Starred repositories
Ongoing research training transformer models at scale
A simple and powerful platform for conducting streetscape perception surveys with image-based questions. Deploy in minutes with Supabase and Vercel.
Build a modern LLM from scratch. Every line commented. Explained like we are five.
DSPy: The framework for programming—not prompting—language models
An extremely fast R package manager, written in Rust. The R equivalent of uv for Python.
A workflow of using street view imagery to estimate road slope
ML algorithms implemented and derived from first-principles in Jupyter Notebooks and NumPy
Lightweight, useful implementation of conformal prediction on real data.
A high-throughput and memory-efficient inference and serving engine for LLMs
A ready-to-fork Claude Code template for academics using LaTeX/Beamer + R. Multi-agent review, quality gates, adversarial QA, and replication protocols.
This package streamlines the process of building, managing, and updating local SQLite databases that contain geospatial features extracted from Google Earth Engine (GEE).
Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Computer Vision Annotation Tool (CVAT) is a leading platform for building high-quality visual datasets for vision AI. It offers open-source, cloud, and enterprise products, as well as labeling serv…
Official code repo for the O'Reilly Book - "Hands-On Large Language Models"
TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.
TabICLv2: A state-of-the-art tabular foundation model
Causal Inference in Observational Data with Unobserved Heterogeneity (Lecture Notes. Masters/PhD-level)
A lightweight, powerful framework for multi-agent workflows
The official Python library for the OpenAI API
Community extensions for TabPFN - the foundation model for tabular data. Built with TabPFN! 🤗
⚡ TabPFN: Foundation Model for Tabular Data ⚡