Hi, I'm Haoyu Gu!
Undergraduate Student in Artificial Intelligence
I'm passionate about Symbolic Music Representation and Generation, Speech and Audio, and Affective Computing. Let's build something interesting together! 🚀
📞 +86 181-0060-7076 | 📧 ghy20050104@gmail.com
📍 Guangzhou, Guangdong, China | Last Update: October 18, 2025
👋 About Me
Current Status
I'm currently pursuing my bachelor's degree in Artificial Intelligence at the School of Future Technology, South China University of Technology (SCUT).
📍 Location
Based in Guangzhou during the semester, and in Nanjing during vacations.
🎓 Education
South China University of Technology
985 Project University, Excellence 9 (E9) League Member
未来技术学院 - One of China's first 12 Future Technology Schools
Major: Artificial Intelligence
Academic Performance: GPA 3.95+, Average Score 93+, Top 3 in Major
Core Courses: C++ Programming, Python Programming, Discrete Mathematics, Data Structures, Computer Networks, Computer Organization and Architecture, Database Systems, Circuit Analysis and Analog Circuits, Digital Circuits, Signals and Systems, Digital Signal Processing, Machine Learning, Deep Learning and Computer Vision
English Proficiency: CET-4, CET-6 Certified
Languages & Skills: C++, Python, MATLAB, LaTeX
National College Entrance Examination (Gaokao)
Total Score: 644
Subject Scores: Chinese: 106, Mathematics: 131, English: 129, Physics: 96, Chemistry: 92, Biology: 90
Nanjing Ninghai High School
The Affiliated High School of Nanjing Normal University, Shuren School
Nanjing Langya Road Primary School
🏆 Honors & Awards
Future Technology Taihu Innovation Award
学业创新一等奖
无锡市政府
Lanqiao Cup C++ Programming Contest (Group A)
广东省二等奖
工业和信息化部人才交流中心
China Mathematics Competition
广东赛区二等奖
中国数学会
SCUT Mathematical Contest
一等奖
华南理工大学数学学院
China Undergraduate Mathematical Contest in Modeling
广东省二等奖
中国工业与应用数学学会
Embedded Chip and System Design Competition
南部赛区二等奖
中国电子学会
🧠 Research Interests
🎵 Symbolic Music Representation and Generation
Research on computational methods for representing and generating symbolic music, exploring how to effectively model musical structures and patterns using machine learning approaches.
🎙️ Speech and Audio
Research in speech and audio processing, including speech recognition, audio analysis, and sound generation using deep learning and signal processing techniques.
💫 Affective Computing
Research in emotion recognition and affective modeling to create more empathetic and responsive AI systems that can understand and respond to human emotions.
🔬 Research Experience
🎼 Symbolic Music Generation
✓ Achieved Progress
We have made significant advances in long-sequence symbolic music generation, developing novel methodologies that enable models to produce extended musical compositions while maintaining structural coherence and thematic consistency throughout the piece. Our work addresses the challenge of generating music that remains musically logical and aesthetically pleasing over longer time spans. Additionally, we have proposed efficient symbolic music representation schemes that strike an optimal balance between information preservation and computational efficiency, allowing for more effective training and inference in music generation systems.
🔄 Ongoing Research
Our current research focuses on three key directions. First, we are investigating controllable music generation methods that enable fine-grained manipulation of musical attributes including style, dynamics, articulation, and harmonic progression, allowing for more precise creative control over the generation process. Second, we are working on enhancing model robustness to ensure consistently high-quality outputs across diverse musical contexts, genres, and compositional scenarios. Third, we are exploring the exciting intersection of music generation and affective computing, developing systems that can recognize, interpret, and generate music with emotional expressiveness, ultimately creating AI systems capable of producing emotionally resonant and contextually appropriate musical content.
🎵 Research Outputs
Music generation samples from our research
长期语义连贯
全曲主题发展连贯，乐句结构清晰，旋律走向符合音乐逻辑
双声部协调
钢琴左右手配合默契，旋律对话清晰，声部走向和谐
创造性表达
和声进行富有新意，旋律转折出人意料，节奏型设计巧妙
调性转换
调式转换自然流畅，使用合理的转调和弦，不同调性之间过渡平滑
📚 Publications
ICASSP 2026Pianoroll-Event: A Novel Score Representation for Symbolic Music
Proposed a novel Pianoroll-Event representation that converts Pianoroll into event sequences for efficient compression while ensuring lossless information. This method significantly reduces sequence length and improves generation quality. Responsible for core encoding design, main paper writing, and critical code implementation.
AAAI 2026Anchored Cyclic Generation: A Paradigm for Long-Sequence Symbolic Music Generation
Proposed the Anchored Cyclic Generation paradigm with anchor features to dynamically correct generation and mitigate error accumulation in long-sequence modeling. Constructed a hierarchical anchoring framework using global sketch and local refinement strategies. Responsible for algorithm analysis, method section writing, and model experiments.
🛠️ Programming Languages & Tools
Python
Advanced
深度学习
C++
Advanced
数据结构与算法
MATLAB
Intermediate
信号处理
LaTeX
Advanced
论文和报告
🎤 Talks & Presentations
AI Journey: From Study to Research
As a member of the AI Association Academic Resources Department, I was invited to share insights on academic studies, competitions, research, and essential computational tools for computer science majors.
Academic Planning & Experience Sharing
Invited as a student representative to share academic insights and planning strategies with the incoming class of 2025 freshmen.
University Life Guide for New Students
Invited as a student representative to welcome and guide the class of 2024 freshmen, sharing insights on university academic life and providing practical guidance for their college journey.
📮 Get in Touch!
Website
GitHub
WeChat & Phone
✨ Thanks for visiting! Feel free to connect and say hello! 👋😄