Bagel Labs is a physical AI research lab based in San Francisco and Toronto. It has developed an architecture that uses dramatically less data and compute to train while delivering a state-of-the-art model-size/performance tradeoff. WorldDiT demonstrates the model advantage; Paris 1.0 and Paris 2.0 demonstrate the training advantage.

WorldDiT couples continuous action generation with auxiliary future normalized RGB patch prediction in one diffusion transformer. The architecture is designed as a general backbone for world and action modeling, while the current release evaluates it on LIBERO and provides four checkpoints, a self contained inference runtime, and an evaluator.

The four clips below show successful rollouts from the released checkpoints. Each clip covers a different LIBERO suite and camera view.

Spatial MP4 · Object MP4 · Goal MP4 · Long MP4

The repository is self contained for WorldDiT inference. LIBERO provides the benchmark environments, assets, task definitions, and initial states.

The released runtime and checkpoints were revalidated from a clean installation on eight RTX Pro 6000 Blackwell GPUs. The reported aggregate covers five hundred simulator episodes per suite. Three hundred episodes per suite informed staged checkpoint selection, while two hundred episodes per suite were disjoint from selection.

Among methods with complete four suite averages, WorldDiT lies on the reported Pareto frontier for total model parameters and mean LIBERO success.

_{Reported LIBERO success against total model parameters for 24 methods. The line connects methods on the Pareto frontier with complete four suite averages. Because the methods follow different published evaluation protocols, the figure summarizes published results rather than a direct comparison under one common evaluation protocol.}

Download the repository and create a clean Python 3.12 environment.

LIBERO supplies the benchmark definitions, assets, and initial states. Keep the checkout at ~/LIBERO, which is the evaluator's default.

The released evaluation was validated with LIBERO commit 8f1084e3132a39270c3a13ebe37270a43ece2a01.

A successful smoke test confirms that the environment, checkpoint, visual encoders, simulator, and rendering path load together. Full benchmark reporting uses complete suite evaluations.

Each of three recent observation steps contributes primary and wrist images together with robot state, while one language instruction conditions the sequence. During training, one diffusion transformer backbone learns a seven step action chunk together with an auxiliary future normalized RGB patch target. At deployment, the encoded history conditions the action velocity field directly. RGB patch token construction and RGB prediction head evaluation remain outside the inference graph, concentrating computation on action generation. The controller executes the first three predicted actions, observes again, and replans.

_{WorldDiT inference pipeline. The encoded observation history conditions action generation through twenty flow steps. The controller executes the first three actions from each seven action chunk, then updates the window and replans.}

If you use WorldDiT in your research, please cite the paper.

The WorldDiT checkpoints, model card, and original release materials are licensed under Creative Commons Attribution 4.0 International. You may copy, redistribute, and adapt them, including commercially, with appropriate credit to Bagel Labs and the WorldDiT authors, a link to the license, and an indication of any changes. Third party dependencies and assets remain governed by their upstream licenses.

WorldDiT is developed by Sen Wang, Praveen Rajasekhar, Bidhan Roy, and Marcos Villagra at Bagel Labs. Questions can be sent to research@bagel.com.

This release builds on LIBERO, robosuite, OpenAI CLIP, and Masked Autoencoders. Third party components remain subject to their respective upstream terms.