- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper introduces ScreenRef, a large-scale GUI grounding dataset with 586K screenshots and 633K referring expressions across desktop, web, and mobile platforms. Based on this dataset, the authors propose D2RL, which applies on-policy self-distillation before reinforcement learning, and train GroundGUI-8B. The model achieves competitive performance on several GUI grounding benchmarks.
Critical strengths
- The data construction pipeline is complete and carefully designed.
- The experimental evaluation is comprehensive. The paper evaluates GroundGUI-8B on five GUI grounding benchmarks and includes both dataset-level comparisons and ablation studies for the proposed training pipeline.
Critical weaknesses
-
Insufficient motivation for ScreenRef and D2RL. The paper claims that existing datasets lack diversity or annotation quality and that RL suffers from sparse rewards, but these issues are not sufficiently quantified before introducing the new dataset and training method. As a result, the necessity of both contributions is not fully convincing.
-
Relatively modest gain from D2RL. From the ablation study, the additional benefit of combining the two stages appears limited.
Questions for authors
-
Can the authors provide more direct evidence that existing GUI grounding datasets are limited in diversity or annotation quality?
-
How severe is the sparse-reward problem in practice?
-
Given the relatively small gain over OPSD or RLOO alone, what is the main advantage of the D2RL method?