Related papers: Learning Vector-Quantized Item Representation for …

Understanding visual inputs for a given task amidst varied changes is a key challenge posed by visual reinforcement learning agents. We propose \textit{Value Explicit Pretraining} (VEP), a method that learns generalizable representations…

Visual concept learning, also known as Text-to-image personalization, is the process of teaching new concepts to a pretrained model. This has numerous applications from product placement to entertainment and personalized design. Here we…

To successfully apply trained neural network models to new domains, powerful transfer learning solutions are essential. We propose to introduce a novel cross-domain latent modulation mechanism to a variational autoencoder framework so as to…

Sequential recommender systems predict items that may interest users by modeling their preferences based on historical interactions. Traditional sequential recommendation methods rely on capturing implicit collaborative filtering signals…

Unsupervised text embedding methods, such as Skip-gram and Paragraph Vector, have been attracting increasing attention due to their simplicity, scalability, and effectiveness. However, comparing to sophisticated deep learning architectures…

Large Language Models (LLMs) have been integrated into recommendation systems to enhance user behavior comprehension. The Retrieval Augmented Generation (RAG) technique is further incorporated into these systems to retrieve more relevant…

Uncovering emergent concepts across transformer layers remains a significant challenge because the residual stream linearly mixes and duplicates information, obscuring how features evolve within large language models. Current research…

Providing user-understandable explanations to justify recommendations could help users better understand the recommended items, increase the system's ease of use, and gain users' trust. A typical approach to realize it is natural language…

Visual transfer learning for unseen categories presents an active research topic yet a challenging task, due to the inherent conflict between preserving category-specific representations and acquiring transferable knowledge. Vision-Language…

Token-based video representation has emerged as a promising approach for enabling large language models (LLMs) to interpret video content. However, existing token reduction techniques, such as pruning and merging, often disrupt essential…

Sequential recommendation aims to model dynamic user behavior from historical interactions. Existing methods rely on either explicit item IDs or general textual features for sequence modeling to understand user preferences. While promising,…

Recent advancements of sequential deep learning models such as Transformer and BERT have significantly facilitated the sequential recommendation. However, according to our study, the distribution of item embeddings generated by these models…

Large Language Models (LLMs) have recently emerged as a powerful paradigm for Knowledge Graph Completion (KGC), offering strong reasoning and generalization capabilities beyond traditional embedding-based approaches. However, existing…

Large Language Models (LLMs) have emerged as promising recommendation systems, offering novel ways to model user preferences through generative approaches. However, many existing methods often rely solely on text semantics or incorporate…

Recommendation system plays an important role in online web applications. Sequential recommender further models user short-term preference through exploiting information from latest user-item interaction history. Most of the sequential…

Semantic ID learning is a key interface in Generative Recommendation (GR) models, mapping items to discrete identifiers grounded in side information, most commonly via a pretrained text encoder. However, these text encoders are primarily…

A recommender system predicts users' potential interests in items, where the core is to learn user/item embeddings. Nevertheless, it suffers from the data-sparsity issue, which the cross-domain recommendation can alleviate. However, most…

Sequential recommender systems rank relevant items by modeling a user's interaction history and computing the inner product between the resulting user representation and stored item embeddings. To avoid the significant memory overhead of…

Recommender systems are one of the most successful applications of machine learning and data science. They are successful in a wide variety of application domains, including e-commerce, media streaming content, email marketing, and…

ID-based Recommender Systems (RecSys), where each item is assigned a unique identifier and subsequently converted into an embedding vector, have dominated the designing of RecSys. Though prevalent, such ID-based paradigm is not suitable for…