Related papers: MOON2.0: Dynamic Modality-balanced Multimodal Repr…

Multimodal models excel in English, supported by abundant image-text and audio-text data, but performance drops sharply for other languages due to limited multilingual multimodal resources. Existing solutions rely on machine translation,…

The popularity of multimodal large language models (MLLMs) has triggered a recent surge in research efforts dedicated to evaluating these models. Nevertheless, existing evaluation studies of MLLMs primarily focus on the comprehension and…

Multimodal video understanding plays a crucial role in tasks such as action recognition and emotion classification by combining information from different modalities. However, multimodal models are prone to overfitting strong modalities,…

Leveraging multimodal data to drive breakthroughs in e-commerce applications through Multimodal Foundation Models (MFMs) is gaining increasing attention from the research community. However, there are significant challenges that hinder the…

Edge-cloud synergies provide a promising paradigm for privacy-preserving deployment of foundation models, where lightweight on-device models adapt to domain-specific data and cloud-hosted models coordinate knowledge sharing. However, in…

Taobao Search consists of two phases: the retrieval phase and the ranking phase. Given a user query, the retrieval phase returns a subset of candidate products for the following ranking phase. Recently, the paradigm of pre-training and…

E-commerce product understanding demands by nature, strong multimodal comprehension from text, images, and structured attributes. General-purpose Vision-Language Models (VLMs) enable generalizable multimodal latent modelling, yet there is…

Multimodal Large Language Models (MLLMs) have endowed LLMs with the ability to perceive and understand multi-modal signals. However, most of the existing MLLMs mainly adopt vision encoders pretrained on coarsely aligned image-text pairs,…

Understanding human intentions (e.g., emotions) from videos has received considerable attention recently. Video streams generally constitute a blend of temporal data stemming from distinct modalities, including natural language, facial…

Advances in multimodal models have greatly improved how interactions relevant to various tasks are modeled. Today's multimodal models mainly focus on the correspondence between images and text, using this for tasks like image-text matching.…

Despite their strong performance in multimodal emotion reasoning, existing Multimodal Large Language Models (MLLMs) often overlook the scenarios involving emotion conflicts, where emotional cues from different modalities are inconsistent.…

Multimodal learning typically relies on the assumption that all modalities are fully available during both the training and inference phases. However, in real-world scenarios, consistently acquiring complete multimodal data presents…

Large language models (LLMs) have demonstrated impressive zero-shot abilities on a variety of open-ended tasks, while recent research has also explored the use of LLMs for multi-modal generation. In this study, we introduce mPLUG-Owl, a…

This survey provides a comprehensive overview of recent advances in multimodal alignment and fusion within the field of machine learning, driven by the increasing availability and diversity of data modalities such as text, images, audio,…

Multimodal information retrieval (MIR) faces inherent challenges due to the heterogeneity of data sources and the complexity of cross-modal alignment. While previous studies have identified modal gaps in feature spaces, a systematic…

Multi-modal large language models (MLLMs) have achieved remarkable performance on objective multimodal perception tasks, but their ability to interpret subjective, emotionally nuanced multimodal content remains largely unexplored. Thus, it…

Multimodal learning, which integrates data from diverse sensory modes, plays a pivotal role in artificial intelligence. However, existing multimodal learning methods often struggle with challenges where some modalities appear more dominant…

While embeddings from multimodal large language models (LLMs) excel as general-purpose representations, their application to dynamic modalities like audio and video remains underexplored. We introduce WAVE (\textbf{u}nified \&…

Despite the impressive results achieved by multimodal large language models (MLLMs), their training typically relies on jointly curated multimodal data, requiring substantial human effort to construct multi-way aligned datasets and thereby…

Multimodal sentiment analysis (MSA) integrates heterogeneous text, audio, and visual signals to infer human emotions. While recent approaches leverage cross-modal complementarity, they often struggle to fully utilize weaker modalities. In…