I am Linus Shyu (许发鑫), a high school student from Qinghai, China, passionate about computer science, machine learning, and product building. I serve as Co-Founder & CTO at FeelFlow.

I build and ship real-world software while exploring applied machine learning, agent systems, and competitive programming. I share what I learn on Bilibili and YouTube, and document projects and contest writeups on my blog.

My work spans research manuscripts, hackathons, and open-source tools — I care about ideas that are both technically solid and useful in practice.

• 2026 One manuscript is under peer review on OpenReview (not yet published).
• 2026 Finalist at AdventureX 2026.
• 2026 Submitted project Composer to the Apple Swift Student Challenge 2026.
• 2026 Participant at Nankathon at Nanjing University.
• 2026 Admitted to the 42 Wolfsburg intensive coding program in Germany.
• 2026 🥉 3rd Prize at MoonShot48 Hackathon in Beijing.
• 2025 🥉 3rd Prize at AdventureX 2025 (won track with XTerminal) & MSA Beijing.
• 2025 Guest at Google I/O Connect China.
• 2025 Finalist at NOI Winter Camp (2024 & 2025).
• 2025 Launched FeelFlow on the App Store.
• 2025 Attendee at the Apple Developer Center event in Cupertino, California.
• 2025 Participant at a hackathon in Changsha, Hunan.
• 2025 Attendee at the Apple Vision Pro product demonstration in Hangzhou.

Applied ML, Agent Systems, Efficient Learning

I study how machine learning systems can stay practical — fast enough to deploy, reliable enough to trust, and structured enough to improve over time. Topics include emotion-aware applications, tool-using agents, and data-efficient modeling.

Competitive programming and hackathon-style engineering keep my implementation skills sharp and grounded in real constraints.