works on
bias amplification 1concept chaining 1implicit reasoning 1language model steering 1model robustness 1

From the 1 of 13 linked papers with an AI index.

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

AQuaUI: Visual Token Reduction for GUI Agents with Adaptive Quadtrees

Yuankai Li, Tinghui Zhu, Ha Min Son +3

Large Multimodal Models (LMMs) have recently emerged as promising backbones for GUI-agent models, where high-resolution GUI screenshots are introduced to the prompts at each iterat…