While Chain-of-Thought empowers Large Vision-Language Models with multi-step reasoning, explicit textual rationales suffer from an information bandwidth bottleneck, where continuous visual details are discarded during discrete tokenization. Recent latent reasoning methods attempt to address this challenge, but often fall prey to premature semantic collapse due to rigid autoregressive objectives. In this paper, we propose Laser, a novel paradigm that reformulates visual deduction via Dynamic Windowed Alignment Learning (DWAL). Instead of forcing a point-wise prediction, Laser aligns the latent state with a dynamic validity window of future semantics. This mechanism enforces a "Forest-before-Trees" cognitive hierarchy, enabling the model to maintain a probabilistic superposition of global features before narrowing down to local details. Crucially, Laser maintains interpretability via decodable trajectories while stabilizing unconstrained learning via Self-Refined Superposition. Extensive experiments on 6 benchmarks demonstrate that Laser achieves state-of-the-art performance among latent reasoning methods, surpassing the strong baseline Monet by 5.03% on average. Notably, it achieves these gains with extreme efficiency, reducing inference tokens by more than 97%, while demonstrating robust generalization to out-of-distribution domains.

翻译：尽管思维链赋予大型视觉语言模型多步推理能力，但显式文本推理过程存在信息带宽瓶颈，连续的视觉细节在离散化标记过程中被丢弃。最近的潜在推理方法试图解决这一挑战，但常因僵化的自回归目标而陷入过早的语义坍缩。本文提出Laser这一新范式，通过动态窗口对齐学习重构视觉推理过程。该方法不强制进行逐点预测，而是将潜在状态与未来语义的动态有效窗口对齐。这种机制强制形成"先见林后见树"的认知层次结构，使模型能够在聚焦局部细节前保持全局特征的概率叠加态。关键的是，Laser通过可解码轨迹保持可解释性，同时通过自优化叠加机制稳定无约束学习。在6个基准测试上的大量实验表明，Laser在潜在推理方法中实现了最先进的性能，平均超越强基线Monet达5.03%。值得注意的是，该方法以极高的效率实现这些优势，推理标记减少超过97%，同时展现出对分布外领域鲁棒的泛化能力。