Han Sun

Dr. Han Sun


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 February 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
LJLinzhao Jia
Linzhao Jia
HSHan Sun
Han Sun
JJJialong Jiang
Jialong Jiang
XYXiaozhe Yang
Xiaozhe Yang
Classroom dialogue analysis is crucial as it significantly impacts both knowledge transmission and teacher–student interactions. Since the inception of classroom analysis research, traditional methods such as manual transcription and coding have served as foundational tools for understanding these interactions. While precise and insightful, these methods are inherently time-consuming, labor-intensive, and susceptible to human bias. Moreover, they struggle to handle the scale and complexity of modern classroom data effectively. In contrast, many contemporary deep learning approaches focus primarily on dialogue classification, but often lack the capability to provide deeper interpretative insights. To address these challenges, this study introduces an automated dialogue analysis system that combines scalability, efficiency, and objectivity in evaluating teaching quality. We first collected a large dataset of classroom recordings from primary and secondary schools in China and manually annotated the dialogues using multiple encoding frameworks. Based on these data, we developed an automated analysis system featuring a novel dialogue classification algorithm that incorporates speaker role information for more accurate insights. Additionally, we implemented innovative visualization techniques to automatically generate comprehensive classroom analysis reports, effectively bridging the gap between traditional manual methods and modern automated approaches. Experimental results demonstrated the system’s high accuracy in distinguishing various types of classroom dialogue. Large-scale analysis revealed key patterns in classroom dynamics, showcasing the strong potential of our system to enhance teaching evaluation and provide valuable insights for improving education practices.

14 October 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
YSYuhui Sun
Yuhui Sun
ZSZhen Sun
Zhen Sun
YLYifan Liao
Yifan Liao
ZZZongmin Zhang
Zongmin Zhang
SLShuaijun Liu
Shuaijun Liu
XZXinhu Zheng
Xinhu Zheng
Real-world agents extend language-model reasoning to digital operations and physical action, raising a central security question: how do digital-side attacks cross trust boundaries in robotic systems, and what physical safety conclusions can existing evidence support? This survey examines semantic hijacking, sensory manipulation, and middleware injection across software agents, modular robotic agents, and vision-language-action (VLA) systems. We compare how untrusted content acquires task authority, corrupted observations affect action generation, and middleware access reaches execution interfaces under different permission and control assumptions. An experiment-level analysis examines environment, trajectory, privilege and exposure, consequence, and assurance, distinguishing generated plans, software-state changes, simulated execution, and physical robot actions. The comparison reveals important evidence boundaries: RoboPAIR evaluates driving plans in Dolphins but API-mediated robot actions in Jackal, while Apollo point-cloud replay demonstrates altered braking decisions without measuring physical deceleration. These differences prevent planning or command-level success from being treated as direct evidence of physical safety violations. Across defenses, protection depends on the integrity of the state used for checking, coverage of executable command paths, and the timing of intervention. Reported attack suppression also need not imply useful protection: Safe Prompting reduces targeted attack success to zero while clean-task success also falls to zero in its LIBERO evaluation. Together, these findings identify the conditions under which digital compromise reaches physical execution, delimit the safety claims supported by current experiments, and motivate stronger assurance of action enforcement and recovery under compromised state.