Starred repositories
OpenPoints: a library for easily reproducing point-based methods for point cloud understanding. The engine for [PointNeXt](https://arxiv.org/abs/2206.04670)
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train Qwen3, Llama 4, DeepSeek-R1, Gemma 3, TTS 2x faster with 70% less VRAM.
A Toolkit for OpenAI's Consistency Models.
Official implementation of IADB (Iterative α-(de)Blending: a Minimalist Deterministic Diffusion Model), published at Siggraph 2023.
PyTorch implementation for DDPM & DDIM
An interface to various automatic differentiation backends in Julia.
⚡ InstaFlow! One-Step Stable Diffusion with Rectified Flow (ICLR 2024)
A latent text-to-image diffusion model
PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
A flexible neural net training library inspired by fast.ai
CUDA accelerated rasterization of gaussian splatting
Curated list of papers and resources focused on 3D Gaussian Splatting, intended to keep pace with the anticipated surge of research in the coming months.
OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning
Differentiable Finite Element Method with JAX
Source code for Fathony, Sahu, Willmott, & Kolter, "Multiplicative Filter Networks", ICLR 2021.
Lightweight, general, scalable C++ library for finite element methods
Pre-built implicit layer architectures with O(1) backprop, GPUs, and stiff+non-stiff DE solvers, demonstrating scientific machine learning (SciML) and physics-informed machine learning methods
Diffusion models for image generation in Julia
Official repository for the paper "Grokfast: Accelerated Grokking by Amplifying Slow Gradients"