异步流水线并行，DreamX-World 1.0 在八块 RTX 5090 GPU 上达到高达 16 FPS。在我们的 5 秒基本评估中，DreamX-World 1.0 获得了 73.75 的相机控制分数和 84.76 的总分，在总分上优于 HY-WorldPlay 1.5 和 LingBot-World，后两者分别达到 80.79 和 80.45。
英文摘要：
DreamX-World 1.0 is a general-purpose interactive text/image-to-video world model for controllable long-horizon generation. It supports camera navigation, revisits to previously observed regions, and promptable events across photorealistic, game-style, and stylized domains. Our data engine combines camera-accurate Unreal Engine rendering, action-rich gameplay recordings, and real-world videos with recovered camera geometry. For camera control, we introduce E-PRoPE, a lightweight variant of projective positional encoding that retains PRoPE's projective camera geometry while applying camera-aware attention to spatially reduced tokens. We convert a bidirectional video generator into a few-step autoregressive world model using causal forcing, DMD-style distillation, and long-rollout training. Training on self-generated long-horizon contexts exposes the model to its own generated history and reduces the style and color drift that accumulates across autoregressive chunks. Memory-Conditioned Scene Persistence retrieves earlier views through camera-geometry-based retrieval, while residual recycling makes the conditioning path less sensitive to imperfect memory latents. Event Instruction Tuning adds composable event control, and reinforcement learning alignment recovers camera control and visual quality after distillation. With mixed-precision DiT execution, residual reuse, 75\%-pruned VAE decoding, and asynchronous pipeline parallelism, DreamX-World 1.0 reaches up to 16\,FPS on eight RTX\,5090 GPUs. On our 5-second basic evaluation, DreamX-World 1.0 achieves a camera-control score of 73.75 and an overall score of 84.76, outperforming HY-WorldPlay 1.5 and LingBot-World in overall score, which achieve 80.79 and 80.45, respectively.
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。
