MIRA: Multiplayer Interactive World Models Trained on Rocket League
Summary
MIRA is a world model trained on multiplayer Rocket League gameplay, enabling interactive simulation.
View Cached Full Text
Cached at: 07/09/26, 07:39 AM
Similar Articles
Multiplayer Interactive World Models with Representation Autoencoders
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.
@hugothomel: how small can you make a world model? we built mira mini, the first reproduction of mira: • reproduced in a week from…
Built Mira Mini, the first reproduction of Mira, in one week with 364m parameters, supporting four-player Rocket League in the browser, fully open source.
@kyutai_labs: Today we’re introducing MIRA, a new multiplayer world model, built with @gen_intuition, in collaboration with Epic Game…
Kyutai Labs introduces MIRA, a new multiplayer world model developed with Gen Intuition and Epic Games, releasing a technical report, dataset, and online demo.
MASS: Multiplayer World Models with Authoritative Shared State
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
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.