一张显卡跑出无限游戏世界
你不需要买几万块的服务器，一张RTX 5090显卡就能实时生成一个可以无限探索、自由交互的3D世界。ABot-World-0是一个“动作视频世界模型”——你按键盘，它实时生成对应的画面，就像在玩一个永远没有边界的游戏。它从AAA大作、模拟引擎和网络视频中学习世界规律，能理解“往前走”“转身”“跳跃”这些原始键盘指令，并生成连贯的720P视频流，延迟仅1.2秒。更关键的是，它通过“长程强制对齐”技术解决了AI生成视频时常见的画面漂移和身份丢失问题，让角色在长时间探索中保持长相一致。这不是一个能直接用的产品，但它展示了未来游戏和虚拟世界的可能：不再需要预渲染地图，AI实时为你创造一切。
📄 原文摘要(英文)
We present ABot-World-0, an action-conditioned video world model for real-time, long-horizon closed-loop interaction, supported by a multi-source data infrastructure spanning AAA games, simulation engines, and internet videos to learn controllable world dynamics. WorldExplorer performs agent-driven collection guided by training feedback, while a unified pipeline applies 14 deterministic quality checks, VLM-based assessment, and synchronized action and text annotation. We progressively distill a bidirectional action-conditioned teacher into a causal student through teacher forcing and ODE distillation, and introduce LongForcing to align long student self-rollouts with an extended-horizon teacher, mitigating accumulated distribution shift and autoregressive drift. Raw keyboard actions provide a unified control interface for scene roaming and third-person character interaction, while reference-character memory provides persistent appearance cues for identity consistency during third-person rollouts. For deployment, we co-design a streaming inference stack with a lightweight VAE decoder, efficient attention, memory-aware scheduling, and low-bit DiT inference. Across optimized low-bit configurations, ABot-World-0 streams 720P video at up to 16 FPS on a single NVIDIA RTX 5090 desktop GPU, with 1.2s action-to-first-frame latency and approximately 19GiB peak VRAM. Experiments on WorldRoamBench and extended interactive rollouts demonstrate competitive controllability and coherent long-horizon world evolution.