Stars
Ongoing research training transformer models at scale
Official repository for FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models
Open-source framework for the research and development of foundation models.
Official repository for Amortized Factor Inference Networks (AFINs).
OmX - Oh My codeX: Your codex is not alone. Add hooks, agent teams, HUDs, and so much more.
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
Train the smallest LM you can that fits in 16MB. Best model wins!
Code and data for analyzing investment biases of large language models in finance.
[NeurIPS 2025 spotlight] Efficient factorized variant of the IPA module.
[NeurIPS 2025] Official implementation for "Model-Informed Flows for Bayesian Inference"
A partially latent flow matching model for the joint generation of a protein’s amino acid sequence and full atomistic structure, including both the backbone and side chain.
An extremely fast Python package and project manager, written in Rust.
Genome modeling and design across all domains of life
Efficiently computes derivatives of NumPy code.
A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.
AlphaFold 3 inference pipeline.
Official code for https://arxiv.org/abs/2210.07290
AcadHomepage: A Modern and Responsive Academic Personal Homepage
Gemini is a modern LaTex beamerposter theme 🖼
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
The purpose of this repo is to make it easy to get started with JAX, Flax, and Haiku. It contains my "Machine Learning with JAX" series of tutorials (YouTube videos and Jupyter Notebooks) as well a…
A simple library to run variational inference on Stan models.
Awesome resources on normalizing flows.
A State-Space Model with Rational Transfer Function Representation.