AI学会了“世界模型”：不只看下一帧，而是理解世界状态
大多数AI模型只做一件事：预测下一个词、下一帧画面或下一个动作。Orca打破了这种割裂——它试图学习一个统一的“世界潜在空间”，把视频、语言、动作信号都映射进去，然后通过轻量解码器输出文本、图像或机器人指令。训练方式也反直觉：一边用125K小时连续视频做“无意识学习”（捕捉密集状态变化），一边用1.6亿条事件标注做“有意识学习”（理解稀疏但关键的事件）。结果证明，世界模型越强，下游任务表现越好，甚至超过专门训练的模型。这不是你明天能用的工具，但它指向一个方向：AI不再只是模式匹配，而是开始像人一样，在脑中构建一个可预测、可操作的世界模型。
📄 原文摘要(英文)
We introduce Orca, an initial instantiation of a general world foundation model. Orca learns a unified world latent space from multimodal world signals and exposes it through multimodal readout interfaces. Rather than optimizing isolated next-token, next-frame, or next-action prediction, we are centered on Next-State-Prediction modeling, offering a unified state-transition modeling route toward understanding, predicting, and acting upon the world. Orca learns through two complementary paradigms: unconscious learning captures dense natural state transitions from continuous videos, and conscious learning models sparse meaningful state transitions by language-described events and VQA supervision. For pre-training, we construct a large-scale world-learning inventory data, including 125K hours of video data and 160M event annotations. After pre-training, Orca learns a unified world latent space. To examine whether the learned latent supports downstream, we evaluate it by three representative downstream readouts: text generation, image prediction, and embodied action generation. Orca's backbone is frozen, and only the lightweight modality-specific decoders are trainable. Experiments show the scalability of the proposed paradigm and verify that stronger world latent enables stronger downstream readouts. Orca outperforms similar-sized specialized baselines. These results show that Orca, as a general world foundation model, presents a promising approach to understanding, predicting, and acting upon the world. Finally, we discuss the current limitations, aiming to provide useful insights and inspiration for the community.