Advancing Open-source World Models

TL;DR

LingBot-World is a high-fidelity, real-time open-source world simulator capable of long-term contextual consistency across diverse environments, aiming to support community-driven applications in content, gaming, and robotics.

Contribution

This paper introduces LingBot-World, a versatile open-source world model with long-term memory and real-time performance, bridging the gap between open and closed-source simulation technologies.

Findings

Supports diverse environments including realistic and cartoon styles

Maintains contextual consistency over minute-long horizons

Achieves real-time interactivity with under 1 second latency

Abstract

We present LingBot-World, an open-sourced world simulator stemming from video generation. Positioned as a top-tier world model, LingBot-World offers the following features. (1) It maintains high fidelity and robust dynamics in a broad spectrum of environments, including realism, scientific contexts, cartoon styles, and beyond. (2) It enables a minute-level horizon while preserving contextual consistency over time, which is also known as "long-term memory". (3) It supports real-time interactivity, achieving a latency of under 1 second when producing 16 frames per second. We provide public access to the code and model in an effort to narrow the divide between open-source and closed-source technologies. We believe our release will empower the community with practical applications across areas like content creation, gaming, and robot learning.