Pytorch implementation of MeanFlow on ImageNet and CIFAR10

Benchmarking Chat Assistants on Long-Term Interactive Memory (ICLR 2025)

[ICCV 2025] CHORDS: Diffusion Sampling Accelerator with Multi-core Hierarchical ODE Solvers

Open-source unified multimodal model

verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"

An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models

Optimizing inference proxy for LLMs

[NeurIPS 2024] The implementation for the paper "Geometric Trajectory Diffusion Models".

[ICLR 2024] The implementation for the paper "Space Group Constrained Crystal Generation"

Official PyTorch implementation for "Large Language Diffusion Models"

Reproduce ICLR2025 Energy-Based Diffusion Language Models for Text Generation

A framework for few-shot evaluation of language models.

The best OSS video generation models, created by Genmo

Official implementation of FIFO-Diffusion: Generating Infinite Videos from Text without Training (NeurIPS 2024)

Official inference repo for FLUX.1 models

Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

Code release for our NeurIPS 2024 Spotlight paper "GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editing"

f-PO: Generalizing Preference Optimization with f-divergence Minimization

The collection of awesome papers on alignment of diffusion models.

[NeurIPS 2024] Physics-Informed Regularization for Domain-Agnostic Dynamical System Modeling

[ICML 2024] Official environments and JAX-implementations for "Subequivariant Reinforcement Learning in 3D Multi-Entity Physical Environments"

Hackable and optimized Transformers building blocks, supporting a composable construction.

LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

[ICML 2024 Best Paper] Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution (https://arxiv.org/abs/2310.16834)

Vector (and Scalar) Quantization, in Pytorch

Documentation on how to access and use the Quick, Draw! Dataset.

Generative Models by Stability AI

A unified framework for 3D content generation.