DreamX-World 1.0：一种通用的交互式世界模型
DreamX-World 1.0: A General-Purpose Interactive World Model
摘要
DreamX-World 1.0是一款适用于各种场景的互动式文本/图像转视频世界模型，能够实现可控的长视距生成。它支持相机导航、重新访问之前已观察过的区域，并且能够处理各种场景——包括逼真效果、游戏风格以及具有特定风格的场景。我们的数据引擎结合了Unreal Engine的高精度渲染技术、充满动作感的游戏录像，以及真实世界的视频数据，同时还包含了经过处理的相机几何信息。在相机控制方面，我们采用了E-PRoPE技术，这是一种轻量级的投影式位置编码方法；该方法保留了PRoPE的投影式相机几何结构，同时通过对空间上有限的标记进行注意力机制处理来实现相机控制。我们通过因果驱动、DMD风格的分馏技术以及长周期训练方式，将双向视频生成器转化为简单的自回归世界模型。在自我生成的长期上下文上进行训练，可以让模型接触到自身产生的历史信息，从而减少自回归模块中出现的风格和色彩漂移问题。记忆条件化的场景持久性功能可以通过基于相机几何信息的检索来恢复早期的视图；而残余数据的再利用则使得条件化路径对不完美的记忆潜势的敏感度降低。事件指令调整功能则提供了可组合的事件控制机制，而强化学习对齐技术则能够在分馏处理后恢复相机的控制能力和视觉质量。通过混合精度事件指令执行、残余数据的重复利用、75%剪枝的VAE解码方式，以及异步流水线并行处理，DreamX-World 1.0在八台RTX 5090 GPU上能够达到高达16帧每秒的流畅度。在我们进行的5秒基本评估中，DreamX-World 1.0在相机控制评分上取得了73.75分，整体评分则为84.76分，远远超过了HY-WorldPlay 1.5和LingBot-World，后两者的整体评分分别为80.79分和80.45分。
English Abstract
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.