Metraipolis › archive › dc_1fe0bb2ab2d8

WARP-JEPA: World-Model-in-the-Loop Amortized Rollout Planning for Frozen Hierarchical Joint-Embedding Predictive Architectures — arXiv:2611.10806

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.10806
License (as archived)
CC0-1.0
Archived
2026-11-10T18:41:13.304Z
SHA-256 of the archived text
ac6289adc7612b1fc945842945dd227bac66a57d128f40845bfb0546166c11f5
Stable URL of this page
https://metraipolis.com/documento/dc_1fe0bb2ab2d8

How to cite

WARP-JEPA: World-Model-in-the-Loop Amortized Rollout Planning for Frozen Hierarchical Joint-Embedding Predictive Architectures — arXiv:2611.10806 — arXiv (en), https://arxiv.org/abs/2611.10806 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1fe0bb2ab2d8 (Metraipolis archive dc_1fe0bb2ab2d8, sha256 ac6289adc7612b1fc945842945dd227bac66a57d128f40845bfb0546166c11f5)
BibTeX
@misc{dc1fe0bb2ab2d8,
  title = {WARP-JEPA: World-Model-in-the-Loop Amortized Rollout Planning for Frozen Hierarchical Joint-Embedding Predictive Architectures — arXiv:2611.10806},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.10806},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1fe0bb2ab2d8; sha256 ac6289adc7612b1fc945842945dd227bac66a57d128f40845bfb0546166c11f5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.10806. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Hierarchical Joint-Embedding Predictive Architectures (H-JEPA) enable long-horizon visual control but rely on costly test-time gradient descent for planning. Our analysis reveals that iterative optimization consumes up to 97.7% of episode runtime and that low predicted rollout costs do not necessarily translate into successful control. We further identify a planning-horizon asymmetry between long-horizon top-level composition and short two-step subordinate planning. To address these challenges, we propose WARP-JEPA, a hierarchical amortized planning framework that replaces online gradient optimization with learned multi-candidate trajectory proposers while keeping the world models frozen. WARP-JEPA combines a lightweight world-model-in-the-loop causal Transformer at the top level with parallel residual MLPs at subordinate levels. The proposers are trained using model-based rollout costs and best-of-K behavior cloning, enabling efficient candidate selection without test-time gradient optimization. Across 30 frozen H-JEPA models on four benchmarks, WARP-JEPA achieves 9.6-18.8x faster episode inference on long-horizon tasks (2.9-3.0x on Cube) and improves task success by up to 33.3 percentage points. These results demonstrate that amortized planning can substantially improve both inference efficiency and control performance without retraining the world models. Code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.10806 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-10T18:37:37.504Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).