AI Agent Skills

Free open public domain football datasets in the Football.TXT format for the World Cup (incl. Canada/USA/Mexico 2026, Qatar 2022, Russia 2018, Brazil 2014, etc.) and Wor…

Advancing Open-source World Models

One sentence creates an AI-driven world — generate maps, characters, and watch stories emerge on their own. 一句话生成一个AI自主驱动的世界.

Implementation of Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players

基于 AI Agent 工作流的修仙世界模拟器，旨在还原智能、开放的仙侠世界。| An open-source Cultivation World Simulator using Agentic Workflow to create a dynamic, emerging Xianxia world.

Open football event data for match analysis, xG research, scouting, and World Cup-style dashboards.

:earth_americas: Simple and ready-to-use tutorials for TensorFlow

Constantly updated lists of world countries and their associated alpha-2, alpha-3 and numeric country codes as defined by the ISO 3166 standard, available in CSV, JSON ,…

A Minimalist, Batteries-included Repository for Advancing World Model Science.

MLNLP: This repository is a collection of AI top conferences papers (e.g. ACL, EMNLP, NAACL, COLING, AAAI, IJCAI, ICLR, NeurIPS, and ICML) with open resource code

A god-simulation sandbox game built on Godot 4 as a multi-agent AI social simulation system. In this virtual world, AI characters possess independent thinking and memory…

Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the future state of the world in the…

DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 Spotlight.

Official code of Motus: A Unified Latent Action World Model

The Learning Hub for UoL's Online CS Students

Cosmos-Transfer2.5, built on top of Cosmos-Predict2.5, produces high-quality world simulations conditioned on multiple spatial control inputs.