Open-source contributor with broad interests in artificial intelligence, deep learning, and practical software development. I enjoy exploring new technologies, building reproducible projects, and contributing useful tools and ideas to the open-source community.

• Master's Degree, China University of Mining and Technology, June 2026
• Bachelor's Degree, Hefei University of Technology, 2023

My interests include, but are not limited to:

• Large Language Models (LLMs)
• 3D point cloud processing and understanding
• Deep learning with PyTorch
• Multimodal learning and computer vision
• Model training, evaluation, and deployment
• Reproducible research and open-source development

• 704 contributions on GitHub in 2025
• 558 contributions on GitHub in 2026 as of July 2026
• My open-source project chunkasr, focused on streaming and offline speech recognition, has received 212 forks.
• Actively involved in code development, documentation, experimentation, and project maintenance
• Interested in developing practical and reusable tools for research and engineering
• Committed to making continuous and meaningful contributions to the open-source community

• Deepen my understanding of large language models and multimodal intelligence
• Explore efficient methods for 3D point cloud analysis
• Build reliable and reproducible deep-learning projects with PyTorch
• Improve the quality, usability, and documentation of open-source projects
• Collaborate with developers and researchers from different technical backgrounds

• Clear and maintainable code
• Reproducible and documented experiments
• Practical solutions before unnecessary complexity
• Continuous learning and long-term contribution

Thanks for visiting my profile. I look forward to learning from the community and contributing more valuable open-source work.