SLQ：通过共享潜在查询桥接模态以实现冻结MLLMs的检索
SLQ: Bridging Modalities via Shared Latent Queries for Retrieval with Frozen MLLMs
AI总结：
SLQ通过冻结MLLMs的主干，引入共享潜在查询提升多模态检索性能，实验显示其在多个基准上表现优异。
摘要：
多模态大语言模型（MLLMs）具备内在推理和世界知识能力，但将其应用于密集检索仍具挑战性。现有方法依赖侵入性参数更新，如全微调和LoRA，可能破坏预训练语义空间并损害推理所需的结构化知识。为此，我们提出SLQ，一种参数高效调优框架，通过冻结主干来适应MLLMs进行检索。SLQ引入少量共享潜在查询，附加于文本和图像令牌，利用模型原生因果注意力将多模态上下文聚合到统一嵌入空间。此外，为更评估检索超越表层模式匹配，我们构建了KARR-Bench基准，专为知识感知推理检索设计。大量实验表明，SLQ在COCO和Flickr30K上优于全微调和LoRA，在MMEB上表现竞争，在KARR-Bench上取得显著提升，验证了通过非侵入性适应保留预训练表示在MLLMs基于检索中的有效性。代码可在https://github.com/CnFaker/SLQ获取。
英文摘要：
Multimodal Large Language Models (MLLMs) possess intrinsic reasoning and world-knowledge capabilities, yet adapting them for dense retrieval remains challenging. Existing approaches rely on invasive parameter updates, such as full fine-tuning and LoRA, which may disrupt the pre-trained semantic space and impair the structured knowledge essential for reasoning. To address this, we propose SLQ, a parameter-efficient tuning framework that adapts MLLMs for retrieval while keeping the backbone entirely frozen. SLQ introduces a small set of Shared Latent Queries that are appended to both text and image tokens, leveraging the model's native causal attention to aggregate multimodal context into a unified embedding space. Furthermore, to better evaluate retrieval beyond superficial pattern matching, we construct KARR-Bench, a benchmark designed for knowledge-aware reasoning retrieval. Extensive experiments show that SLQ outperforms full fine-tuning and LoRA on COCO and Flickr30K, while achieving competitive performance on MMEB and yielding substantial gains on KARR-Bench, validating that preserving the pre-trained representations via non-invasive adaptation is an effective strategy for MLLM-based retrieval. The code is available under: https://github.com/CnFaker/SLQ.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
