20 papers
Surprise2Refine: Axis-Centered Exploration-To-Refinement for Agent-Assisted Creative Scaffolding
Yuzhe You, Gromit Yeuk-Yin Chan, Shunan Guo +4
Designers require different design spaces across creative stages: broad during exploration, and targeted during refinement. Yet existing agent-driven tools assume a fixed or contin…
CoAdapt-GUI: Joint Workflow Context and Policy Adaptation for Unseen GUI Applications
Linqiang Guo, Li Gu, Zihuan Jiang +8
Mobile GUI agents remain brittle when deployed to applications absent from source training. We study novel-app generalization under a limited target interaction budget and without…
Benchmarking LLM Judges for Mobile Agent Evaluation
Ziqiang Wang, Ziqiang Wan, Li Gu +5
Mobile agent benchmarks increasingly rely on LLM-based judges to evaluate task completion, yet the reliability of these judges on mobile agent trajectories remains largely unexamin…
DA-MergeLoRA: Hypernetwork-Based LoRA Merging for Few-Shot Test-Time Domain Adaptation
Siobhan Reid, Zhixiang Chi, Li Gu +3
Few-shot Test-Time Domain Adaptation (FSTT-DA) seeks to adapt models to novel domains using only a handful of unlabeled target samples. This setting is more realistic than typical…
Dynamic Neural Graph Encoding of Inference Processes in Deep Weight Space
Di Wu, Huan Liu, Zhixiang Chi +3
The rapid advancements in using neural networks as implicit data representations have attracted significant interest in developing machine learning methods that analyze and process…
No Adaptation Without Observation: Observability-Constrained Test-Time Prompt Tuning for LiDAR Semantic Segmentation
Linlian Jiang, Wentao Ju, Sadman Rakib Pinon +4
LiDAR semantic segmentation often degrades under real-world deployment due to evolving sensing conditions, while collecting new annotations for retraining is impractical. Test-time…