做航空视觉语言导航的看这个：DreamFly在OpenFly上SR和SPL都超过现有方法，导航误差最低，还能判断何时到达。
DreamFly 是基于 Dream-VLA 的扩散式航空视觉语言导航框架。它引入因果对齐历史记忆，仅使用当前决策前的观测增强视觉表征，避免未来信息泄漏。导航采用 receding-horizon 扩散规划，预测 K 步动作块但只执行第一步，实现 plan-K、execute-one 策略。LiteStop 在初始全掩码状态直接从动作 logits 估计停止概率，将终止判断与动作生成解耦。在 OpenFly 基准上，DreamFly 在 test-seen/test-unseen 上分别取得 32.04%/29.46% SR 和 28.22%/23.54% SPL，并达到最低导航误差。
DreamFly: Causal Memory and Receding-Horizon Diffusion Planning for Aerial Vision-Language Navigation
Aerial vision-language navigation (VLN) requires an embodied agent to integrate visual evidence over time, plan future actions, and determine when it has reached a navigation goal under partial observability. Although recent VLA models offer a promising perception-to-action paradigm, adapting them to aerial navigation remains challenging due to limited historical context, short planning horizons, and unreliable implicit termination. To address these challenges, we propose DreamFly, a diffusion-based aerial VLN framework built on Dream-VLA. DreamFly introduces a causally aligned historical memory that augments the current visual representation using only observations preceding the current decision step, enabling temporal reasoning without future information leakage. We further formulate navigation as receding-horizon diffusion planning, where the policy predicts a $K$-step action chunk but executes only the first action before replanning. This plan-$K$, execute-one strategy uses future actions as auxiliary planning targets while preserving closed-loop visual feedback. Finally, LiteStop estimates the stop probability directly from action logits at the initial all-mask state, decoupling explicit termination from action generation. Experiments on the OpenFly benchmark demonstrate consistent improvements in seen and unseen environments. DreamFly achieves 32.04%/29.46% SR and 28.22%/23.54% SPL on the test-seen/test-unseen splits, respectively, outperforming all compared methods on both metrics while attaining the lowest navigation error. These results demonstrate the effectiveness of jointly modeling historical context, future action structure, and explicit termination for aerial VLN.