Related papers: MHSNet:An MoE-based Hierarchical Semantic Represen…

While federated learning (FL) enables fine-tuning of large language models (LLMs) without compromising data privacy, the substantial size of an LLM renders on-device training impractical for resource-constrained clients, such as mobile…

It is known that unsupervised nonlinear dimensionality reduction and clustering is sensitive to the selection of hyperparameters, particularly for deep learning based methods, which hinders its practical use. How to select a proper network…

Dense Retrieval Models (DRMs) are a prominent development in Information Retrieval (IR). A key challenge with these neural Transformer-based models is that they often struggle to generalize beyond the specific tasks and domains they were…

We present HetNet (Multi-level \textbf{Het}erogeneous \textbf{Net}work), a highly efficient mirror detection network. Current mirror detection methods focus more on performance than efficiency, limiting the real-time applications (such as…

Video-text retrieval is an important yet challenging task in vision-language understanding, which aims to learn a joint embedding space where related video and text instances are close to each other. Most current works simply measure the…

Joint understanding of video and language is an active research area with many applications. Prior work in this domain typically relies on learning text-video embeddings. One difficulty with this approach, however, is the lack of…

Mixture of Experts (MoE) models enable parameter-efficient scaling through sparse expert activations, yet optimizing their inference and memory costs remains challenging due to limited understanding of their specialization behavior. We…

Many approaches can derive information about a single speaker's identity from the speech by learning to recognize consistent characteristics of acoustic parameters. However, it is challenging to determine identity information when there are…

The rapid development of the Internet has led to introducing new methods for e-recruitment and human resources management. These methods aim to systematically address the limitations of conventional recruitment procedures through…

With the rapid development and widespread application of Large Language Models (LLMs), the use of Machine-Generated Text (MGT) has become increasingly common, bringing with it potential risks, especially in terms of quality and integrity in…

Multimodal embedding models have gained significant attention for their ability to map data from different modalities, such as text and images, into a unified representation space. However, the limited labeled multimodal data often hinders…

Detecting AI-involved text is essential for combating misinformation, plagiarism, and academic misconduct. However, AI text generation includes diverse collaborative processes (AI-written text edited by humans, human-written text edited by…

In this paper, we introduce the MLM (Multiple Languages and Modalities) dataset - a new resource to train and evaluate multitask systems on samples in multiple modalities and three languages. The generation process and inclusion of semantic…

Multimodal learning robust to missing modality has attracted increasing attention due to its practicality. Existing methods tend to address it by learning a common subspace representation for different modality combinations. However, we…

Person re-identification (re-ID) tackles the problem of matching person images with the same identity from different cameras. In practical applications, due to the differences in camera performance and distance between cameras and persons…

Talent search and recommendation systems at LinkedIn strive to match the potential candidates to the hiring needs of a recruiter or a hiring manager expressed in terms of a search query or a job posting. Recent work in this domain has…

Multimodal information extraction (IE) tasks have attracted increasing attention because many studies have shown that multimodal information benefits text information extraction. However, existing multimodal IE datasets mainly focus on…

While deeply supervised networks are common in recent literature, they typically impose the same learning objective on all transitional layers despite their varying representation powers. In this paper, we propose Hierarchically Supervised…

Understanding and leveraging the 3D structures of proteins is central to a variety of biological and drug discovery tasks. While deep learning has been applied successfully for structure-based protein function prediction tasks, current…

Mixture-of-Experts (MoE) presents a naturally compatible and scalable framework for multimodal learning, demonstrating strong adaptability across diverse modalities and tasks. Despite its growing success, a comprehensive and systematic…