- Hangzhou
-
07:16
(UTC +08:00) - https://mathewshen.me/
- https://orcid.org/0009-0004-9321-4442
- in/mathewshen
Lists (7)
Sort Name ascending (A-Z)
- All languages
- Astro
- Batchfile
- C
- C#
- C++
- CMake
- CSS
- Clojure
- Cuda
- Cython
- Dart
- Dockerfile
- Elixir
- Emacs Lisp
- Erlang
- Gleam
- Go
- HTML
- Haskell
- Java
- JavaScript
- Julia
- Jupyter Notebook
- Kotlin
- Less
- Lua
- Makefile
- Markdown
- Mojo
- Nix
- PostScript
- Python
- R
- RMarkdown
- Roff
- Ruby
- Rust
- SCSS
- Scala
- Shell
- Svelte
- Swift
- TeX
- TypeScript
- Typst
- Vim Script
- Vue
- Zig
Starred repositories
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Fast Rust library for PDF inspection, classification, and text extraction. Intelligently detects scanned vs text-based PDFs to enable smart routing decisions.
Review-first terminal diff viewer for agentic coders
Open-source Reflect rewrite: A local-first AI agent-friendly Markdown note-taking app
The Little Book of Reinforcement Learning
Markdown knowledge graph — LSP for your editor, CLI + MCP memory for your AI agents
GPT-2-style LLM built from scratch in C/CUDA with hand-written backprop, BPE tokenizer, FlashAttention, pretraining, and SFT.
TabFM (Tabular Foundation Model) is a pretrained tabular foundation model developed by Google Research for tabular data regression and classification.
LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence https://arxiv.org/abs/2509.03505
A genetic algorithm implementation for Rust
⚡ TabPFN: Foundation Model for Tabular Data ⚡
Learn it. Build it. Ship it for others.
Effortlessly compose, extend, and observe every service in real-time for the first time ever.
PANTHER: Generative Pretraining Beyond Language for Sequential User Behavior Modeling (official repository)
Make your functions return something meaningful, typed, and safe!
🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.
A SOTA quantization algorithm for high-accuracy low-bit LLM inference, seamlessly optimized for CPU/XPU/CUDA, with multi-datatype support and full compatibility with vLLM, SGLang, and Transformers.
>99.5% KaTeX syntax coverage. LaTeX math renderer in pure Rust. No JavaScript, no WebView, no DOM. One Rust core → iOS, Android, Flutter, Web, PNG. C ABI · WASM · Server-side PNG/SVG.
The headless browser for AI agents and web scraping
🚀 Fast and simple Node.js version manager, built in Rust
How Do Decoder-Only LLMs Perceive Users? Rethinking Attention Masking for User Representation Learning
Repository for Fraud Dataset Benchmark
Open-source Chrome extension with a Spotlight-style command palette, instant tab, bookmark and history search, and a customizable new tab page.
OpenSeeker: A search agent with open-source data and models
Local-first observability your agent reads back. TMA1 records every LLM call, then routes what it sees into the agent's next turn via hooks and MCP.
A user-friendly, lightweight TUI for disk imaging