I'm a CS student at Soochow University. I’m a curious, energetic person who loves exploring, tinkering, and innovating. I stay positive and resilient under pressure, and my biggest strength is learning by doing—adapting fast, enjoying the unknown, and quickly getting up to speed across disciplines.

I work at the intersection of music information retrieval and embodied 3D safety understanding. I am interested in how geometry can become a useful inductive bias for neural sequence and vision-language models.

#	Project	Description	Tech
1	Echoesphere	My graduation project — an experimental interactive game where sound shapes the world
2	echoesphere_agent	AI decision-making agent for exhibition contexts
3	echoesphere-communication	Raspberry Pi sensor data collection & LED strip control
4	perry_hermes	A vibe-coded AI agent in Rust
5	amagicpear.github.io	My personal homepage

Domain	Stack
Languages
Frameworks
AI / ML
Music
Design
Infra

• Exploring chord progression generation with geometry-aware tokenisation
• Exploring 3D safety understanding in 3D Gaussian Splatting scenes
• Building multimodal interaction systems (vision + language + hardware)
• Learning Rust for systems-level performance
• Making LLM-powered tools that simplify real-world workflows

"The best code is the code that doesn't exist — but if it must exist, make it minimal."

I'm not trying to write the most code. I'm trying to write the least code that does the most. Every refactor, every optimization, every architectural decision starts with one question: can this be simpler?