Metraipolis › archive › dc_6b3de5ea95f6

AMBER: Multi-View Adaptive Budget Allocation for Listwise Vision-Language Reranking — arXiv:2610.02831

Source
arXiv
Original
https://arxiv.org/abs/2610.02831
License (as archived)
CC0-1.0
Archived
2026-10-05T22:49:17.845Z
SHA-256 of the archived text
ebbb771a988c6d9803505519f22c70502ee2e281eeb412af5402ae5aa01241a8
Stable URL of this page
https://metraipolis.com/documento/dc_6b3de5ea95f6

How to cite

AMBER: Multi-View Adaptive Budget Allocation for Listwise Vision-Language Reranking — arXiv:2610.02831 — arXiv, https://arxiv.org/abs/2610.02831 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6b3de5ea95f6 (Metraipolis archive dc_6b3de5ea95f6, sha256 ebbb771a988c6d9803505519f22c70502ee2e281eeb412af5402ae5aa01241a8)
BibTeX
@misc{dc6b3de5ea95f6,
  title = {AMBER: Multi-View Adaptive Budget Allocation for Listwise Vision-Language Reranking — arXiv:2610.02831},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.02831},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6b3de5ea95f6; sha256 ebbb771a988c6d9803505519f22c70502ee2e281eeb412af5402ae5aa01241a8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.02831. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-language models (VLMs) are powerful listwise rerankers for multimodal retrieval, but high inference costs restrict them to evaluating small local candidate views. Existing multi-call strategies rely on fixed schedules, wasting expensive VLM calls on uninformative candidate pairs and easy queries. To address this, we propose Adaptive Multi-view Budgeted Elo Reranking (AMBER), an online, budgeted multi-view reranking framework that dynamically optimizes global resource allocation. AMBER treats fragmented listwise VLM outputs as local tournaments, using continuous Elo updates to maintain a lightweight global ranking state. Building on this, it allocates computation at two levels: dynamically constructing candidate views with high score ambiguity, and scheduling queries to maximize expected information gain. We show that each Elo update corresponds to a stochastic gradient ascent step on the Bradley-Terry log-likelihood, and provide a submodular information-theoretic motivation for the query-level allocation strategy. Experiments on CIRR, CIRCO, and PhotoBench demonstrate that AMBER achieves the strongest overall performance among the compared multi-call VLM reranking methods under comparable VLM-call budgets, while remaining effective in lower-budget settings. Our code is publicly 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/2610.02831 — 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 2026-10-05T22:45:55.641Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).