一次前向胜过两次：InnerZoom实现准确高效的GUI定位

摘要

基于MLLM的GUI定位方法通常将目标定位建模为自回归坐标生成，从而使模型能够利用MLLM强大的指令遵循和语义理解能力。然而，这种范式要求模型在解码坐标标记时，既要保留区域级的目标证据，又要达到GUI点击所需的空间精度。我们的诊断分析表明，目标区域感知能力会在解码器中间层出现，但既无法保留，也无法转化为最终的坐标预测。现有的ZoomIn类方法通过外部裁剪并重新运行的方式来解决这个问题，虽然提升了定位精度，但增加了端到端延迟和计算成本。为了在不增加额外成本的情况下保留两阶段缩放方法的精度优势，我们提出InnerZoom——一种用于跨层证据桥接的单次前向传播框架。InnerZoom将原始前向传播中与目标相关的线索转化为紧凑的跨层证据状态，然后在后续解码层中保留、精炼并重新注入该状态，以指导坐标预测。大量实验结果表明，InnerZoom-4B在所有六个GUI定位基准测试中均达到最优性能，在OSWorld-G、UI-Vision、OSWorld-GR和MMBench-GUI上分别取得64.7、40.2、73.1和87.6的成绩，分别超过此前最优结果4.1、3.2、2.9和2.3个百分点。在受控的4B设置下，InnerZoom相比相同的SFT+RL基线平均提升5.3个百分点，并且平均超过两阶段ZoomIn方法1.3个百分点，同时端到端延迟最高降低31.8%，TFLOPs降低约29%。代码和模型将公开提供。

English

MLLM-based GUI grounding methods commonly formulate target localization as autoregressive coordinate generation, enabling models to leverage the strong instruction-following and semantic understanding capabilities of MLLMs. However, this formulation requires the model to retain region-level target evidence while decoding coordinate tokens with the spatial precision demanded by GUI clicking. Our diagnostic analysis reveals that target-region awareness emerges in intermediate decoder layers but is neither retained nor translated into the final coordinate prediction. Existing ZoomIn-style methods address this issue through an external crop-and-rerun pass, which improves localization but increases end-to-end latency and computational cost. To retain the accuracy benefits of two-pass zooming without this extra cost, we propose InnerZoom, a single-forward framework for cross-layer evidence bridging. InnerZoom transforms target-related cues from the original forward pass into a compact cross-layer evidence state, then preserves, refines, and reinjects this state throughout later decoding layers to guide coordinate prediction. Extensive experimental results suggest that InnerZoom-4B achieves state-of-the-art performance on all six GUI grounding benchmarks, obtaining 64.7 on OSWorld-G, 40.2 on UI-Vision, 73.1 on OSWorld-GR, and 87.6 on MMBench-GUI, surpassing the previous best results by 4.1, 3.2, 2.9, and 2.3 points, respectively. Under a controlled 4B setting, InnerZoom improves the same SFT+RL baseline by 5.3 points on average and outperforms two-pass ZoomIn by 1.3 points on average, while reducing end-to-end latency by up to 31.8% and TFLOPs by about 29%. Code and models will be publicly available.