Related papers: Instruction-aware User Embedding via Synergistic L…

Pre-trained language models (PLMs) have made significant advances in natural language inference (NLI) tasks, however their sensitivity to textual perturbations and dependence on large datasets indicate an over-reliance on shallow…

With recent advances in Multimodal Large Language Models (MLLMs) showing strong visual understanding and reasoning, interest is growing in using them to improve the editing performance of diffusion models. Despite rapid progress, most…

Recently, semantically constrained adversarial examples (SemanticAE), which are directly generated from natural language instructions, have become a promising avenue for future research due to their flexible attacking forms. To generate…

Image-text multimodal representation learning aligns data across modalities and enables important medical applications, e.g., image classification, visual grounding, and cross-modal retrieval. In this work, we establish a connection between…

The successful integration of large language models (LLMs) into recommendation systems has proven to be a major breakthrough in recent studies, paving the way for more generic and transferable recommendations. However, LLMs struggle to…

Representation learning is fundamental to modern machine learning, powering applications such as text retrieval and multimodal understanding. However, learning robust and generalizable representations remains challenging. While prior work…

We present ImageBind-LLM, a multi-modality instruction tuning method of large language models (LLMs) via ImageBind. Existing works mainly focus on language and image instruction tuning, different from which, our ImageBind-LLM can respond to…

Artificial Neural Networks are powerful function approximators capable of modelling solutions to a wide variety of problems, both supervised and unsupervised. As their size and expressivity increases, so too does the variance of the model,…

Learning precise representations of users and items to fit observed interaction data is the fundamental task of collaborative filtering. Existing studies usually infer entangled representations to fit such interaction data, neglecting to…

Learning sentence embeddings from dialogues has drawn increasing attention due to its low annotation cost and high domain adaptability. Conventional approaches employ the siamese-network for this task, which obtains the sentence embeddings…

Most existing time series classification methods adopt a discriminative paradigm that maps input sequences directly to one-hot encoded class labels. While effective, this paradigm struggles to incorporate contextual features and fails to…

This paper explores the intricate relationship between interpretability and robustness in deep learning models. Despite their remarkable performance across various tasks, deep learning models often exhibit critical vulnerabilities,…

User modeling, which learns to represent users into a low-dimensional representation space based on their past behaviors, got a surge of interest from the industry for providing personalized services to users. Previous efforts in user…

The lack of labeled data is a major obstacle to learning high-quality sentence embeddings. Recently, self-supervised contrastive learning (SCL) is regarded as a promising way to address this problem. However, the existing works mainly rely…

Modeling a sequence of interactions between users and items (e.g., products, posts, or courses) is crucial in domains such as e-commerce, social networking, and education to predict future interactions. Representation learning presents an…

Recently, multi-view learning (MVL) has garnered significant attention due to its ability to fuse discriminative information from multiple views. However, real-world multi-view datasets are often heterogeneous and imperfect, which usually…

In this paper, we present an Adaptive Ensemble Learning framework that aims to boost the performance of deep neural networks by intelligently fusing features through ensemble learning techniques. The proposed framework integrates ensemble…

Instruction-tuned large language models have revolutionized natural language processing and have shown great potential in applications such as conversational agents. These models, such as GPT-4, can not only master language but also solve…

Large-scale pre-training and instruction tuning have been successful at creating general-purpose language models with broad competence. However, building general-purpose vision-language models is challenging due to the rich input…

Objective and scalable measurement of teaching quality is a persistent challenge in education. While Large Language Models (LLMs) offer potential, general-purpose models have struggled to reliably apply complex, authentic classroom…