Metraipolis › archive › dc_b23d3f7e366e
ENCP: Episode-Normalized Conformal Prediction for Vision-and-Language Navigation — arXiv:2609.17499
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.17499
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T18:39:00.193Z
- SHA-256 of the archived text
541561458ab0ddafef2748a6de18e86a65210eb3cafe7f6dbc509fbe6f8cd5c4- Stable URL of this page
https://metraipolis.com/documento/dc_b23d3f7e366e
How to cite
ENCP: Episode-Normalized Conformal Prediction for Vision-and-Language Navigation — arXiv:2609.17499 — arXiv (en), https://arxiv.org/abs/2609.17499 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b23d3f7e366e (Metraipolis archive dc_b23d3f7e366e, sha256 541561458ab0ddafef2748a6de18e86a65210eb3cafe7f6dbc509fbe6f8cd5c4)
BibTeX
@misc{dcb23d3f7e366e,
title = {ENCP: Episode-Normalized Conformal Prediction for Vision-and-Language Navigation — arXiv:2609.17499},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.17499},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b23d3f7e366e; sha256 541561458ab0ddafef2748a6de18e86a65210eb3cafe7f6dbc509fbe6f8cd5c4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.17499. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Uncertainty estimation for Vision-Language-Navigation (VLN) models is a critical task since it can help identify ambiguous and unreliable predictions, enabling agents to make safer navigation decisions. As one of the most advanced uncertainty estimation frameworks, conformal prediction (CP) offers a promising approach for uncertainty estimation in VLN. However, given that VLN agent requires a sequence of steps, standard calibration in conformal prediction fails to provide coverage guarantee it promises over a dependent, variable-length VLN episode. To this end, we propose Episode-Normalized Conformal Prediction (ENCP), which rescales a nonconformity score by the policy's residual confidence and calibrates one maximum score per episode. Under exchangeable calibration and test episodes, this construction covers the ground truth at every step with probability at least $1 - \alpha$, while allowing dependence among steps within an episode. Across four VLN policies and three nonconformity scores on R2R and REVERIE dataset, ENCP meets all reported empirical step-coverage targets on the seen-to-unseen evaluation. These results demonstrate that ENCP can provide model-agnostic uncertainty estimates, which might be useful for determining when a VLN agent should defer to a more capable predictor, including human assistance. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-16 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.17499 — 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 2026-10-15T18:03:09.764Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).