2 citations · 4 across the 15 of their papers we have counts for
17 papers
One Rollout Is All You Get: Fully Test-Time Adaptation for GUI Agents
Ziqiang Wang, Li Gu, Zhixiang Chi +6
GUI agents are deployed with frozen weights and discard everything they experience on the job. Existing ways to update an agent's weights assume something deployment withholds: gro…
From Visual Widgets to UI Code: Efficient Tool-Grounded Generation
Houston H. Zhang, Tao Zhang, Li Gu +5
Existing screenshot-to-code systems face a trade-off between flexibility and controllability. Direct multimodal generation can hallucinate visible details, whereas structured pipel…
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, Li Gu, Zhixiang Chi +4
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…
Q-Reflector: Learning GUI Action Reflection with Generated Conditions
Linqiang Guo, Wei Liu, Li Gu +3
Mobile GUI agents require accurate action reflection for reliable long-horizon execution, assessing whether each action was successfully executed and whether its outcome constitute…
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…
Beyond the GUI Paradigm: Do Mobile Agents Need the Phone Screen?
Li Gu, Zihuan Jiang, Linqiang Guo +6
Recent advances in mobile agents are dominated by the GUI paradigm, in which agents perceive UI information and emit screen interactions. However, mobile platforms also expose a co…
ETR: Entropy Trend Reward for Efficient Chain-of-Thought Reasoning
Xuan Xiong, Huan Liu, Li Gu +4
Chain-of-thought (CoT) reasoning improves large language model performance on complex tasks, but often produces excessively long and inefficient reasoning traces. Existing methods…
Generalization in Online Reinforcement Learning for Mobile Agents
Li Gu, Zihuan Jiang, Zhixiang Chi +5
Graphical user interface (GUI)-based mobile agents automate digital tasks on mobile devices by interpreting natural-language instructions and interacting with the screen. While rec…
Widget2Code: From Visual Widgets to UI Code via Multimodal LLMs
Houston H. Zhang, Tao Zhang, Baoze Lin +10
User interface to code (UI2Code) aims to generate executable code that can faithfully reconstruct a given input UI. Prior work focuses largely on web pages and mobile screens, leav…
PointMAC: Meta-Learned Adaptation for Robust Test-Time Point Cloud Completion
Linlian Jiang, Rui Ma, Li Gu +3
Point cloud completion is essential for robust 3D perception in safety-critical applications such as robotics and augmented reality. However, existing models perform static inferen…
Plug-in Feedback Self-adaptive Attention in CLIP for Training-free Open-Vocabulary Segmentation
Zhixiang Chi, Yanan Wu, Li Gu +5
CLIP exhibits strong visual-textual alignment but struggle with open-vocabulary segmentation due to poor localization. Prior methods enhance spatial coherence by modifying intermed…
Learning to Adapt Frozen CLIP for Few-Shot Test-Time Domain Adaptation
Zhixiang Chi, Li Gu, Huan Liu +4
Few-shot Test-Time Domain Adaptation focuses on adapting a model at test time to a specific domain using only a few unlabeled examples, addressing domain shift. Prior methods lever…
MetaWriter: Personalized Handwritten Text Recognition Using Meta-Learned Prompt Tuning
Wenhao Gu, Li Gu, Ching Yee Suen +1
Recent advancements in handwritten text recognition (HTR) have enabled the effective conversion of handwritten text to digital formats. However, achieving robust recognition across…
DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning
Wenhao Gu, Li Gu, Ziqiang Wang +2
Despite recent significant advancements in Handwritten Document Recognition (HDR), the efficient and accurate recognition of text against complex backgrounds, diverse handwriting s…
Distribution Alignment for Fully Test-Time Adaptation with Dynamic Online Data Streams
Ziqiang Wang, Zhixiang Chi, Yanan Wu +4
Given a model trained on source data, Test-Time Adaptation (TTA) enables adaptation and inference in test data streams with domain shifts from the source. Current methods predomina…
Adapting to Distribution Shift by Visual Domain Prompt Generation
Zhixiang Chi, Li Gu, Tao Zhong +4
In this paper, we aim to adapt a model at test-time using a few unlabeled data to address distribution shifts. To tackle the challenges of extracting domain knowledge from a limite…