custom static site generator used for https://www.furidamu.org/

Open-source implementation of AlphaEvolve

Simple MPI implementation for prototyping or learning

A collection of projects designed to help developers quickly get started with building deployable applications using the Claude API

A standard format for offline reinforcement learning datasets, with popular reference datasets and related utilities

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.

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

My personal Obsidian vault template. A bottom-up approach to note-taking and organizing things I am interested in.

Event Log and Incident Analysis for Astronomy

[ICLR 2023] ReAct: Synergizing Reasoning and Acting in Language Models

Building Open-Ended Embodied Agents with Internet-Scale Knowledge

world modeling challenge for humanoid robots

Code repository for O'Reilly book

Isaac Gym Reinforcement Learning Environments

Implementation of Video Diffusion Models, Jonathan Ho's new paper extending DDPMs to Video Generation - in Pytorch

A simple way to keep track of an Exponential Moving Average (EMA) version of your Pytorch model

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

Simplifying reinforcement learning for complex game environments

A curated list of awesome Deep Reinforcement Learning resources.

Official code for "RB-Modulation: Training-Free Personalization of Diffusion Models using Stochastic Optimal Control"

A framework for serving and evaluating LLM routers - save LLM costs without compromising quality

The paper list of the 86-page SCIS cover paper "The Rise and Potential of Large Language Model Based Agents: A Survey" by Zhiheng Xi et al.

AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more sample and compute efficient than reinforcement learning methods…

A framework for managing and maintaining multi-language pre-commit hooks.

🔊 Text-Prompted Generative Audio Model

Implementation of 🦩 Flamingo, state-of-the-art few-shot visual question answering attention net out of Deepmind, in Pytorch