The paper introduces CERES, a closed‑loop multimodal indexing framework that addresses semantic collapse in multimodal generation by building a three‑level semantic pyramid and using scale‑routed cross‑attention to generate images that remain retrievable by their original queries. CERES employs a co‑occurrence‑aware router, a lightweight U‑Net generator, and a soft‑Jaccard coverage objective to ensure generated images cover the intended concepts, verified by re‑indexing with a frozen vision‑language model and an external DINOv2 probe. Experiments on four pansharpening benchmarks show state‑of‑the‑art performance, especially under extreme scale variation, and significant improvements in concept‑query retrieval and image‑text ranking metrics.
By Guangyuan Dong, Chuang Liu, Haoyu Wang, Yangchen Zeng, Jiaqi Zhang, Li Jiuxing, Xiaoyang Yu, Pinlong Zhao, Yuchao Hou, Ziwei Li, Zheng Lin, Alexander Lim Han Yang, Yusen Wu
arXiv:2606. 20280v1 Announce Type: cross Abstract: Leveraging Multimodal Large Language Models (MLLMs) via contrastive learning has become a mainstream paradigm for improving the performance of Universal Multimodal Retrieval (UMR).
By Yuhan Liu, Pei Fu, Hang Li, Yukun Qi, Chao Jiang, Jingwen Fu, Zhen Liu, Bin Qin, Zhenbo Luo, Jian Luan, Jingmin Xin
arXiv:2608. 20810v1 Announce Type: cross Abstract: Multimodal information systems increasingly route generated visual content back through the same vision-language index that informed its production, so the output must remain retrievable by the queries it was meant to serve.
By Guangyuan Dong, Chuang Liu, Yangchen Zeng, Haoyu Wang, Xiaoyang Yu, Pinlong Zhao, Yuchao Hou, Ziwei Li, Zheng Lin
Vis-Poison is a novel attack that poisons multimodal retrieval-augmented generation systems by inserting attacker-controlled images as visual evidence, without altering any textual metadata. The attack uses an automated multi-agent approach to create visually plausible poisoned images and has been tested on two multimodal RAG pipelines, four embedding models, and six generation models. In black-box settings, Vis-Poison achieves an end-to-end success rate between 40.16% and 65.40% against 30,000-entry knowledge bases, and remains effective against various multimodal large language models with an average success rate above 60%.
By Rujin Liang, Zhongpu Chen, Yuhao Lei, Xin Miao
arXiv:2609.05518v1 Announce Type: cross
Abstract: Despite the strong capabilities of multimodal large language models (MLLMs), their parametric knowledge remains incomplete and difficult to update, m...
By Jiacheng Cai, Zijin Hong, Zheng Yuan, Huachi Zhou, Qinggang Zhang, Xiao Huang
The paper investigates how multimodal large language models (MLLMs) handle conflicting evidence presented in text, image, or both forms. Across 13 MLLMs and two datasets, the authors find that models are not robust to knowledge conflict: they tend to accept contradictory image evidence more readily than contradictory text, and when both modalities conflict the preference is arbitrary, depending on input order, model, and dataset. The instability degrades multimodal retrieval-augmented generation and can be exploited by adversarial attacks, while simple mitigation techniques such as prompting, steering, and direct preference optimization largely fail, with supervised fine‑tuning offering only moderate improvement.
By Jungyeon Lee, Yejin Yoon, Taeuk Kim
The paper investigates how Vision Language Models (VLMs) can be fooled by tiny, human‑imperceptible changes to images. It introduces a gradient‑based attack that targets only the vision encoder, reducing computational cost while still effectively disrupting both untargeted and targeted multimodal interpretations. Experiments on open‑source VLMs such as Qwen2.5‑VL, Granite‑Vision, FastVLM, and Phi‑3.5‑Vision demonstrate that these small perturbations can dramatically alter the models’ textual outputs.
The paper introduces SRAIN, a framework that learns sample‑wise, rank‑aware interpolation weights for composed visual data retrieval. Instead of relying on complex multimodal large language models, SRAIN uses simple linear interpolation in embedding space, dynamically predicting query‑specific weights through batch‑wise rank‑aware estimation and a compact memory bank for hard negatives. This approach achieves state‑of‑the‑art performance on composed video retrieval and competitive results on composed image retrieval while significantly reducing query‑time latency.
By Boseung Jeong, Taegyu Park, Donghyeon Kwon, Hyunsouk Cho, Suha Kwak
arXiv:2608. 11343v1 Announce Type: new Abstract: Multimodal retrieval and classification across different types of media, spanning text, images,video and audio, has traditionally relied on dual-encoder models that align visual and textual representations through contrastive learning.
By Archan Dutta, Vyanktesh Kanungo
arXiv:2506. 08774v2 Announce Type: replace-cross Abstract: Different machine learning models can represent the same underlying concept in different ways.
By Fan Xu, Luis A. Leiva
arXiv:2605. 18160v2 Announce Type: replace-cross Abstract: In recent years, multimodal large language models (MLLMs) have achieved remarkable progress, primarily attributed to effective paradigms for integrating visual and textual information.
By Xinpeng Dong, Min Zhang, Kairong Han, Xu Tan, Fei Wu, Kun Kuang
arXiv:2606. 02578v1 Announce Type: cross Abstract: Recent multimodal large language models have demonstrated strong reasoning ability, yet their reliability as automated evaluators remains limited by a critical weakness: when visual evidence conflicts with textual cues, MLLM judges tend to reward plausible narratives over perceptually correct answers.
By Seojeong Park, Jiho Choi, Junyong Kang, Seonho Lee, Jaeyo Shin, Hyunjung Shim