Efficient deep learning traditionally relies on static heuristics like weight magnitude or activation awareness (e.g., Wanda, RIA). While successful in unstructured settings, we observe a critical limitation when applying these metrics to the structural pruning of deep vision networks. These contemporary metrics suffer from a magnitude bias, failing to preserve critical functional pathways. To overcome this, we propose a decoupled kinetic paradigm inspired by Alternating Gradient Flow (AGF), utilizing an absolute feature-space Taylor expansion to accurately capture the network's structural "kinetic utility". First, we uncover a topological phase transition at extreme sparsity, where AGF successfully preserves baseline functionality and exhibits topological implicit regularization, avoiding the collapse seen in models trained from scratch. Second, transitioning to architectures without strict structural priors, we reveal a phenomenon of Sparsity Bottleneck in Vision Transformers (ViTs). Through a gradient-magnitude decoupling analysis, we discover that dynamic signals suffer from signal compression in converged models, rendering them suboptimal for real-time routing. Finally, driven by these empirical constraints, we design a hybrid routing framework that decouples AGF-guided offline structural search from online execution via zero-cost physical priors. We validate our paradigm on large-scale benchmarks: under a 75% compression stress test on ImageNet-1K, AGF effectively avoids the structural collapse where traditional metrics aggressively fall below random sampling. Furthermore, when systematically deployed for dynamic inference on ImageNet-100, our hybrid approach achieves Pareto-optimal efficiency. It reduces the usage of the heavy expert by approximately 50% (achieving an estimated overall cost of 0.92$\times$) without sacrificing the full-model accuracy.

翻译：传统高效深度学习依赖静态启发式方法（如权重幅度或激活感知，例如Wanda、RIA）。尽管这些方法在非结构化场景下表现成功，但我们观察到其在深度视觉网络结构剪枝中存在关键局限：当前度量存在幅度偏差，无法保留关键功能通路。为此，我们提出受交替梯度流（AGF）启发的解耦动力学范式，利用绝对特征空间泰勒展开精准捕获网络结构的"动力学效用"。首先，我们发现在极端稀疏性下存在拓扑相变，AGF能成功维持基线功能并展现拓扑隐式正则化，避免从头训练模型中的崩溃现象。其次，转向缺乏严格结构先验的架构时，我们揭示了视觉Transformer（ViT）中的"稀疏瓶颈"现象。通过梯度-幅度解耦分析，发现动态信号在收敛模型中遭受信号压缩，导致其不适用于实时路由。最后，基于这些实证约束，我们设计了混合路由框架，通过零代价物理先验将AGF引导的离线结构搜索与在线执行解耦。我们在大规模基准上验证了该范式：在ImageNet-1K的75%压缩应力测试下，AGF有效避免了传统度量急剧低于随机抽样的结构崩溃。此外，当系统部署于ImageNet-100的动态推理时，我们的混合方法实现了帕累托最优效率：在不牺牲全模型精度的条件下，将重型专家模块的使用量减少约50%（达到0.92倍的预估总开销）。