超越视觉思维链：内化的视觉思维用于主动视频推理

摘要

多模态大语言模型日益采用视觉思维链（Visual CoT）来对空间、时间及具身环境进行推理。通过生成中间推理图像，Visual CoT为视觉预判提供了一种直观机制，但同时也引入了显著的推理开销，这一问题在主动视频推理场景中尤为突出。我们探究模型能否在训练阶段学会视觉思考，而在推理阶段直接进行推理。为此，我们提出内化视觉思维（IVT），一种在后训练阶段联合优化文本预测与下一嵌入预测的框架，训练数据为无标注视频。给定部分观测的视频，IVT在预测目标文本答案的同时预测未来帧的潜在表征，从而促使模型捕获运动、物体状态变化、交互行为及潜在意图。在推理阶段，IVT直接生成答案，无需合成或重新编码未来帧。我们围绕目标表征、解码器设计、预测视界、数据混合、训练课程及预测目标开展了受控研究。实验结果表明，IVT在所有六项评测设置上均优于直接答案微调方法，同时保持相同的推理路径。与显式Visual CoT相比，IVT取得了相当或更优的性能，并将平均端到端延迟降低了5倍以上。综合而言，我们的研究结果表明，视觉思维链中推理阶段所采用的显式像素空间生成，对于有效的主动视频推理可能并非必需。预测性世界建模可以在训练阶段被内化，从而产生兼具更高准确性和显著更高效率的多模态推理模型。

English

Multimodal large language models increasingly use visual chain-of-thought (Visual CoT) to reason about spatial, temporal, and embodied environments. By generating intermediate reasoning images, Visual CoT provides an intuitive mechanism for visual foresight but introduces substantial inference overhead, which is particularly problematic for proactive video reasoning. We ask whether models can learn to think visually during training while reasoning directly at inference. We introduce Internalized Visual Thinking (IVT), a post-training framework that jointly optimizes textual prediction and next-embedding prediction over unlabeled videos. Given a partially observed video, IVT predicts latent representations of future frames together with the target textual answer, encouraging the model to capture motion, object transitions, interactions, and latent intent. At inference, IVT generates the answer directly without synthesizing or re-encoding future frames. We conduct controlled studies across target representations, decoder designs, prediction horizons, data mixtures, training curricula, and predictive objectives. IVT improves over direct-answer fine-tuning on all six evaluation settings while retaining the same inference pathway. Compared with explicit Visual CoT, IVT achieves comparable or better performance and reduces average end-to-end latency by more than 5x. Together, our findings suggest that explicit pixel-space generation at inference time, as used in visual chain-of-thought, may not be necessary for effective proactive video reasoning. Predictive world modeling can be internalized during training to produce multimodal reasoners that are both more accurate and substantially more efficient.