cd /news/machine-learning/mira-multiplayer-interactive-world-m… · home topics machine-learning article
[ARTICLE · art-49974] src=github.com ↗ pub= topic=machine-learning verified=true sentiment=↑ positive

MIRA: Multiplayer Interactive World Models with Representation Autoencoders

Researchers from General Intuition, Kyutai, and Epic Games released MIRA, a 5-billion-parameter latent diffusion world model that generates real-time 2v2 Rocket League matches at 20 FPS on a single GPU. The model, trained on a dataset of synchronized player views and actions, enables interactive gameplay inside the simulation and is available as open-source code with a live demo at mira-wm.com.

read3 min views1 publishedJul 7, 2026
MIRA: Multiplayer Interactive World Models with Representation Autoencoders
Image: source

readme.mp4 #

MIRA is a real-time world model of Rocket League: a 5B parameters latent diffusion model generates the video frame by frame from all four players' actions, so a full 2v2 match can be played inside the model at 20 FPS on a single GPU. Play it live at mira-wm.com.

This is the official code release for the technical report:

MIRA: Multiplayer Interactive World Models with Representation Autoencoders, a collaboration between

General Intuition, Kyutai, and Epic Games.

@article{mira2026,
  title={{MIRA}: Multiplayer Interactive World Models with Representation Autoencoders},
  author={Hu, Anthony and Volhejn, V{\'a}clav and Ramanana Rahary, Adrien and Mulder, Chris and Makkar, Aditya and Royer, Am{\'e}lie and Liao, Alyx and Orsini, Manu and Jelley, Adam and Alonso, Eloi and Laurent, Florian and Nor{\'e}n, Fredrik and Swingos, James and H{\"u}nermann, Jan and Rollins, Kent and Hosseini, Lucas and Le Cauchois, Matthieu and Peter, Maxim and de Witte, Pim and Brown, Tim and Micheli, Vincent and B{\"o}hle, Moritz and de Marmiesse, Gabriel and Sharmanska, Viktoriia and Specia, Lucia and Black, Michael and P{\'e}rez, Patrick},
  year={2026}
}
pixi run setup   # one-time: creates the environment and installs MIRA (requires an NVIDIA GPU)
pixi run test    # run the test suite

Requires pixi and torch >= 2.8 (installed for you).

Each sample is a 4-second window of a 2v2 match, captured from all four players' synchronised views. For every frame of every view, the dataset provides the video frame, the player's keyboard action, and the game state (ball, cars, and score). The full dataset is on the HuggingFace Hub (see the dataset card).

from mira.data import RocketScienceDataset

ds = RocketScienceDataset.from_hub("kyutai/rocket-science", split="test", shards=1)

clips = ds.load_match(ds.match_ids()[0], clip_len=16, target_fps=20)
clip = clips[0]

clip.frames    # tensor (P, T, C, H, W) uint8 — the rendered video, one per player
clip.actions   # tensor (P, T, 9)       int32 — multi-hot keyboard state, aligned to each frame
clip.events    # list of game events overlapping this window (goals, boost pickups, ...)
clip.physics   # per player, per frame: game state (ball, cars, score)

Explore it interactively (4-player grid, keyboard overlay, top-down overview of the game using the game state):

pixi run explore

Entry points under scripts/

are Hydra apps — override any config key as key=value

. Multi-GPU runs go through torchrun

; single-GPU works too.

python scripts/train_codec.py dataset.train_index=/path/to/train dataset.test_index=/path/to/test

python scripts/train_world_model.py \
    model.architecture.config.codec_checkpoint=/path/to/codec_ckpt \
    dataset.train_index=/path/to/train dataset.test_index=/path/to/test

python scripts/train_world_model.py model=multi_wrapper_world_model dataset.n_players=4 \
    model.architecture.config.wm_config.codec_checkpoint=/path/to/codec_ckpt \
    run.finetune_from=/path/to/single_player_ckpt \
    dataset.train_index=/path/to/train dataset.test_index=/path/to/test

Codec training uses a frozen DINOv3-L/16 encoder whose weights are gated by Meta. Download dinov3_vitl16_pretrain_lvd1689m-8aa4cbdd.pth

from the DINOv3 page and set RS_DINO_WEIGHTS_DIR=/path/to/weights

. World-model training and inference don't need it.

python scripts/eval_world_model_offline.py /path/to/checkpoint-1000/checkpoint.pth

Apache License 2.0 — see LICENSE.

── more in #machine-learning 4 stories · sorted by recency
── more on @general intuition 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/mira-multiplayer-int…] indexed:0 read:3min 2026-07-07 ·