相关论文: Information Router for Mitigating Modality Dominan…

Different modalities hold considerable gaps in optimization trajectories, including speeds and paths, which lead to modality laziness and modality clash when jointly training multimodal models, resulting in insufficient and imbalanced…

Mixture-of-Experts (MoE) has emerged as an effective approach to reduce the computational overhead of Transformer architectures by sparsely activating a subset of parameters for each token while preserving high model capacity. This paradigm…

Multimodal Information Extraction (MIE) requires fusing text and visual cues from visually rich documents. While recent methods have advanced multimodal representation learning, most implicitly assume modality equivalence or treat…

In this paper, we propose Meeting recognizer Output Voting Error Reduction (MOVER), a novel system combination method for meeting recognition tasks. Although there are methods to combine the output of diarization (e.g., DOVER) or automatic…

Low-light image enhancement (LLIE) is a fundamental yet challenging task due to the presence of noise, loss of detail, and poor contrast in images captured under insufficient lighting conditions. Recent methods often rely solely on…

Multi-modal image fusion (MMIF) integrates valuable information from different modality images into a fused one. However, the fusion of multiple visible images with different focal regions and infrared images is a unprecedented challenge in…

Recently, the Mixture of Expert (MoE) architecture, such as LR-MoE, is often used to alleviate the impact of language confusion on the multilingual ASR (MASR) task. However, it still faces language confusion issues, especially in mismatched…

News representation and user-oriented modeling are both essential for news recommendation. Most existing methods are based on textual information but ignore the visual information and users' dynamic interests. However, compared to textual…

Existing Multimodal Large Language Models (MLLMs) are predominantly trained and tested on consistent visual-textual inputs, leaving open the question of whether they can handle inconsistencies in real-world, layout-rich content. To bridge…

Short video platforms have become important channels for news dissemination, offering a highly engaging and immediate way for users to access current events and share information. However, these platforms have also emerged as significant…

Human beings naturally utilize multiple reasoning modalities to learn and solve logical problems, i.e., different representational formats such as natural language, code, and symbolic logic. In contrast, most existing LLM-based approaches…

Multimodal recommendation focuses primarily on effectively exploiting both behavioral and multimodal information for the recommendation task. However, most existing models suffer from the following issues when fusing information from two…

Pre-trained video large language models excel at visual reasoning. However, they struggle when videos arrive with auxiliary streams, such as audio, depth map, or dense temporal evidence. In such a scenario, uniform fusion induces modality…

The aim of multimodal neural networks is to combine diverse data sources, referred to as modalities, to achieve enhanced performance compared to relying on a single modality. However, training of multimodal networks is typically hindered by…

Multimodal large language models (MLLMs) have demonstrated strong capabilities on vision-and-language tasks. However, recent findings reveal an imbalance in their reasoning capabilities across visual and textual modalities. Specifically,…

Information fusion is used widely to improve document classification by the integration of multiple data sources (multimodal) or representations (multiview). However, the field lacks a unified framework, a quantitative synthesis of its…

The challenge of Multimodal Deformable Image Registration (MDIR) lies in the conversion and alignment of features between images of different modalities. Generative models (GMs) cannot retain the necessary information enough from the source…

Vision-language pretrained models have seen remarkable success, but their application to safety-critical settings is limited by their lack of interpretability. To improve the interpretability of vision-language models such as CLIP, we…

This work focuses on learning useful and robust deep world models using multiple, possibly unreliable, sensors. We find that current methods do not sufficiently encourage a shared representation between modalities; this can cause poor…

Multimodal Large Language Models (MLLMs) extend the capacity of LLMs to understand multimodal information comprehensively, achieving remarkable performance in many vision-centric tasks. Despite that, recent studies have shown that these…