Hi , I'm Albert !

A and

Welcome to my repo

I code with

---

🛠️ Technologies & Tools

• Web Development: Next.js, FastAPI, React, Express, Redux, React Router
• Styling: Tailwind CSS
• Build Tools: Webpack, ESLint, Yarn
• Database and Authentication: Drizzle, SQLalchemy, PostgreSQL, Supabase
• API: RESTful API
• Markdown Processing: Contentlayer
• Preferred and Used Programming Languages: Python (with PyTorch and FastAPI), TypeScript
• Known Languages: Java SE (without any framework)

🌐 Deployment

Experience deploying applications using Vercel, and VPS with Coolify.
Building infrastructure with ForwardEmail and Cloudflare.

Feel free to check out my projects and connect with me!

Email: [email protected]
Discord: @albert_zhao_ca

📝 Publications

1. Srpo: Enhancing multimodal llm reasoning via reflection-aware reinforcement learning (NeurIPS 2025) https://srpo.pages.dev/

2. SafeBehavior: Simulating Human-Like Multistage Reasoning to Mitigate Jailbreak Attacks in Large Language Models arXiv:2509.26345 https://safebehavior.trust4ai.org

3. Plan Then Action:High-Level Planning Guidance Reinforcement Learning for LLM Reasoning arXiv:2510.01833