Related papers: Uncovering and Mitigating Transient Blindness in M…

Text-guided audio editing aims to modify specific acoustic events while strictly preserving non-target content. Despite recent progress, existing approaches remain fundamentally limited. Training-free methods often suffer from signal…

Visible-infrared person re-identification (VI-ReID) aims to search the same pedestrian of interest across visible and infrared modalities. Existing models mainly focus on compensating for modality-specific information to reduce modality…

Recent advances in multimodal large language models (MLLMs) have significantly improved medical AI, enabling it to unify the understanding of visual and textual information. However, as medical knowledge continues to evolve, it is critical…

Recent advances in multimodal vision and language modeling have predominantly focused on the English language, mostly due to the lack of multilingual multimodal datasets to steer modeling efforts. In this work, we address this gap and…

Medical artificial intelligence (AI) systems, particularly multimodal vision-language models (VLM), often exhibit intersectional biases where models are systematically less confident in diagnosing marginalised patient subgroups. Such bias…

As a crucial extension of entity alignment (EA), multi-modal entity alignment (MMEA) aims to identify identical entities across disparate knowledge graphs (KGs) by exploiting associated visual information. However, existing MMEA approaches…

While Multimodal Large Language Models (MLLMs) excel in general vision-language tasks, their application to remote sensing change understanding is hindered by a fundamental "temporal blindness". Existing architectures lack intrinsic…

The swift advancement in Multimodal LLMs (MLLMs) also presents significant challenges for effective knowledge editing. Current methods, including intrinsic knowledge editing and external knowledge resorting, each possess strengths and…

Generalizable person re-identification (Re-ID) is a very hot research topic in machine learning and computer vision, which plays a significant role in realistic scenarios due to its various applications in public security and video…

Large Vision-Language Models (LVLMs) have recently achieved impressive results in multimodal tasks such as image captioning and visual question answering. However, they remain prone to object hallucination -- generating descriptions of…

Unified Multimodal Models (UMMs) integrate multimodal understanding and generation, yet they are limited to maintaining visual consistency and disambiguating visual cues when referencing details across multiple input images. In this work,…

Multimodal embedding models, built upon causal Vision Language Models (VLMs), have shown promise in various tasks. However, current approaches face three key limitations: the use of causal attention in VLM backbones is suboptimal for…

Despite significant progress in Unified Multimodal Retrieval (UMR) powered by Large Multimodal Models (LMMs), existing embedding methods primarily focus on sample-level objectives via contrastive learning while overlooking the crucial…

Visual question answering (VQA) systems face significant challenges when adapting to real-world data shifts, especially in multi-modal contexts. While robust fine-tuning strategies are essential for maintaining performance across…

Knowledge editing enables multimodal large language models (MLLMs) to efficiently update outdated or incorrect information. However, existing benchmarks primarily emphasize cognitive-level modifications while lacking a focus on deeper…

Image Quality Assessment (IQA) models benefit significantly from semantic information, which allows them to treat different types of objects distinctly. Currently, leveraging semantic information to enhance IQA is a crucial research…

While Knowledge Editing has been extensively studied in monolingual settings, it remains underexplored in multilingual contexts. This survey systematizes recent research on Multilingual Knowledge Editing (MKE), a growing subdomain of model…

Multimodal/vision language models (VLMs) are increasingly being deployed in healthcare settings worldwide, necessitating robust benchmarks to ensure their safety, efficacy, and fairness. Multiple-choice question and answer (QA) datasets…

Recent advances in Multimodal Large Language Models (MLLMs) have shown impressive reasoning capabilities across vision-language tasks, yet still face the challenge of compute-difficulty mismatch. Through empirical analyses, we identify that…

This paper presents an in-depth study of multimodal machine translation (MMT), examining the prevailing understanding that MMT systems exhibit decreased sensitivity to visual information when text inputs are complete. Instead, we attribute…