DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

This repository provides a simple pipeline to load data, train a Pi Zero model, and evaluate its performance.

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

Implementation of π₀, the robotic foundation model architecture proposed by Physical Intelligence

Recipes for shrinking, optimizing, customizing cutting edge vision models. 💜

Coding a Multimodal (Vision) Language Model from scratch in PyTorch with full explanation: https://www.youtube.com/watch?v=vAmKB7iPkWw

A simple testbed for robotics manipulation policies

[RSS 2024] Code for "Multimodal Diffusion Transformer: Learning Versatile Behavior from Multimodal Goals" for CALVIN experiments with pre-trained weights

Code for "Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation"

TorchCFM: a Conditional Flow Matching library

Pytorch implementation of Transfusion, "Predict the Next Token and Diffuse Images with One Multi-Modal Model", from MetaAI

A flexible and efficient codebase for training visually-conditioned language models (VLMs)

A comprehensive list of papers about Robot Manipulation, including papers, codes, and related websites.

An Open-source Toolkit for LLM Development

Codebase for the BestMan Mobile Manipulator Platform

RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation

Central repository for tools, tutorials, resources, and documentation for robotics simulation in Unity.

Awesome Lists about Robot Learning.

GLM-4-Voice | 端到端中英语音对话模型

This repo is designed for General Robotic Operation System

Official implementation of CoPa: General Robotic Manipulation through Spatial Constraints of Parts with Foundation Models

Data collection part for ARCap

Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities。

Learning Latent Dynamics for Planning from Pixels

OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models

O1 Replication Journey: A Strategic Progress Report – Part I

Fast and simple implementation of RL algorithms, designed to run fully on GPU.