arXiv subjects

Yanlai Wu

Publications and source records attributed to Yanlai Wu.

4 recordsLinked to original sources

arXiv2026

Privacy Control in Conversational LLM Platforms: A Walkthrough Study

Large language models (LLMs) are increasingly integrated into daily life through conversational interfaces, processing user data via natural language inputs and exhibiting advanced reasoning capabilities, which raises new concerns about user control over privacy. While much research has focused on potential privacy risks, less attention has been paid to the data control mechanisms these platforms provide. This study examines six conversational LLM platforms, analyzing how they define and implement features for users to access, edit, delete, and share data. Our analysis reveals an emerging paradigm of data control in conversational LLM platforms, where user data is generated and derived through interaction itself, natural language enables flexible yet often ambiguous control, and multi-user interactions with shared data raise questions of co-ownership and governance. Based on these findings, we offer practical insights for platform developers, policymakers, and researchers to design more effective and usable privacy controls in LLM-powered conversational interactions.

cs.HC↗

arXiv2025

WIP: Enhancing Game-Based Learning with AI-Driven Peer Agents

This work-in-progress paper presents SPARC (Systematic Problem Solving and Algorithmic Reasoning for Children), a gamified learning platform designed to enhance engagement and knowledge retention in K-12 STEM education. Traditional approaches often struggle to motivate students or facilitate deep understanding, especially for complex scientific concepts. SPARC addresses these challenges by integrating interactive, narrative-driven gameplay with an artificial intelligence peer agent built on large language models. Rather than simply providing answers, the agent engages students in dialogue and inquiry, prompting them to explain concepts and solve problems collaboratively. The platform's design is grounded in educational theory and closely aligned with state learning standards. Initial classroom pilots utilized a multi-method assessment framework combining pre- and post-tests, in-game analytics, and qualitative feedback from students and teachers. Preliminary findings indicate that SPARC significantly increases student engagement, with most participants reporting greater interest in STEM subjects and moderate gains in conceptual understanding observed in post-test results. Ongoing development focuses on refining the AI agent, expanding curriculum integration, and improving accessibility. These early results demonstrate the potential of combining AI-driven peer support with game-based learning to create inclusive, effective, and engaging educational experiences for K-12 learners.

cs.CY↗

arXiv2025

Enhancing Fatigue Detection through Heterogeneous Multi-Source Data Integration and Cross-Domain Modality Imputation

Fatigue detection for human operators is important in safety-related applications such as aviation, mining, and long-haul transport. Reliable estimation of operator fatigue can support timely warnings, adaptive task scheduling, takeover reminders, and other safety-management decisions in human-machine systems. However, the effectiveness of these functions depends on whether fatigue-related signals can be reliably captured in the deployment environment. While many studies have shown the value of high-fidelity sensors in controlled laboratory environments, their performance often degrades when used in real-world settings because of noise, lighting conditions, and field-of-view constraints, thereby limiting their practical use. This paper formalizes a deployment-oriented setting for real-world fatigue detection, where high-quality sensors are often unavailable in practical applications. To address this issue, we use knowledge from heterogeneous source domains, including high-fidelity sensors that are difficult to deploy in the field but commonly used in controlled environments, to assist fatigue detection in the real-world target domain. Based on this idea, we design a heterogeneous and multi-source fatigue-detection framework that uses the available modalities in the target domain while leveraging diverse configurations in the source domains through cross-domain modality imputation based on shared modalities.

cs.RO↗

arXiv2023

TIDE: Test Time Few Shot Object Detection

Few-shot object detection (FSOD) aims to extract semantic knowledge from limited object instances of novel categories within a target domain. Recent advances in FSOD focus on fine-tuning the base model based on a few objects via meta-learning or data augmentation. Despite their success, the majority of them are grounded with parametric readjustment to generalize on novel objects, which face considerable challenges in Industry 5.0, such as (i) a certain amount of fine-tuning time is required, and (ii) the parameters of the constructed model being unavailable due to the privilege protection, making the fine-tuning fail. Such constraints naturally limit its application in scenarios with real-time configuration requirements or within black-box settings. To tackle the challenges mentioned above, we formalize a novel FSOD task, referred to as Test TIme Few Shot DEtection (TIDE), where the model is un-tuned in the configuration procedure. To that end, we introduce an asymmetric architecture for learning a support-instance-guided dynamic category classifier. Further, a cross-attention module and a multi-scale resizer are provided to enhance the model performance. Experimental results on multiple few-shot object detection platforms reveal that the proposed TIDE significantly outperforms existing contemporary methods. The implementation codes are available at https://github.com/deku-0621/TIDE

cs.CV↗