# AMBER: Multi-View Adaptive Budget Allocation for Listwise Vision-Language Reranking

arXiv: https://arxiv.org/abs/2610.02831 · HTML: https://mlsanity.com/paper/2610.02831/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Document understanding and multimodal RAG, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 15 of its 31 references that are in the map.
- First posted on arXiv 2 Oct 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Document understanding and multimodal RAG](https://mlsanity.com/mllm/document-understanding-and-multimodal-rag/)

## Builds on (most cited first, 15 of 15)

- [Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models](https://mlsanity.com/paper/2108.04024/) (2021)
- [Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking](https://mlsanity.com/paper/2601.04720/) (2026)
- [Zero-Shot Composed Image Retrieval with Textual Inversion](https://mlsanity.com/paper/2303.15247/) (2023)
- [MM-Embed: Universal Multimodal Retrieval with Multimodal LLMs](https://mlsanity.com/paper/2411.02571/) (2024)
- [RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!](https://mlsanity.com/paper/2312.02724/) (2023)
- [Generative Cross-Modal Retrieval: Memorizing Images in Multimodal Language Models for Retrieval and Beyond](https://mlsanity.com/paper/2402.10805/) (2024)
- [Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying](https://mlsanity.com/paper/2506.02020/) (2025)
- [Chain-of-Thought Re-ranking for Image Retrieval Tasks](https://mlsanity.com/paper/2509.14746/) (2025)
- [When Vision Meets Texts in Listwise Reranking](https://mlsanity.com/paper/2601.20623/) (2026)
- [RETLLM: Training and Data-Free MLLMs for Multimodal Information Retrieval](https://mlsanity.com/paper/2602.22278/) (2026)
- [LLM-based Listwise Reranking under the Effect of Positional Bias](https://mlsanity.com/paper/2604.03642/) (2026)
- [ReCQR: Incorporating conversational query rewriting to improve Multimodal Image Retrieval](https://mlsanity.com/paper/2603.26669/) (2026)
- [Very Efficient Listwise Multimodal Reranking for Long Documents](https://mlsanity.com/paper/2605.11864/) (2026)
- [Fine-Grained Zero-Shot Composed Image Retrieval with Complementary Visual-Semantic Integration](https://mlsanity.com/paper/2601.14060/) (2026)
- [Weaving Visual Narratives: Agentic Image Bundle Composition Beyond Atomic Visual Matching](https://mlsanity.com/paper/2608.28695/) (2026)

## Abstract (arXiv)

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 https://github.com/wnlfc/AMBER.