Related papers: CMML: Contextual Modulation Meta Learning for Cold…

Large Multimodal Models (LMMs) exhibit remarkable multi-tasking ability by learning mixed instruction datasets. However, novel tasks would be encountered sequentially in dynamic world, which urges for equipping LMMs with multimodal…

A central capability of intelligent systems is the ability to continuously build upon previous experiences to speed up and enhance learning of new tasks. Two distinct research paradigms have studied this question. Meta-learning views this…

In-Context Learning (ICL) empowers Large Language Models (LLMs) for rapid task adaptation without Fine-Tuning (FT), but its reliance on demonstration selection remains a critical challenge. While many-shot ICL shows promising performance…

Collaborative Metric Learning (CML) has recently emerged as a popular method in recommendation systems (RS), closing the gap between metric learning and collaborative filtering. Following the convention of RS, existing practices exploit…

Modern recommender systems operate in uniquely dynamic settings: user interests, item pools, and popularity trends shift continuously, and models must adapt in real time without forgetting past preferences. While existing tutorials on…

Recommender systems serve as foundational infrastructure in modern information ecosystems, helping users navigate digital content and discover items aligned with their preferences. At their core, recommender systems address a fundamental…

A major challenge of reinforcement learning (RL) in real-world applications is the variation between environments, tasks or clients. Meta-RL (MRL) addresses this issue by learning a meta-policy that adapts to new tasks. Standard MRL methods…

Meta learning is a promising solution to few-shot learning problems. However, existing meta learning methods are restricted to the scenarios where training and application tasks share the same out-put structure. To obtain a meta model…

We formalize a new concept for LLMs, context-enhanced learning. It involves standard gradient-based learning on text except that the context is enhanced with additional data on which no auto-regressive gradients are computed. This setting…

We examine Contextualized Machine Learning (ML), a paradigm for learning heterogeneous and context-dependent effects. Contextualized ML estimates heterogeneous functions by applying deep learning to the meta-relationship between contextual…

Recently, relational metric learning methods have been received great attention in recommendation community, which is inspired by the translation mechanism in knowledge graph. Different from the knowledge graph where the entity-to-entity…

Traditional ID-based recommender systems often struggle with cold-start and generalization challenges. Multimodal recommendation systems, which leverage textual and visual data, offer a promising solution to mitigate these issues. However,…

Learning new tasks by drawing on prior experience gathered from other (related) tasks is a core property of any intelligent system. Gradient-based meta-learning, especially MAML and its variants, has emerged as a viable solution to…

Large-scale models trained on extensive datasets have become the standard due to their strong generalizability across diverse tasks. In-context learning (ICL), widely used in natural language processing, leverages these models by providing…

Conditional Maximum Mean Discrepancy (CMMD) can capture the discrepancy between conditional distributions by drawing support from nonlinear kernel functions, thus it has been successfully used for pattern classification. However, CMMD does…

Selecting appropriate physical models is a critical yet difficult step in many areas of computational science and engineering. In multiphase Computational Fluid Dynamics (CFD), practitioners must choose among numerous closure model…

A well-designed recommender system can accurately capture the attributes of users and items, reflecting the unique preferences of individuals. Traditional recommendation techniques usually focus on modeling the singular type of behaviors…

Multimodal recommendation combines the user historical behaviors with the modal features of items to capture the tangible user preferences, presenting superior performance compared to the conventional ID-based recommender systems. However,…

Meta-gradient methods (Xu et al., 2018; Zahavy et al., 2020) offer a promising solution to the problem of hyperparameter selection and adaptation in non-stationary reinforcement learning problems. However, the properties of meta-gradients…

The cold-start issue is the challenge when we talk about recommender systems, especially in the case when we do not have the past interaction data of new users or new items. Content-based features or hybrid solutions are common as…