MiniReranker: Efficient Multimodal Reranking Through Visual Cache Reuse and Interaction Sparsity
MCML Authors
Abstract
Abstract
Multimodal large language models (MLLMs) have recently shown strong potential as point-wise rerankers by directly modeling query–document relevance through next-token prediction. However, point-wise reranking suffers from substantial repeated computation across query–document pairs, while the causal structure of transformers allows only prefix segments to be reused via pre-caching. To address the misalignment of existing query-first and document-first formats with both VQA-style prompting and computation-aware reuse, we propose a vision-first formulation that improves both cache reuse efficiency and reranking performance. However, the remaining cost is still considerable and stems from three main sources: (1) *model depth*, for which we reduce active parameters via early exit; (2) *cross-segment attention*, which we restrict to a narrow interaction band across a few layers; and (3) *visual tokens*, where we reduce the number of tokens via embedder-guided pruning. Together, these designs form *miniReranker*, which reduces reranking runtime to <1% of the dense implementation under high-reuse settings for a single query, while preserving >96% of the dense model performance.
inproceedings FLZ+26
Findings @EMNLP 2026
Findings of the Conference on Empirical Methods in Natural Language Processing. Budapest, Hungary, Oct 24-29, 2026.Authors
Y. Fan • X. Lu • A. Zhao • J. Tong • P. Nie • K. Zou • Y. Ma • W. Zhang • X. ShenLinks
DOIResearch Area
BibTeXKey: FLZ+26