Related papers: Contrastive Learning-Enhanced Large Language Model…

Vision-language models (VLMs) like CLIP have showcased a remarkable ability to extract transferable features for downstream tasks. Nonetheless, the training process of these models is usually based on a coarse-grained contrastive loss…

Many machine learning models have been built to tackle information overload issues on Massive Open Online Courses (MOOC) platforms. These models rely on learning powerful representations of MOOC entities. However, they suffer from the…

Modular Neural Networks (MNNs) demonstrate various advantages over monolithic models. Existing MNNs are generally $\textit{explicit}$: their modular architectures are pre-defined, with individual modules expected to implement distinct…

Contrastive Language-Image Pre-training (CLIP) has become a cornerstone in vision-language representation learning, powering diverse downstream tasks and serving as the default vision backbone in multimodal large language models (MLLMs).…

Multimodal Large Language Models (MLLMs) increasingly need to forget specific knowledge such as unsafe or private information without requiring full retraining. However, existing unlearning methods often disrupt vision language alignment,…

Multimodal representation learning produces high-dimensional embeddings that align diverse modalities in a shared latent space. While this enables strong generalization, it also introduces scalability challenges, both in terms of storage…

Metamaterials, known for their ability to manipulate light at subwavelength scales, face significant design challenges due to their complex and sophisticated structures. Consequently, deep learning has emerged as a powerful tool to…

Deep learning-based methods have achieved encouraging performances in the field of magnetic resonance (MR) image reconstruction. Nevertheless, to properly learn a powerful and robust model, these methods generally require large quantities…

While some powerful neural network architectures (e.g., Transformer, Graph Neural Networks) have achieved improved performance in sequential recommendation with high-order item dependency modeling, they may suffer from poor representation…

Speaker verification can be formulated as a representation learning task, where speaker-discriminative embeddings are extracted from utterances of variable lengths. Momentum Contrast (MoCo) is a recently proposed unsupervised representation…

Dense retrieval calls for discriminative embeddings to represent the semantic relationship between query and document. It may benefit from the using of large language models (LLMs), given LLMs' strong capability on semantic understanding.…

Learning continually from a stream of non-i.i.d. data is an open challenge in deep learning, even more so when working in resource-constrained environments such as embedded devices. Visual models that are continually updated through…

Cross-modal alignment Learning integrates information from different modalities like text, image, audio and video to create unified models. This approach develops shared representations and learns correlations between modalities, enabling…

Recent studies have demonstrated that pre-trained cross-lingual models achieve impressive performance in downstream cross-lingual tasks. This improvement benefits from learning a large amount of monolingual and parallel corpora. Although it…

The advent of pre-trained Vision-Language Models (VLMs) has significantly transformed Continual Learning (CL), mainly due to their zero-shot classification abilities. Such proficiency makes VLMs well-suited for real-world applications,…

Recently, more and more people study online for the convenience of access to massive learning materials (e.g. test questions/notes), thus accurately understanding learning materials became a crucial issue, which is essential for many…

Many applications require linking individuals, firms, or locations across datasets. Most widely used methods, especially in social science, do not employ deep learning, with record linkage commonly approached using string matching…

This study explores the application of self-supervised learning techniques for event sequences. It is a key modality in various applications such as banking, e-commerce, and healthcare. However, there is limited research on self-supervised…

Large Language Models (LLMs) integrated with agent-based reasoning frameworks have recently shown strong potential for autonomous decision-making and system-level operations. One promising yet underexplored direction is microservice…

As the real propagation environment becomes in creasingly complex and dynamic, millimeter wave beam prediction faces huge challenges. However, the powerful cross modal representation capability of vision-language model (VLM) provides a…