arXiv：cs.AI· Wenteng Chen, Jiachen Zhu, Rong Shan, Tianyi Xu, Yuxiang Chen, Congmin Zheng, Teng Wang, Junjie Wu, Weiwen Liu, Changwang Zhang, Weinan Zhang, Jun Wang, Jianghao Lin·· 5 小时前AI 评分40
AMBER：面向列表式视觉语言重排序的多视图自适应预算分配
AMBER: Multi-View Adaptive Budget Allocation for Listwise Vision-Language Reranking
AI 导读
针对视觉语言模型（VLM）多视图重排序中固定调度浪费昂贵调用的问题，研究者提出 AMBER——一种在线、带预算的多视图重排序框架，通过连续 Elo 更新维护轻量全局排序状态，并在候选视图构建与查询调度两个层面动态分配算力。在 CIRR、CIRCO 和 PhotoBench 上，AMBER 在可比 VLM 调用预算下取得所比较方法中最强整体性能，且在更低预算下仍有效。代码已公开。
正文
Authors:Wenteng Chen, Jiachen Zhu, Rong Shan, Tianyi Xu, Yuxiang Chen, Congmin Zheng, Teng Wang, Junjie Wu, Weiwen Liu, Changwang Zhang, Weinan Zhang, Jun Wang, Jianghao Lin
Abstract: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.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.02831 [cs.AI] |
| (or arXiv:2610.02831v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.02831 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Wenteng Chen [view email]
[v1]
Fri, 2 Oct 2026 05:23:50 UTC (322 KB)
来源：arXiv：cs.AI · arxiv.org