A local derivative of the D3IL demonstrations with two-camera vision coverage across all eight task subsets, LeRobot v2.1 trajectories, and precomputed LingBot-VA video/text features. Upload status: See UPLOADSTATUS.json. This repository is complete only when its status is complete. Files may appear incrementally during the initial upload. There are 25,195 train clips and 2,878 eval clips, split by episode. The release contains 8,298 Parquet trajectories, 16,596 MP4 videos, and 56,146 per-camera latent files. - lerobot/ /: meta/, data/, videos/, latents/, and per-subset configuration. - lerobot/lingbotjointconfig.json: shared action normalization and camera/channel mapping.…
Independent publisher
Omni
Zeus-Omni
Models in Library0
Datasets in Library1
Models on Hugging Face—
Followers—
Compare the published evidence
This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.