Expertini Research Research

Browse Research Papers

1,132+ open-access research outputs.

โœ• Clear
๐Ÿ” kui wu ๐Ÿ“‚ Computer Science
Showing 1132 results for "kui wu" in Computer Science
Computer Science Preprint PDF DOI

Beyond Screenshots: Evaluating VLMs' Understanding of UI Animations

Chen Liang, Xirui Jiang, Naihao Deng, Eytan Adar, Anhong Guo ยท 2026

AI agents operating on user interfaces must understand how interfaces communicate state and feedback to act reliably. As a core communicative modality, animations are increasingly used in modern interโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Generative UI as an Accessibility Bridge: Lessons from C2C E-Commerce

Bektur Ryskeldiev ยท 2026

Web accessibility rests on static standards and developer compliance. That model frays in platforms where content is user-generated: photos arrive blurry or off-frame, descriptions skip size and condiโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

VisualNeo: Bridging the Gap between Visual Query Interfaces and Graph Query Engines

Kai Huang, Houdong Liang, Chongchong Yao, Xi Zhao, Yue Cui, Yao Tian, Ruiyuan Zhang, Xiaofang Zhou ยท 2026

Visual Graph Query Interfaces (VQIs) empower non-programmers to query graph data by constructing visual queries intuitively. Devising efficient technologies in Graph Query Engines (GQEs) for interactiโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

"We Wanted to Do Better Than the Law": Exploring UI/UX Designers' Privacy Advocacy in Practice

Keyu Yao, Jinghui Cheng, Jin L.C. Guo ยท 2026

Designers hold primary responsibility for shaping the user interface (UI) and user experience (UX) of a product. This role goes beyond aesthetics and usability, extending to the privacy outcomes of usโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

RFID-Based Non-Biometric Classroom Attendance System: Proxy Attendance Detection via Weight Sensor Integration

Furkan Ege, Muhsin Ozdemir ยท 2026

Attendance tracking in educational institutions, when conducted through traditional methods, leads to structural problems that consume instruction time and threaten academic integrity. Attendance duraโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

TraceScope: Interactive URL Triage via Decoupled Checklist Adjudication

Haolin Zhang, William Reber, Yuxuan Zhang, Guofei Gu, Jeff Huang ยท 2026

Modern phishing campaigns increasingly evade snapshot-based URL classifiers using interaction gates (e.g., checkbox/slider challenges), delayed content rendering, and logo-less credential harvesters. โ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

AgentLens: Adaptive Visual Modalities for Human-Agent Interaction in Mobile GUI Agents

Jeonghyeon Kim, Byeongjun Joung, Junwon Lee, Joohyung Lee, Taehoon Min, Sunjae Lee ยท 2026

Mobile GUI agents can automate smartphone tasks by interacting directly with app interfaces, but how they should communicate with users during execution remains underexplored. Existing systems rely onโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

ViBR: Automated Bug Replay from Video-based Reports using Vision-Language Models

Sidong Feng, Dingbang Wang, Nikola Tomic, Tingting Yu, Aldeida Aleti, Chunyang Chen ยท 2026

Bug reports play a critical role in software maintenance by helping users convey encountered issues to developers. Recently, GUI screen capture videos have gained popularity as a bug reporting artifacโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

PlayCoder: Making LLM-Generated GUI Code Playable

Zhiyuan Peng, Wei Tao, Xin Yin, Chenhao Ying, Yuan Luo, Yiwen Guo ยท 2026

Large language models (LLMs) have achieved strong results in code generation, but their ability to generate GUI applications, especially games, remains insufficiently studied. Existing benchmarks mainโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Proactive Detection of GUI Defects in Multi-Window Scenarios via Multimodal Reasoning

Xinyao Zhang, Rui Wang, Jinhao Cui, Haotian Huang, Wei Xue, Wenhua Hu, Jianwen Xiang, Rui Hao ยท 2026

