Renyuan Liu

+86 14784206312 | rliu@e.gzhu.edu.cn

Education

• Guangzhou University B.Eng. in Computer Science (Information Security); GPA: 90.13/100.00; Ranking: Top 10%
  Sept. 2022 - Jun. 2026 (Expected)
  Curriculum: Machine Learning 100*, Data Structure and Algorithm Laboratory 99*, Operating System 98* (Course Project 95*), Programming Practice 98*, Data Structure and Algorithm 97*, Programming Laboratory I 95*, Computer Network (Course Project 95*), Principles of Computer Composition, Higher Mathematics, Discrete Mathematics, Linear Algebra, Probability and Mathematical Statistics (*: rank 1st in all students of the course).

• The University of Hong Kong/University of Macau (Summer Camp)
  Nov. 2023
  GPA: 97.50/100.00 (Interdisciplinary Programme)
  Honor: Commendation Letter for Outstanding Performance in the Winning Team

Publications

• R. Liu and Q. Fu, Attention-Driven LPLC2 Neural Ensemble Model for Multi-Target Looming Detection and Localization. Accepted at 2025 International Joint Conference on Neural Networks.

• G. Gao, R. Liu, M. Wang and Q. Fu, A Computationally Efficient Neuronal Model for Collision Detection With Contrast Polarity-Specific Feed-Forward Inhibition. Biomimetics, vol. 9, no. 11, p. 650, 2024.

Research Experience

Machine Life and Intelligence Research Centre, Guangzhou University.
Advisor: Prof. Qinbing Fu

• Attention-Driven LPLC2 Neural Ensemble Model for Multi-Target Looming Detection and Localization, paper accepted at IJCNN, first author.
  Jul. 2024 - Nov. 2024
  • Conducted a full-cycle research on modeling the lobula plate/lobula columnar, type 2 (LPLC2) neural ensemble of the fruit fly Drosophila with ultra-selectivity to looming objects for robust perception and localization of multiple looming objects by leveraging a bottom-up attention mechanism to generate attention fields driven by motion sensitive neural pathways.
  • Developed the multi-attention LPLC2 (mLPLC2) neural network model inspired by the visual system of the fly (independently, 3k lines of code in C/C++). Our current work focus on implementing mLPLC2 model into the embedded visual-perceptual and motion-control system of the micro robot Colias in real physical world (independently, 2k lines of code in C).
• A Computationally Efficient Neuronal Model for Collision Detection with Contrast Polarity-Specific Feed-Forward Inhibition, article published at Biomimetics, second author.
  Mar. 2024 - Jul. 2024
  • Participated in the entire research on modeling the optimized locust lobula giant movement detector neuron with detailed feed-forward inhibition (oLGMD) to enhance processing speed and the robustness towards translating movement.
  • Implemented oLGMD model into the embedded system of Colias (independently, 1k lines of code in C), and conducted closed-loop arena comparative experiments to evaluate performance of oLGMD, achieving the highest success ratio of collision avoidance at 97.51% while nearly halving the processing time compared with previous LGMD models; conducted all online experiments of this paper, analyzing the results using real-world data collected by the Colias robot; designed criteria to assess time efficiency and collision selectivity; led the initial writing of the introduction and experimentation sections; participated in revising the submitted paper.
• Research on Computational Neuroscience for Collision Detection
  Mar. 2023 - Present
  • Reading and giving reports of research articles during research seminars on a weekly basis.
  • Provincial Key College Students’ Innovative Entrepreneurial Training Plan Program: Bio-Inspired LGMD Collision Detection Model Leveraging Optical Flow and Learning-Based Optimization.
  • Modeled self-inhibition in neural networks for collision perception against translating motion; developed neuromorphic binocular models for collision prediction which combines directional and depth motion cues; optimized directional-selective neuron parameters using a genetic algorithm; collected a stereo RGB-D dataset capturing diverse indoor-outdoor collision scenarios to support model training and evaluation; conducted online robotic experiments with the Colias and TurtleBot robots; designed detailed figures illustrating the models and experiments; drafted manuscript introductions, and contributed to manuscript revisions. One manuscript of the above works is under review, and two are to be submitted.

Honors and Awards

• National First Prize (Top 5%), 2024 Asia and Pacific Mathematical Contest in Modeling
  Nov. 2024

• Provincial First Prize & Innovation Silver Award (Top 2 out of 1,167 Teams), the 5th “Greater Bay Area Cup” Guangdong-Hong Kong-Macao Financial Mathematics Modeling Competition
  Nov. 2024

• The Third-Class Scholarship (Top 12%), Guangzhou University
  Nov. 2024

• The First-Class Scholarship (Top 5%), Guangzhou University
  Nov. 2023

Skills

• Language: IELTS 6.5 (R8.0, L6.5, W6.0, S5.5), CET-6 564
• Programming Languages: C/C++, Python, Matlab
• Others: LaTeX, Keil, Webots, Linux, Git, Markdown, MS Office/Visio, Adobe Photoshop/Premiere Pro

Hobbies: Movie, Music, Photography, Basketball, Jogging, Badminton, Hiking.