AutoFocus converts token perplexity into an anisotropic Gaussian uncertainty field to drive region proposals and shape-aware zooming for improved GUI grounding in VLMs.
arXiv preprint arXiv:2505.00684 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A co-evolving proposer-critic RL framework improves GUI grounding accuracy by letting the model critique its own proposals rendered on screenshots.
citing papers explorer
-
AutoFocus: Uncertainty-Aware Active Visual Search for GUI Grounding
AutoFocus converts token perplexity into an anisotropic Gaussian uncertainty field to drive region proposals and shape-aware zooming for improved GUI grounding in VLMs.
-
Measure Twice, Click Once: Co-evolving Proposer and Visual Critic via Reinforcement Learning for GUI Grounding
A co-evolving proposer-critic RL framework improves GUI grounding accuracy by letting the model critique its own proposals rendered on screenshots.