Related papers: PSQE: A Theoretical-Practical Approach to Pseudo S…

Machine learning based malware detectors become obsolete over time due to concept drift in benign and malware applications. Recent methods rely on fully labeled data and use hierarchical contrastive loss (HCL) with active learning to…

Image aesthetic enhancement aims to perceive aesthetic deficiencies in images and perform corresponding editing operations, which is highly challenging and requires the model to possess creativity and aesthetic perception capabilities.…

Generalized Entity Matching (GEM), which aims at judging whether two records represented in different formats refer to the same real-world entity, is an essential task in data management. The prompt tuning paradigm for pre-trained language…

With the development of fast and massively parallel evaluations in many domains, Quality-Diversity (QD) algorithms, that already proved promising in a large range of applications, have seen their potential multiplied. However, we have yet…

Multimodal information extraction (MIE) aims to extract structured information from unstructured multimedia content. Due to the diversity of tasks and settings, most current MIE models are task-specific and data-intensive, which limits…

Prevailing LLM serving engines employ expert parallelism (EP) to implement multi-device inference of massive MoE models. However, the efficiency of expert parallel inference is largely bounded by inter-device communication, as EP embraces…

We propose a pre-training strategy called Multi-modal Multi-task Masked Autoencoders (MultiMAE). It differs from standard Masked Autoencoding in two key aspects: I) it can optionally accept additional modalities of information in the input…

Sentence embedding tasks are important in natural language processing (NLP), but improving their performance while keeping them reliable is still hard. This paper presents a framework that combines pseudo-label generation and model ensemble…

Entity Alignment (EA) is essential for knowledge graph (KG) fusion, but existing benchmarks often allow models to exploit name overlap rather than relational structure. This makes it difficult to evaluate whether models can reject same-name…

Multimodal Sentiment Analysis (MSA) integrates complementary features from text, video, and audio for robust emotion understanding in human interactions. However, models suffer from severe data scarcity and high annotation costs, severely…

Remarkable effectiveness of the channel or spatial attention mechanisms for producing more discernible feature representation are illustrated in various computer vision tasks. However, modeling the cross-channel relationships with channel…

Masked Autoencoder (MAE) has demonstrated superior performance on various vision tasks via randomly masking image patches and reconstruction. However, effective data augmentation strategies for MAE still remain open questions, different…

Parameter-efficient transfer learning (PETL) has emerged as a pivotal paradigm for adapting pre-trained foundation models to downstream tasks, significantly reducing trainable parameters yet suffering from substantial memory overhead caused…

In this paper, we aim at tackling a general but interesting cross-modality feature learning question in remote sensing community --- can a limited amount of highly-discrimin-ative (e.g., hyperspectral) training data improve the performance…

Cross-lingual representation learning transfers knowledge from resource-rich data to resource-scarce ones to improve the semantic understanding abilities of different languages. However, previous works rely on shallow unsupervised data…

Recent speech enhancement (SE) models increasingly leverage self-supervised learning (SSL) representations for their rich semantic information. Typically, intermediate features are aggregated into a single representation via a lightweight…

Machine Translation Quality Estimation (QE) is the task of evaluating translation output in the absence of human-written references. Due to the scarcity of human-labeled QE data, previous works attempted to utilize the abundant unlabeled…

Multimodal Entity Linking (MEL) aims to associate textual and visual mentions with entities in a multimodal knowledge graph. Despite its importance, current methods face challenges such as incomplete contextual information, coarse…

Large Mixture of Experts (MoE) models could achieve state-of-the-art quality on various language tasks, including machine translation task, thanks to the efficient model scaling capability with expert parallelism. However, it has brought a…

Grounded Multimodal Named Entity Recognition (GMNER) is an emerging information extraction (IE) task, aiming to simultaneously extract entity spans, types, and corresponding visual regions of entities from given sentence-image pairs data.…