4 papers
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…
Automating Android Build Repair: Bridging the Reasoning-Execution Gap in LLM Agents with Domain-Specific Tools
Ha Min Son, Huan Ren, Xin Liu +1
Android is the largest mobile platform, yet automatically building applications remains a practical challenge. While Large Language Models (LLMs) show promise for code repair, thei…
Domain Generalization in-the-Wild: Disentangling Classification from Domain-Aware Representations
Ha Min Son, Zhe Zhao, Shahbaz Rezaei +1
Evaluating domain generalization (DG) for foundational models like CLIP is challenging, as web-scale pretraining data potentially covers many existing benchmarks. Consequently, cur…
FixCLR: Negative-Class Contrastive Learning for Semi-Supervised Domain Generalization
Ha Min Son, Shahbaz Rezaei, Xin Liu
Semi-supervised domain generalization (SSDG) aims to solve the problem of generalizing to out-of-distribution data when only a few labels are available. Due to label scarcity, appl…