Advances in vision-language models (VLMs) have enabled effective cross-modality retrieval. However, when both text and images exist in the database, similarity scores would differ in scale by modality. This phenomenon, known as the modality gap, hinders accurate retrieval. Most existing studies address this issue with manually labeled data, e.g., by fine-tuning VLMs on them. In this work, we propose a similarity standardization approach with pseudo data construction. We first compute the mean and variance of the similarity scores between each query and its paired data in text or image modality. Using these modality-specific statistics, we standardize all similarity scores to compare on a common scale across modalities. These statistics are calculated from pseudo pairs, which are constructed by retrieving the text and image candidates with the highest cosine similarity to each query. We evaluate our method across seven VLMs using two multi-modal QA benchmarks (MMQA and WebQA), where each question requires retrieving either text or image data. Our experimental results show that our method significantly improves retrieval performance, achieving average Recall@20 gains of 64% on MMQA and 28% on WebQA when the query and the target data belong to different modalities. Compared to E5-V, which addresses the modality gap through image captioning, we confirm that our method more effectively bridges the modality gap.

Infodemics and health misinformation have significant negative impact on individuals and society, exacerbating confusion and increasing hesitancy in adopting recommended health measures. Recent advancements in generative AI, capable of producing realistic, human like text and images, have significantly accelerated the spread and expanded the reach of health misinformation, resulting in an alarming surge in its dissemination. To combat the infodemics, most existing work has focused on developing misinformation datasets from social media and fact checking platforms, but has faced limitations in topical coverage, inclusion of AI generation, and accessibility of raw content. To address these issues, we present MM Health, a large scale multimodal misinformation dataset in the health domain consisting of 34,746 news article encompassing both textual and visual information. MM Health includes human-generated multimodal information (5,776 articles) and AI generated multimodal information (28,880 articles) from various SOTA generative AI models. Additionally, We benchmarked our dataset against three tasks (reliability checks, originality checks, and fine-grained AI detection) demonstrating that existing SOTA models struggle to accurately distinguish the reliability and origin of information. Our dataset aims to support the development of misinformation detection across various health scenarios, facilitating the detection of human and machine generated content at multimodal levels.

W.J.T. Mitchell's influential essay 'What do pictures want?' shifts the theoretical focus away from the interpretative act of understanding pictures and from the motivations of the humans who create them to the possibility that the picture itself is an entity with agency and wants. In this article, I reframe Mitchell's question in light of contemporary AI image generation tools to ask: what do AI-generated images want? Drawing from art historical discourse on the nature of abstraction, I argue that AI-generated images want specificity and concreteness because they are fundamentally abstract. Multimodal text-to-image models, which are the primary subject of this article, are based on the premise that text and image are interchangeable or exchangeable tokens and that there is a commensurability between them, at least as represented mathematically in data. The user pipeline that sees textual input become visual output, however, obscures this representational regress and makes it seem like one form transforms into the other -- as if by magic.

Retrieval-Augmented Generation (RAG) has emerged as a promising technique to enhance the quality and relevance of responses generated by large language models. While recent advancements have mainly focused on improving RAG for text-based queries, RAG on multi-modal documents containing both texts and images has not been fully explored. Especially when fine-tuning does not work. This paper proposes BRIT, a novel multi-modal RAG framework that effectively unifies various text-image connections in the document into a multi-modal graph and retrieves the texts and images as a query-specific sub-graph. By traversing both image-to-text and text-to-image paths in the graph, BRIT retrieve not only directly query-relevant images and texts but also further relevant contents to answering complex cross-modal multi-hop questions. To evaluate the effectiveness of BRIT, we introduce MM-RAG test set specifically designed for multi-modal question answering tasks that require to understand the text-image relations. Our comprehensive experiments demonstrate the superiority of BRIT, highlighting its ability to handle cross-modal questions on the multi-modal documents.

The widespread presence of incomplete modalities in multimodal data poses a significant challenge to achieving accurate rumor detection. Existing multimodal rumor detection methods primarily focus on learning joint modality representations from \emph{complete} multimodal training data, rendering them ineffective in addressing the common occurrence of \emph{missing modalities} in real-world scenarios. In this paper, we propose a hierarchical soft prompt model \textsf{TriSPrompt}, which integrates three types of prompts, \textit{i.e.}, \emph{modality-aware} (MA) prompt, \emph{modality-missing} (MM) prompt, and \emph{mutual-views} (MV) prompt, to effectively detect rumors in incomplete multimodal data. The MA prompt captures both heterogeneous information from specific modalities and homogeneous features from available data, aiding in modality recovery. The MM prompt models missing states in incomplete data, enhancing the model's adaptability to missing information. The MV prompt learns relationships between subjective (\textit{i.e.}, text and image) and objective (\textit{i.e.}, comments) perspectives, effectively detecting rumors. Extensive experiments on three real-world benchmarks demonstrate that \textsf{TriSPrompt} achieves an accuracy gain of over 13\% compared to state-of-the-art methods. The codes and datasets are available at https: //anonymous.4open.science/r/code-3E88.

