MIRA: Multiplayer Interactive World Models Trained on Rocket League

Hacker News Top Models

Summary

MIRA is a world model trained on multiplayer Rocket League gameplay, enabling interactive simulation.

<a href="https:&#x2F;&#x2F;mira-wm.com&#x2F;blog-post&#x2F;" rel="nofollow">https:&#x2F;&#x2F;mira-wm.com&#x2F;blog-post&#x2F;</a>
Original Article
View Cached Full Text

Cached at: 07/09/26, 07:39 AM

# MIRA Source: [https://mira-wm.com/](https://mira-wm.com/) Loading…

Similar Articles

Multiplayer Interactive World Models with Representation Autoencoders

Hugging Face Daily Papers

This paper introduces MIRA, the first large-scale multiplayer world model for highly dynamic physics-based environments, trained on 10,000 hours of Rocket League gameplay. The 5-billion-parameter latent diffusion model generates stable four-player rollouts in real time, with distributional quality holding steady for hours.

MASS: Multiplayer World Models with Authoritative Shared State

Hugging Face Daily Papers

This paper introduces MASS, a method for multiplayer world models that disentangles world dynamics from view rendering using an authoritative shared state, enabling scalable and consistent multi-agent simulation with up to 1,024 concurrent players.

RISE: Adaptive Imagination for World Action Models

Hugging Face Daily Papers

RISE introduces an adaptive framework for imagination rollouts in world action models, using a counterfactual driving dataset to improve planning performance while reducing unnecessary computation.