Jesse Zhang

Beijing University of Technology B.S., Beijing University of Technology (2025)

I'm a senior student at Beijing University of Technology, advised by Xiaoyan Li. My research interests span a wide range of topics, including Large Language Models (LLMs), Agents, Reinforcement Learning, and Embodied Intelligence 🤖. My vision is to ensure that everyone can benefit from artificial intelligence, rather than seeing their quality of life and well-being diminished by technological advancements. I love sharing ideas and experiences on my blog — come take a look! 👀

Looking for a Research Internship opportunity!

Technical Skills 🛠️
Languages: Python, C++, JavaScript/TypeScript, SQL
Frameworks & tools: PyTorch, OpenAI Triton, React/Next.js, Docker, Git


Education
  • Beijing University of Technology

    Beijing University of Technology

    B.S. in Artificial Intelligence Sep. 2021 - Jul. 2025 (Expected)

  • The Affiliated High School of Peking University

    The Affiliated High School of Peking University

    High School Diploma Sep. 2019 - Jul. 2021

Honors & Awards
  • Provincial First Prize, China Undergraduate Mathematical Contest in Modeling (CUMCM) 2023
  • Kaggle Silver Medal (Top 5% teams), LLM Prompt Recovery Challenge 2024
Experience
  • Pony.ai

    Pony.ai

    Software Engineer Intern April. 2024 - Aug. 2024

  • Beijing University of Technology

    Beijing University of Technology

    Research Assistant (advised by Xiaoyan Li) Sep. 2024 - Now

News
2024
Looking for a research intern position!
Oct 19
Selected Publications (view all )
MemoMusic 3.0: Considering Context at Music Recommendation and Combining Music Theory at Music Generation
MemoMusic 3.0: Considering Context at Music Recommendation and Combining Music Theory at Music Generation

Luntian Mou, Yihan Sun, Yunhan Tian, Yiqi Sun, Yuhang Liu, Zexi Zhang, Ruichen He, Juehui Li, Jueying Li, Zijin Li, Feng Gao, Yemin Shi, Ramesh Jain

IEEE International Conference on Multimedia and Expo Workshops (ICMEW) 2023 Workshop

MemoMusic 3.0 enhances personalized music recommendation by considering the music listening context, and improves music generation by introducing music theory. The system considers how context affects listeners' emotional states and incorporates music theory knowledge for better generation. Using a Transformer-based framework trained on Classic, Pop, and Yanni music, it generates music based on dominant melodies with target emotional values while following music theory principles. Experimental results show improved emotional impact and user satisfaction.

MemoMusic 3.0: Considering Context at Music Recommendation and Combining Music Theory at Music Generation
MemoMusic 3.0: Considering Context at Music Recommendation and Combining Music Theory at Music Generation

Luntian Mou, Yihan Sun, Yunhan Tian, Yiqi Sun, Yuhang Liu, Zexi Zhang, Ruichen He, Juehui Li, Jueying Li, Zijin Li, Feng Gao, Yemin Shi, Ramesh Jain

IEEE International Conference on Multimedia and Expo Workshops (ICMEW) 2023 Workshop

MemoMusic 3.0 enhances personalized music recommendation by considering the music listening context, and improves music generation by introducing music theory. The system considers how context affects listeners' emotional states and incorporates music theory knowledge for better generation. Using a Transformer-based framework trained on Classic, Pop, and Yanni music, it generates music based on dominant melodies with target emotional values while following music theory principles. Experimental results show improved emotional impact and user satisfaction.

All publications