Related papers: LogiCoL: Logically-Informed Contrastive Learning f…
The rapid growth of Large Language Models (LLMs) usage has highlighted the importance of gradient-free in-context learning (ICL). However, interpreting their inner workings remains challenging. This paper introduces a novel multimodal…
Dense retrieval has become the new paradigm in passage retrieval. Despite its effectiveness on typo-free queries, it is not robust when dealing with queries that contain typos. Current works on improving the typo-robustness of dense…
Multimodal recommendation systems integrate diverse multimodal information into the feature representations of both items and users, thereby enabling a more comprehensive modeling of user preferences. However, existing methods are hindered…
Unsupervised contrastive learning achieves great success in learning image representations with CNN. Unlike most recent methods that focused on improving accuracy of image classification, we present a novel contrastive learning approach,…
Universal Multimodal embedding models built on Multimodal Large Language Models (MLLMs) have traditionally employed contrastive learning, which aligns representations of query-target pairs across different modalities. Yet, despite its…
Multimodal Contrastive Learning (MCL) advances in aligning different modalities and generating multimodal representations in a joint space. By leveraging contrastive learning across diverse modalities, large-scale multimodal data enhances…
In simple open-domain question answering (QA), dense retrieval has become one of the standard approaches for retrieving the relevant passages to infer an answer. Recently, dense retrieval also achieved state-of-the-art results in multi-hop…
Search-augmented reasoning agents interleave multi-step reasoning with external information retrieval, but uncontrolled retrieval often leads to redundant evidence, context saturation, and unstable learning. Existing approaches rely on…
In addition to relevance, diversity is an important yet less studied performance metric of cross-modal image retrieval systems, which is critical to user experience. Existing solutions for diversity-aware image retrieval either explicitly…
Multimodal contrastive learning is a methodology for linking different data modalities; the canonical example is linking image and text data. The methodology is typically framed as the identification of a set of encoders, one for each…
Curriculum learning (CL), motivated by the intuition that learning in increasing order of difficulty should ease generalization, is commonly adopted both in pre-training and post-training of large language models (LLMs). The intuition of CL…
In modern e-commerce search systems, dense retrieval has become an indispensable component. By computing similarities between query and item (product) embeddings, it efficiently selects candidate products from large-scale repositories. With…
Contrastive learning (CL) methods effectively learn data representations in a self-supervision manner, where the encoder contrasts each positive sample over multiple negative samples via a one-vs-many softmax cross-entropy loss. By…
knowledge graph-based recommendation methods have achieved great success in the field of recommender systems. However, over-reliance on high-quality knowledge graphs is a bottleneck for such methods. Specifically, the long-tailed…
Current sequential recommender systems are proposed to tackle the dynamic user preference learning with various neural techniques, such as Transformer and Graph Neural Networks (GNNs). However, inference from the highly sparse user behavior…
Session-based recommendation, which aims to predict the next item of users' interest as per an existing sequence interaction of items, has attracted growing applications of Contrastive Learning (CL) with improved user and item…
Despite exciting progress in causal language models, the expressiveness of the representations is largely limited due to poor discrimination ability. To remedy this issue, we present ContraCLM, a novel contrastive learning framework at both…
Recommender systems usually rely on observed user interaction data to build personalized recommendation models, assuming that the observed data reflect user interest. However, user interacting with an item may also due to conformity, the…
Pre-trained contrastive vision-language models have demonstrated remarkable performance across a wide range of tasks. However, they often struggle on fine-trained datasets with categories not adequately represented during pre-training,…
LLMs have fundamentally transformed dense retrieval, upgrading backbones from discriminative encoders to generative architectures. However, a critical disconnect remains: while LLMs possess strong reasoning capabilities, current retrievers…