YIHUAN LI

Dr. YIHUAN LI


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
1 May 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
HWHua WU
Hua WU
HHHaotian Hong
Haotian Hong
JMJiayu Mao
Jiayu Mao
ZYZhexun Yin
Zhexun Yin
YWYanxiong Wu
Yanxiong Wu
YLYIHUAN LI
YIHUAN LI
Large language models (LLMs) have been widely used in real-world applications due to their ability to decipher and make sense of perturbed information. However, the performance of LLMs that suffered from input perturbations has not been fully analyzed. In this paper, we propose a self-correction reflection method inspired by human cognition to improve robustness and mitigate the impact of perturbations on LLM performance. Firstly, we analyze the vulnerabilities of tokenization in LLMs through empirical demonstrations, comparative analysis with human cognition, and theoretical investigation of perturbation susceptibility. Secondly, we imitate the correction of input information in the human brain, which is enhanced by the consistency principle, aiming to enable the model to correct the perturbation and reduce the impact on the final response. Finally, we conduct experiments to validate the method’s efficacy, demonstrating improved performance across multiple models and datasets. We introduce a new evaluation metric, Model-Specific Cosine Similarity (MSCS), to quantify how well a specific model understands perturbation text, providing a more comprehensive evaluation of different LLM architectures. Particularly for different types of perturbations, after applying self-correction reflection, the average MSCS improvement across all models reaches 10.88%, while the average ACC improvement is 10.22%. The study also underscores the need for more innovative tokenization techniques and architectural design to achieve human-like cognitive robustness. This study could pave the way for more reliable, adaptable, and intelligent language models capable of thriving in practical applications.

5 May 2025 in Drones
Verified
Journal Article
Open access
PDF file
HWHua WU
Hua WU
HLHao Li
Hao Li
JYJunwei Yu
Junwei Yu
YWYanxiong Wu
Yanxiong Wu
XBXiaojing Bai
Xiaojing Bai
JLJuncheng Liu
Juncheng Liu
Viewpoint planning is crucial to ensure both inspection efficiency and observation precision in UAV inspection tasks. To address the issues of excessive waypoints and inadequate observation precision in traditional methods, this paper proposes a hierarchical reinforcement learning-based viewpoint planning method. The proposed method decomposes the viewpoint planning task into a high-level waypoint planning strategy and a low-level pose and zoom planning strategy. Additionally, a reward function is designed to enhance inspection precision, enabling collaborative optimization of waypoint positions, viewpoint poses, and focal lengths. Experimental results show that, compared with the classic coverage path planning method and non-hierarchical reinforcement learning approaches, the proposed method reduces the number of waypoints by at least 70% across multiple inspection objects. Furthermore, experiments with viewpoint planning at different precision levels demonstrate that the proposed method achieves scalable precision during inspection, with the observation resolution improving to 1.51 pixels/mm. Finally, a qualitative comparison is made between the proposed method in this paper and other representative methods in viewpoint planning. These results effectively demonstrate the validity and superiority of the proposed method in improving both inspection task efficiency and observation precision.

24 December 2024
Verified
Book Chapter
Closed access
PDF file
KLKaituo Liu
Kaituo Liu
YLYIHUAN LI
YIHUAN LI
QPQiao Peng
Qiao Peng