GroundCascade: Selective Second Opinions for GUI Grounding
cs.CV
Submitted: 2026-11-09
Updated: 2026-11-09
Code: https://github.com/vocaela/kv-ground
Terminology
Sources
- MHVF: Training-Free GUI Grounding via Verification-Guided Multi-Hypothesis Search
- RankGround: Efficient High-Resolution GUI Grounding via Lightweight Reranker-Guided Crop Selection
- GUI-Lens: Enabling Precise GUI Grounding for Off-the-Shelf VLMs via Coarse-to-Fine Cropping
- Zoom in, Click out: Unlocking and Evaluating the Potential of Zooming for GUI Grounding
- Zoom Consistency: A Free Confidence Signal in Multi-Step Visual Grounding Pipelines
- Chain-of-Ground: Improving GUI Grounding via Iterative Reasoning and Reference Feedback
- How Many Pixels Is a Digit Worth? Place-Aware Coordinate Entropy for GUI Agent Confidence Estimation
- Generalist Scanner Meets Specialist Locator: A Synergistic Coarse-to-Fine Framework for Robust GUI Grounding
- What Happens Before Decoding? Prefill Determines GUI Grounding in VLMs
- Adaptive Vision-Language Model Routing for Computer Use Agents
- UI-Zoomer: Uncertainty-Driven Adaptive Zoom-In for GUI Grounding
- UI-Venus-2 Technical Report
- UI-Venus-1.5 Technical Report
- SafeGround: Know When to Trust GUI Grounding Models via Uncertainty Calibration
- LEASH: Uncertainty-Aware Weak-to-Strong Escalation and Oversight for Computer-Use Agents
- Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents
- AutoFocus: Uncertainty-Aware Active Visual Search for GUI Grounding
- LookAgain: Closed-Loop GUI Grounding with Visually Grounded Reflection
- MAI-UI Technical Report: Real-World Centric Foundation GUI Agents
- Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs