Qantara headline checkpoints

Released checkpoints for Qantara, a compact (~21M-param) JEPA world model trained from pixels and actions whose single checkpoint serves latent planning, behaviour cloning, and video-inverse inference, and for our LeWM reproduction baseline. These reproduce the Qantara and LeWM (reproduction) rows of Table 1 in the paper, Qantara: Bridge-Flow Training for Multi-Paradigm JEPA Inference.

• Project page: https://corl-team.github.io/qantara
• Code: https://github.com/corl-team/qantara
• Paper: https://arxiv.org/abs/2607.04978
• Thread: https://x.com/rusrakhimov/status/2074847486288806306

Files

24 checkpoints = 2 methods × 4 environments × 3 training seeds.

env ∈ {pusht, tworoom, cube, reacher}, seed ∈ {11, 22, 33}.

Loading

Each file is a full model object (torch.save of a jepa.JEPA). Clone the code repo, then:

import torch
model = torch.load("qantara-pusht-s11.ckpt", map_location="cpu", weights_only=False)

The repository's eval.py consumes these directly. See the repo README for the full train → eval → figure pipeline.

Citation

@misc{qantara2026,
  title     = {Qantara: Bridge-Flow Training for Multi-Paradigm JEPA Inference},
  author    = {Rakhimov, Ruslan and Bredis, George and Maksyuta, Yuriy and Gavrilov, Daniil},
  year      = {2026},
  note      = {ICML 2026 Workshop on Decision-Making from Offline Datasets to Online Adaptation (DEMO); non-archival},
  eprint    = {2607.04978},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url       = {https://arxiv.org/abs/2607.04978},
}