StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing

Official Implementation of Paper: WMPO: World Model-based Policy Optimization for Vision-Language-Action Models

Open-source unified multimodal model

[ICLR 2026] SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

A curated list of recent robot learning papers incorporating diffusion models for robotics tasks.

Official repository for "iVideoGPT: Interactive VideoGPTs are Scalable World Models" (NeurIPS 2024), https://arxiv.org/abs/2405.15223

CleanDiffuser: An Easy-to-use Modularized Library for Diffusion Models in Decision Making

Re-implementation of pi0 vision-language-action (VLA) model from Physical Intelligence

This repository implements a Best-of-N (BoN) strategy for inference-aware fine-tuning of large language models. The system supports multiple leading LLM providers and includes comprehensive testing…

Open-Sora: Democratizing Efficient Video Production for All

Scalable and memory-optimized training of diffusion models

Evaluating FSD on SimplerEnv

Evaluating and reproducing real-world robot manipulation policies (e.g., RT-1, RT-1-X, Octo, and OpenVLA) in simulation under common setups (e.g., Google Robot, WidowX+Bridge)

HunyuanVideo: A Systematic Framework For Large Video Generation Model

Official implementation of our paper: "Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing" (ICML 2025)

📚 Collection of awesome generation acceleration resources.

FORA introduces simple yet effective caching mechanism in Diffusion Transformer Architecture for faster inference sampling.

Inference script for Oasis 500M

RoboTwin 2.0 Offical Repo

High-speed Large Language Model Serving for Local Deployment

world modeling challenge for humanoid robots

RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots

Coherent Video Inpainting Using Optical Flow-Guided Efficient Diffusion

Two Birds, One Stone: A Unified Framework for Joint Learning of Image and Video Style Transfers(ICCV2023)