Un Forward bat Deux : InnerZoom pour un ancrage GUI précis et efficace

Résumé

基于MLLM的GUI定位方法通常将目标检测建模为自回归坐标生成，使模型能够利用MLLM强大的指令跟随和语义理解能力。然而，这种设计要求模型在解码坐标令牌时保有区域级目标证据，以满足GUI点击所需的空间精度。我们的诊断分析表明，目标区域感知能力在解码器中间层出现，但既未保留也未转化为最终的坐标预测。现有的ZoomIn式方法通过外部裁剪并重新运行来应对该问题，这虽提升了定位精度，却增加了端到端延迟和计算成本。为在不增加额外成本的前提下保留两轮缩放带来的精度优势，我们提出InnerZoom——一种跨层证据桥接的单次前向框架。InnerZoom将原始前向过程中的目标相关线索转化为紧凑的跨层证据状态，并在后续解码层中持续保留、精炼并注入该状态，以引导坐标预测。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上取得64.7，在UI-Vision上取得40.2，在OSWorld-GR上取得73.1，在MMBench-GUI上取得87.6，分别超越此前最佳结果4.1、3.2、2.9和2.3个点。在受控的4B设置下，InnerZoom相比相同SFT+RL基线平均提升5.3个点，且比两轮ZoomIn平均高出1.3个点，同时将端到端延迟降低最多31.8%，TFLOPs减少约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.