# InnerZoom：单前向跨层证据桥接实现精准高效GUI定位

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-06-29 08:00
- AIHOT 分数：50
- AIHOT 链接：https://aihot.virxact.com/items/cmr059nvo0405slki0ytxvypm
- 原文链接：https://arxiv.org/abs/2606.30084

## AI 摘要

针对MLLM自回归坐标生成丢失区域级目标证据的问题，InnerZoom提出单前向跨层证据桥接框架，将原始前向中的目标线索压缩为跨层证据状态，在后序解码层保留、精炼并重新注入以指导坐标预测。InnerZoom-4B在全部六个GUI定位基准上达到最优，OSWorld-G 64.7、UI-Vision 40.2、OSWorld-GR 73.1、MMBench-GUI 87.6，分别超此前最佳4.1、3.2、2.9、2.3分。相比同基线平均提升5.3点，对比两遍ZoomIn平均提升1.3点，端到端延迟降低31.8%，TFLOPs降低约29%。代码与模型将开源。

## 正文

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.