M.S. in Applied Mathematics · Fudan University
English · 简体中文
I am an Applied Mathematics M.S. student at Fudan University, interested in scientific machine learning and practical AI systems. My current work explores neural operators, learning-based methods for physical systems, and AI-assisted research and engineering workflows.
Alongside research, I maintain public projects and contribute upstream to open-source projects I use, gradually building experience in agent engineering, reproducible workflows, and scientific/developer tooling.
| Area | Exploring |
|---|---|
| Scientific ML | Neural operators, PDEs, and learning for physical systems |
| Agent Engineering | Agent reliability, research agents, and developer tooling |
| Open Source | Public projects, upstream contributions, and reproducible workflows |
|
Agent-orchestrated, reproducible engineering simulation workflows with explicit physics validation. A public lab for learning and building trustworthy automation around Ansys-based simulation workflows, with solver-derived evidence and structured validation.
|
An evidence-first engineering review protocol for AI agents. A public-preview protocol for reviewing software projects with applicability-aware scoring, explicit trade-offs, and evidence-backed findings. Reviews are read-only by default.
|
|
Compare the workspace instruction surfaces seen by DeepSeek Harness, Codex, and Claude Code. A small developer tool that makes cross-agent instruction discovery differences visible, with explicit observed/predicted evidence semantics. The v0.1 release is available on npm and GitHub Releases.
|
A self-hosted, teaching-first dashboard for learning and using SLURM clusters. The interface shows the real command behind each data block, combining a practical cluster dashboard with a guided path through SLURM, GPU monitoring, and basic Linux/HPC workflows.
|
- DeepMathLLM / Creative-Intelligence — deterministic regression/integration coverage and resumable-workflow provenance/session-identity hardening (PR #1 merged, #2 merged, #3 open).
- DeepMathLLM / Moonshine — crash-safe tool execution journaling and interrupted-turn recovery (PR #4 draft).
- Scientific Machine Learning
- Neural Operators
- AI4Science
- Learning-based methods for physical systems
Open to conversations around research, open-source projects, and AI engineering.
