@hugothomel: how small can you make a world model? we built mira mini, the first reproduction of mira: • reproduced in a week from…
Summary
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.
View Cached Full Text
Cached at: 07/17/26, 12:25 AM
how small can you make a world model?
we built mira mini, the first reproduction of mira: • reproduced in a week from scratch • four players, one shared rocket league match, in the browser • distilled to 364m params,
weights, code, full report: all open. https://t.co/nui5agbcT8
Similar Articles
MIRA: Multiplayer Interactive World Models Trained on Rocket League
MIRA is a world model trained on multiplayer Rocket League gameplay, enabling interactive simulation.
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.
@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.
@devemin: Can you play sim right away on the web lol https://huggingface.co/spaces/pollen-robotics/microduck-simulator…
A tweet shares a link to the Microduck Sandbox on Hugging Face Spaces, a web-based simulator by pollen-robotics that can be played directly in the browser.
@heyrobinai: THE ENTIRE AI INDUSTRY JUST GOT HUMILIATED a tiny model trained in just a few hours on a single graphics card is planni…
Yann LeCun's team releases LeWorldModel, a tiny 15M-parameter physics model trained on a single GPU in hours that outperforms billion-dollar foundation models in planning speed and physical plausibility, challenging the dominant scaling paradigm.