Talnex

ManiGaussian

[ECCV 2024] ManiGaussian: Dynamic Gaussian Splatting for Multi-task Robotic Manipulation

RL4VLM

Official Repo for Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning

MAP-NEO

prismarine-viewer

Web based viewer for servers and bots

LLaMA-Factory

A WebUI for Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

node-minecraft-protocol

Parse and serialize minecraft packets, plus authentication and encryption.

PhysDreamer

Code for PhysDreamer

2d-gaussian-splatting

[SIGGRAPH'24] 2D Gaussian Splatting for Geometrically Accurate Radiance Fields

Video-Pre-Training

Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos

DeepSeek-V2

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

neuro-ncap

NeuroNCAP benchmark for end-to-end autonomous driving

minerl

MineRL Competition for Sample Efficient Reinforcement Learning - Python Package

MC-Planner

Implementation of "Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents"

JARVIS-1

JARVIS-1: Open-world Multi-task Agents with Memory-Augmented Multimodal Language Models

MineDreamer

This repo is the official implementation of "MineDreamer: Learning to Follow Instructions via Chain-of-Imagination for Simulated-World Control "

Voyager

An Open-Ended Embodied Agent with Large Language Models

MineDojo

Building Open-Ended Embodied Agents with Internet-Scale Knowledge

MineCLIP

Foundation Model for MineDojo

fastapi

FastAPI framework, high performance, easy to learn, fast to code, ready for production

generative_agents

Generative Agents: Interactive Simulacra of Human Behavior

ReplayMod

Minecraft ReplayMod

ChatDev

Create Customized Software using Natural Language Idea (through LLM-powered Multi-Agent Collaboration)

AgentVerse

🤖 AgentVerse 🪐 is designed to facilitate the deployment of multiple LLM-based agents in various applications, which primarily provides two frameworks: task-solving and simulation

Creative-Agents

2D-Gaussian-Splatting

A 2D Gaussian Splatting paper for no obvious reasons. Enjoy!

DouZero

[ICML 2021] DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning | 斗地主AI

rlcard

Reinforcement Learning / AI Bots in Card (Poker) Games - Blackjack, Leduc, Texas, DouDizhu, Mahjong, UNO.

Cradle

The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curation, in a standardized general environment with minimal requirements.

doing_the_PhD

DouZero_For_HappyDouDiZhu

基于DouZero定制AI实战欢乐斗地主