MIRA - Blog post
mira-wm.com · 2,415 words · saved by 1 readers
Multiplayer world model - a dream of Rocket League.
MIRA: Multiplayer Interactive World Models with Representation Autoencoders# Hover/tap on one quarter to zoom. We train a model to simulate Rocket League, Epic Games' car-football game. It allows four players to play a 2v2 match together, responding in real time to their actions and generating a consistent view of the game at 20 fps, with a resolution of 576p split across the four players. It's a 5B-parameter diffusion transformer paired with a 600M-param video representation codec. We're open-sourcing the dataset as well as training and inference code. The project is a stepping stone to…
saved by
related reading
- Scaling Video Pretraining with Imagination Modelsinductionlabs.com
- World Models | Rohit Bandarurohitbandaru.github.io
- The Model That Dreams the Worldmoe-capital.com
- World Models: Computing the Uncomputablenotboring.co
- How not to do research - Rajan Agarwalrajan.sh
- The First Fully General Computer Action Model | blogsi.inc
- How to train a frontier-level world modelnext-state.github.io
- [2509.24527] Training Agents Inside of Scalable World Modelsarxiv.org
- A Functional Taxonomy of World Models - Dr. Fei-Fei Lidrfeifei.substack.com
- GameNGengamengen.github.io
- Can Video World Models Track Unobserved World States?joonghyuk.com
- FLUX 3 x mimic: The Next Generation of Video-Action Modelsbfl.ai