Related papers: Learn Before Represent: Bridging Generative and Co…

In the past year, Generative Recommendations (GRs) have undergone substantial advancements, especially in leveraging the powerful sequence modeling and reasoning capabilities of Large Language Models (LLMs) to enhance overall recommendation…

Continual learning (CL) has emerged as a pivotal paradigm to enable large language models (LLMs) to dynamically adapt to evolving knowledge and sequential tasks while mitigating catastrophic forgetting-a critical limitation of the static…

Tremendous breakthroughs have been developed in Semi-Supervised Semantic Segmentation (S4) through contrastive learning. However, due to limited annotations, the guidance on unlabeled images is generated by the model itself, which…

Recent self-supervised contrastive methods have been able to produce impressive transferable visual representations by learning to be invariant to different data augmentations. However, these methods implicitly assume a particular set of…

Reinforcement learning (RL) has shown impressive results in sequential decision-making tasks. Meanwhile, Large Language Models (LLMs) and Vision-Language Models (VLMs) have emerged, exhibiting impressive capabilities in multimodal…

Among different existing graph self-supervised learning strategies, graph contrastive learning (GCL) has been one of the most prevalent approaches to this problem. Despite the remarkable performance those GCL methods have achieved, existing…

Understanding vision and language representations of product content is vital for search and recommendation applications in e-commerce. As a backbone for online shopping platforms and inspired by the recent success in representation…

Multilingual generative models obtain remarkable cross-lingual in-context learning capabilities through pre-training on large-scale corpora. However, they still exhibit a performance bias toward high-resource languages and learn isolated…

Data augmentation is a crucial component in unsupervised contrastive learning (CL). It determines how positive samples are defined and, ultimately, the quality of the learned representation. In this work, we open the door to new…

Recommender systems have seen significant advancements with the influence of deep learning and graph neural networks, particularly in capturing complex user-item relationships. However, these graph-based recommenders heavily depend on…

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by integrating external knowledge, where the LLM's ability to generate responses based on the combination of a given query and retrieved documents is crucial.…

The learn-to-compare paradigm of contrastive representation learning (CRL), which compares positive samples with negative ones for representation learning, has achieved great success in a wide range of domains, including natural language…

In reinforcement learning (RL), it is easier to solve a task if given a good representation. While deep RL should automatically acquire such good representations, prior work often finds that learning representations in an end-to-end fashion…

Though language model text embeddings have revolutionized NLP research, their ability to capture high-level semantic information, such as relations between entities in text, is limited. In this paper, we propose a novel contrastive learning…

Masked language models (MLMs) such as BERT and RoBERTa have revolutionized the field of Natural Language Understanding in the past few years. However, existing pre-trained MLMs often output an anisotropic distribution of token…

Generative Commonsense Reasoning (GCR) requires a model to reason about a situation using commonsense knowledge, while generating coherent sentences. Although the quality of the generated sentences is crucial, the diversity of the…

Graph neural networks (GNNs) have advanced recommender systems by modeling interaction relationships. However, existing graph-based recommenders rely on sparse ID features and do not fully exploit textual information, resulting in low…

Ensuring that Large Language Models (LLMs) generate text representative of diverse sub-populations is essential, particularly when key concepts related to under-represented groups are scarce in the training data. We address this challenge…

Bundle Recommendation (BR) aims at recommending bundled items on online content or e-commerce platform, such as song lists on a music platform or book lists on a reading website. Several graph based models have achieved state-of-the-art…

Reinforcement Learning with Verifiable Rewards (RLVR) plays a key role in stimulating the explicit reasoning capability of Large Language Models (LLMs). We can achieve expert-level performance in some specific domains via RLVR, such as…