Multimodal aspect-based sentiment analysis(MABSA) seeks to identify aspect terms within paired image-text data and determine their fine grained sentiment polarities, representing a fundamental task for improving the effectiveness of applications such as product review systems and public opinion monitoring. Existing methods face challenges such as cross modal alignment noise and insufficient consistency in fine-grained representations. While global modality alignment methods often overlook the connection between aspect terms and their corresponding local visual regions, bridging the representation gap between text and images remains a challenge. To address these limitations, this paper introduces an end to end Contrastive Learning framework with Adaptive Multi-loss and Progressive Attention Fusion(CLAMP). The framework is composed of three novel modules: Progressive Attention Fusion network, Multi-task Contrastive Learning, and Adaptive Multi-loss Aggregation. The Progressive Attention Fusion network enhances fine-grained alignment between textual features and image regions via hierarchical, multi-stage cross modal interactions, effectively suppressing irrelevant visual noise. Secondly, multi-task contrastive learning combines global modal contrast and local granularity alignment to enhance cross modal representation consistency. Adaptive Multi-loss Aggregation employs a dynamic uncertainty based weighting mechanism to calibrate loss contributions according to each task's uncertainty, thereby mitigating gradient interference. Evaluation on standard public benchmarks demonstrates that CLAMP consistently outperforms the vast majority of existing state of the art methods.

Document understanding remains a significant challenge for multimodal large language models (MLLMs). While previous research has primarily focused on locating evidence pages through precise multimodal queries, our work investigates a fundamental yet overlooked aspect: how input format influences document comprehension performance. Through systematic analysis, we discover that raw OCR text often impairs rather than improves MLLMs' performance, which is a counterintuitive finding we attribute to attention dispersion and structure loss. To further substantiate our hypothesis, we propose a novel structure-preserving approach that encodes document elements using the LaTex paradigm, maintaining the hierarchical organization and spatial relationships critical for comprehension. Our attention analysis reveals that structured text induces structured attention patterns on both textual and visual content, directing models to focus on semantically meaningful regions while reducing attention waste. This approach significantly enhances MLLMs' document question answering performance across diverse document types without requiring architectural modifications or additional training.

Due to the presence of political echo chambers, it becomes imperative to detect and remove subjective bias and emotionally charged language from both the text and images of political articles. However, prior work has focused on solely the text portion of the bias rather than both the text and image portions. This is a problem because the images are just as powerful of a medium to communicate information as text is. To that end, we present a model that leverages both text and image bias which consists of four different steps. Image Text Alignment focuses on semantically aligning images based on their bias through CLIP models. Image Bias Scoring determines the appropriate bias score of images via a ViT classifier. Text De-Biasing focuses on detecting biased words and phrases and neutralizing them through BERT models. These three steps all culminate to the final step of debiasing, which replaces the text and the image with neutralized or reduced counterparts, which for images is done by comparing the bias scores. The results so far indicate that this approach is promising, with the text debiasing strategy being able to identify many potential biased words and phrases, and the ViT model showcasing effective training. The semantic alignment model also is efficient. However, more time, particularly in training, and resources are needed to obtain better results. A human evaluation portion was also proposed to ensure semantic consistency of the newly generated text and images.

Vision-language models (VLMs) allow to embed texts and images in a shared representation space. However, it has been shown that these models are subject to a modality gap phenomenon meaning there exists a clear separation between the embeddings from one modality and another in the embedding space. While this misalignment is detrimental for downstream tasks such as multimodal retrieval, multimodal clustering or zero-shot classification, etc. no generic and practical methods have so far been proposed to assess it precisely and even reduce it. We therefore propose novel measures and effective techniques (spectral- and optimal transport-based methods) to achieve this goal. Extensive experiments conducted on several image-text datasets and models demonstrate their effectiveness and beneficial effects on downstream tasks. Our code is available at the URL provided in the paper's abstract.