ABot-World-0: 在单块桌面GPU上展开的无限交互世界

ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU

July 21, 2026

作者: Fan Jiang, Zhaoxu Sun, Mengchao Wang, Ziyu Zhu, Chiyu Wang, Yunpeng Zhang, Wenlin Liu, Yun Wang, Xue Zheng, Rui Sun, Junfeng Ni, Hongyu Pan, Zhongxu Sun, Fei Yu, Zengye Ge, Mengmeng Du, Nianfei Fan, Mingchao Sun, Yu Liu, Yongchang, Yanqing Zhu, Jiahang Wang, Ning Ying, Yuze Xuan, Di Yang, Zhicheng Liu, Zhe Gao, Tingbing Xu, Jiacheng Sui, Wenjin Yang, Junnan Lai, Shufeng Liu, Yuan Liu, Zheng Zhou, Yingliang Peng, Dawei Cao, Kaifeng Sheng, Yuxiang Cai, Fei Lu, Mu Xu, Ning Guo

cs.AI

摘要

我們提出ABot-World-0，這是一個以動作條件為基礎的影片世界模型，用於即時、長時程的閉環互動。該模型藉由涵蓋AAA遊戲、模擬引擎與網路影片的多源資料基礎設施，學習可控的世界動態。WorldExplorer根據訓練回饋進行智能體驅動的資料收集，而統一流程則應用14項確定性品質檢查、基於VLM的評估，以及同步的動作與文字標註。我們透過教師強迫與ODE蒸餾，逐步將雙向動作條件教師模型蒸餾為因果學生模型，並引入LongForcing以將學生的長自迴歸推論與擴展時程的教師對齊，從而緩解累積分佈偏移與自迴歸漂移。原始鍵盤動作為場景漫遊與第三人稱角色互動提供了統一的控制介面，而參考角色記憶則在第三人稱推論中提供持續的外觀線索，以維持身份一致性。在部署方面，我們協同設計了一個串流推理棧，包含輕量級VAE解碼器、高效注意力機制、記憶體感知排程，以及低比特DiT推理。在優化的低比特配置下，ABot-World-0可在單張NVIDIA RTX 5090桌面GPU上以高達16 FPS的速度串流720P影片，動作到首幀延遲為1.2秒，峰值VRAM約19GiB。在WorldRoamBench與擴展互動推論實驗中，展現了具競爭力的可控性與連貫的長時程世界演化。

English

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.