Multi-window mobile scenarios, such as split-screen and foldable modes, make GUI display defects more likely by forcing applications to adapt to changing window sizes and dynamic layout reflow. Existiโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Temporal UI State Inconsistency in Desktop GUI Agents: Formalizing and Defending Against TOCTOU Attacks on Computer-Use Agents

Wenpeng Xu ยท 2026

GUI agents that control desktop computers via screenshot-and-click loops introduce a new class of vulnerability: the observation-to-action gap (mean 6.51 s on real OSWorld workloads) creates a Time-Ofโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Analysing Human Interaction with Electronic Displays in Microgravity

Pradipta Biswas, Himanshu Vishwakarma, Mukund Mitra, KamalPreet Singh Saluja, Aumkar Kishore Shah ยท 2026

Human Space Flight missions often require interaction with touchscreen displays. This paper presents a study of investigating human machine interaction with touchscreen using both finger and stylus inโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

SkillDroid: Compile Once, Reuse Forever

Qijia Chen, Andrea Bellucci, Zhida Sun, Giulio Jacucci ยท 2026

LLM-based mobile GUI agents treat every task invocation as an independent reasoning episode, requiring a full LLM inference call at each action step. This per-step dependence makes them stateless: a tโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Beyond Chat and Clicks: GUI Agents for In-Situ Assistance via Live Interface Transformation

Pan Hao, Rishi Selvakumaran, Jacob Sun, Qianwen Wang ยท 2026

Complex visual interfaces are powerful yet have a steep learning curve, as users must navigate feature-rich visual interfaces while reasoning about domain-specific operations. Existing approaches eithโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

NewsTorch: A PyTorch-based Toolkit for Learner-oriented News Recommendation

Rongyao Wang, Veronica Liesaputra, Zhiyi Huang ยท 2026

News recommender systems are devised to alleviate the information overload, attracting more and more researchers' attention in recent years. The lack of a dedicated learner-oriented news recommendatioโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

RecNextEval: A Reference Implementation for Temporal Next-Batch Recommendation Evaluation

Tze-Kean Ng, Joshua Teng-Khing Khoo, Aixin Sun ยท 2026

A good number of toolkits have been developed in Recommender Systems (RecSys) research to promote fair evaluation and reproducibility. However, recent critical examinations of RecSys evaluation protocโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Agentic Open RAN: A Deterministic and Auditable Framework for Intent-Driven Radio Control

Hengxu Li, Dongkuan Xu, Mingzhe Chen, Yuchen Liu ยท 2026

Large language models (LLMs) open new possibilities for agentic control in Open RAN, allowing operators to express intents in natural language while delegating low-level execution to autonomous agentsโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

From Words to Widgets for Controllable LLM Generation

Chao Zhang, Yiren Liu, Lunyiu Nie, Jeffrey M. Rzeszotarski, Yun Huang, Tal August ยท 2026

Natural language remains the predominant way people interact with large language models (LLMs). However, users often struggle to precisely express and control subjective preferences (e.g., tone, styleโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

GALA: Multimodal Graph Alignment for Bug Localization in Automated Program Repair

Zhuoyao Liu, Zhengran Zeng, Shu-Dong Huang, Yang Liu, Shikun Zhang, Wei Ye ยท 2026

Large Language Model (LLM)-based Automated Program Repair (APR) has shown strong potential on textual benchmarks, yet struggles in multimodal scenarios where bugs are reported with GUI screenshots. Exโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

Same Outcomes, Different Journeys: A Trace-Level Framework for Comparing Human and GUI-Agent Behavior in Production Search Systems

Maria Movin, Claudia Hauff, Aron Henriksson, Panagiotis Papapetrou ยท 2026

LLM-driven GUI agents are increasingly used in production systems to automate workflows and simulate users for evaluation and optimization. Yet most GUI-agent evaluations emphasize task success and prโ€ฆ

Read Paper โ†’
Page 1 of 57 Next โ†’