Papers
arxiv:2605.12549

What Happens Before Decoding? Prefill Determines GUI Grounding in VLMs

Published on May 10
Authors:
,
,
,
,
,
,

Abstract

Existing training-free approaches for GUI grounding often rely on multiple inference runs, such as iterative cropping or candidate aggregation, to identify target elements. Despite this additional computation, each forward pass still independently interprets the instruction and parses the visual layout, without enabling progressive interaction among visual tokens. In this paper, we study what happens during GUI grounding in Vision-Language Models (VLMs) and identify a previously overlooked bottleneck. We show that grounding follows a two-stage paradigm: the prefill stage determines candidate UI elements, while the decoding stage subsequently refines the final coordinates. This asymmetry establishes prefill as the critical step, as errors in candidate selection cannot be effectively corrected during decoding. Based on this observation, we propose Re-Prefill, a training-free method that revisits inference by introducing an attention-guided second prefill stage to refine target selection. Specifically, visual tokens that consistently receive high attention from the query position, i.e., the final token, across layers are extracted as a preliminary target hypothesis and appended to the input, together with the instruction hidden states, enabling the model to deeply re-think its decision before coordinate generation. Experiments across four VLMs and five benchmarks, including ScreenSpot-Pro, ScreenSpot-V2, OSWorld-G, UI-Vision, and MMBench-GUI, demonstrate consistent improvements without additional training, with gains of up to 4.3% on ScreenSpot-Pro. Code will be available at https://github.com/linjiaping1/Re-Prefill.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2605.12549
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2605.12549 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2605.12549 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2605.12549 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.