Metraipolis › archive › dc_c728ecc48154
SPACE: Sparse Predictive Attractor via Counterfactual Eviction for Streaming Video Memory — arXiv:2609.32592
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.32592
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T23:51:00.524Z
- SHA-256 of the archived text
cf6701937018217593cb0b725eae4b7f7fe553835b46984e71e8e13dfad83b51- Stable URL of this page
https://metraipolis.com/documento/dc_c728ecc48154
How to cite
SPACE: Sparse Predictive Attractor via Counterfactual Eviction for Streaming Video Memory — arXiv:2609.32592 — arXiv (en), https://arxiv.org/abs/2609.32592 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c728ecc48154 (Metraipolis archive dc_c728ecc48154, sha256 cf6701937018217593cb0b725eae4b7f7fe553835b46984e71e8e13dfad83b51)
BibTeX
@misc{dcc728ecc48154,
title = {SPACE: Sparse Predictive Attractor via Counterfactual Eviction for Streaming Video Memory — arXiv:2609.32592},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.32592},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c728ecc48154; sha256 cf6701937018217593cb0b725eae4b7f7fe553835b46984e71e8e13dfad83b51},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32592. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Fixed-capacity streaming video memory requires repeated eviction decisions whose effects accumulate over time. Yet existing policies are evaluated primarily in terms of retained information or downstream accuracy, leaving how repeated updates alter the futures supported by memory largely unexamined. We define a memory's predictive state as the future representations supported by its retained history and formulate eviction as counterfactual control over transitions in this space. We introduce SPACE (Sparse Predictive Attractor via Counterfactual Eviction), which uses a frozen multi-horizon JEPA to predict the future representations induced by alternative eviction actions. Counterfactual utility identifies future-useful alternatives, while slow predictive-basin geometry determines when to correct avoidable drift and when to adapt to sustained predictive change, without online parameter updates. We further introduce MABS-Bench, which evaluates future-task sufficiency, within-regime predictive stability, transition responsiveness, and perturbation recovery under matched causal streams and memory budgets. Across multiple video datasets, SPACE yields consistent improvements in dataset-native task performance while reducing predictive-state drift. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.32592 — 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 2026-10-07T23:29:27.074Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).