Metraipolis › archive › dc_f53095d75ea9

Measure Less, Know More: Self-Supervised Test-Time Feature Acquisition — arXiv:2610.03454

Source
arXiv
Original
https://arxiv.org/abs/2610.03454
License (as archived)
CC0-1.0
Archived
2026-10-05T22:50:40.833Z
SHA-256 of the archived text
a22eedb129536d85ad8a8db12e3956c4afc58e6ccdf4be4300420a4f9db4323a
Stable URL of this page
https://metraipolis.com/documento/dc_f53095d75ea9

How to cite

Measure Less, Know More: Self-Supervised Test-Time Feature Acquisition — arXiv:2610.03454 — arXiv, https://arxiv.org/abs/2610.03454 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f53095d75ea9 (Metraipolis archive dc_f53095d75ea9, sha256 a22eedb129536d85ad8a8db12e3956c4afc58e6ccdf4be4300420a4f9db4323a)
BibTeX
@misc{dcf53095d75ea9,
  title = {Measure Less, Know More: Self-Supervised Test-Time Feature Acquisition — arXiv:2610.03454},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.03454},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f53095d75ea9; sha256 a22eedb129536d85ad8a8db12e3956c4afc58e6ccdf4be4300420a4f9db4323a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.03454. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent progress in multimodal, high-dimensional learning has enabled foundation models to process heterogeneous, large-scale data. However, at test time, acquiring all features or modalities can be prohibitively costly and often redundant. Sequentially selecting informative modalities is therefore critical, yet challenging when the downstream task or prediction target is unknown. To this end, we introduce ECHO-$k$, a task-agnostic and self-supervised learning principle for modality acquisition: we use a deep model's internal pretrained representations (e.g., from a foundation model) as proxy targets that summarize cross-modal information. We provide theoretical guarantees in a stylized linear setting that motivate a reinforcement learning (RL) policy for sequential modality selection. Across task-agnostic and label-free acquisition baselines, ECHO-$k$ consistently improves budgeted downstream performance across diverse foundation-model backends. Our method provides a principled route to cost-aware test-time deployment, with implications for any multimodal system where measurements are expensive or time-constrained, and downstream tasks unknown a priori.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.03454 — 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 2026-10-05T22:45:55.864Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).