conftrace_

ui grounding

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

screen stream understanding (1) mobile gui agent (1) screen understanding (1) positional continuity (1) patch-level supervision (1) visual token selection (1) gui agent (1) visual token pruning (1) visual encoder (1) vision-language model (1)

Papers

FocusUI: Efficient UI Grounding via Position-Preserving Visual Token Selection CVPR 2026 UI-Hawk: Unleashing the Screen Stream Understanding for Mobile GUI Agents EMNLP 2025