Dev
GitHub repos gaining traction - what high-signal users are starring and what's climbing the board, captured daily and enriched from GitHub. Raw material for spotting new tech and patterns worth building on.
3,195
repos tracked
105
surfaced this week
193
created < 30d
Python
top language
183 repos
-
Scribed notes for the [IFT6169] Deep Learning Theory course at UdeM
-
TabICLv2: An open tabular foundation model
-
scikit-learn: machine learning in Python
-
Tensor library for machine learning
-
Dive into Deep Learning - Quarto rebuild
-
MathVista: data, code, and evaluation for Mathematical Reasoning in Visual Contexts
-
An interactive HTML pretty-printer for machine learning research in IPython notebooks.
-
Tensors and Dynamic neural networks in Python with strong GPU acceleration
-
Open ABI and FFI for Machine Learning Systems
-
MaxApki: flash-card apps, scheduled with FSRS
-
The Julia Programming Language
-
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
-
Benchmarks scikit-learn-compatible machine learning libraries
-
Implement a reasoning LLM in PyTorch from scratch, step by step
-
SGLang is a high-performance serving framework for large language models and multimodal models.
-
Train transformer language models with reinforcement learning.
-
Autoresearch agents that improve your benchmark: independent re-measurement, enforced budgets, results as pull requests
-
Unified framework for robot learning with multi-physics/renderer support
-
Native iPad chess learning app
-
Isaac Lab API, powered by MuJoCo-Warp, for RL and robotics research
-
Textbook on reinforcement learning from human feedback
-
Docs of the Hugging Face Hub
-
Machine Learning Engineering Open Book
-
Open Machine Learning Compiler Framework
-
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
-
JAX in JavaScript – ML library for the web, running on WebGPU & Wasm
-
Small reproducible problems for Sutro Group's energy-efficient learning research
-
Lab Website
-
Backend that powers the dataset viewer on Hugging Face dataset pages through a public API.
-
OPAL: a reactive optimizer. A coding agent rewrites the optimizer while your model trains.
-
Lectures given in the department's Advanced Topics in Machine Learning
-
Lectures given in the departments Advanced Topics in Machine Learning or NLP Module
-
Machine Learning and the Physical World module
-
Short course targeted at Exec Ed on Machine Learning, AI and Data Science
-
Multimodal RL training framework for diffusion & omni models
-
declarative self-improving language-model programs for Elixir 😇
-
Continued development of pufferdrive
-
Reproducible navigation benchmarking & residual RL fine-tuning for Wanderland
-
Hosting the scikit-learn blog.
-
Use Hugging Face with JavaScript
-
Machine learning and adaptive intelligence course
-
An open source implementation of CLIP.
-
The first exam for code agents in the physical world: frozen robot tasks from many benchmark suites, each answered with a program and verified in a separate sandbox. Runs on Harbor.
-
Software for lectures on machine learning.
-
Machine learning with dataframes
-
A scikit-learn compatible neural network library that wraps PyTorch
-
Executable RL environment for diagnosing and repairing distributed PyTorch training failures, with sandboxed execution and correctness-verified recovery rewards.
-
A standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
-
Distributed High-Performance Symbolic Regression in Julia
-
Symbolic Learning in Python and Julia