Improving GUI Grounding with Explicit Position-to-Coordinate Mapping
This addresses a crucial bottleneck for autonomous agents in GUI automation, though it appears incremental as it builds on existing methods to improve specific performance issues.
The paper tackles the problem of GUI grounding where current VLMs struggle with reliable patch-to-pixel mapping, especially on high-resolution displays unseen during training, by introducing RULER tokens for explicit coordinate markers and Interleaved MRoPE for improved spatial encoding, resulting in consistent accuracy gains across multiple benchmarks with the largest improvements on high-resolution interfaces.
GUI grounding, the task of mapping natural-language instructions to pixel coordinates, is crucial for autonomous agents, yet remains difficult for current VLMs. The core bottleneck is reliable patch-to-pixel mapping, which breaks when extrapolating to high-resolution displays unseen during training. Current approaches generate coordinates as text tokens directly from visual features, forcing the model to infer complex position-to-pixel mappings implicitly; as a result, accuracy degrades and failures proliferate on new resolutions. We address this with two complementary innovations. First, RULER tokens serve as explicit coordinate markers, letting the model reference positions similar to gridlines on a map and adjust rather than generate coordinates from scratch. Second, Interleaved MRoPE (I-MRoPE) improves spatial encoding by ensuring that width and height dimensions are represented equally, addressing the asymmetry of standard positional schemes. Experiments on ScreenSpot, ScreenSpot-V2, and ScreenSpot-Pro show consistent gains in grounding accuracy, with the largest improvements on high-resolution interfaces. By providing explicit spatial guidance rather than relying on implicit learning, our approach enables more reliable GUI automation across diverse resolutions and platforms.