Related papers: BM25 Query Augmentation Learned End-to-End

Continual learning is an emerging topic in the field of deep learning, where a model is expected to learn continuously for new upcoming tasks without forgetting previous experiences. This field has witnessed numerous advancements, but few…

Data augmentation is an effective technique to improve the generalization of deep neural networks. Recently, AutoAugment proposed a well-designed search space and a search algorithm that automatically finds augmentation policies in a…

Transformers have become central to natural language processing and large language models, but their deployment at scale faces three major challenges. First, the attention mechanism requires massive matrix multiplications and frequent…

Due to the concise and structured nature of tables, the knowledge contained therein may be incomplete or missing, posing a significant challenge for table question answering (TableQA) and data analysis systems. Most existing datasets either…

Deep neural network based full-band speech enhancement systems face challenges of high demand of computational resources and imbalanced frequency distribution. In this paper, a light-weight full-band model is proposed with two dedicated…

Indexes can significantly improve search performance in relational databases. However, if the query workload changes frequently or new data updates occur continuously, it may not be worthwhile to build a conventional index upfront for query…

In order to reduce overfitting, neural networks are typically trained with data augmentation, the practice of artificially generating additional training data via label-preserving transformations of existing training examples. While these…

Binary neural networks (BNNs), where both weights and activations are binarized into 1 bit, have been widely studied in recent years due to its great benefit of highly accelerated computation and substantially reduced memory footprint that…

The general capabilities of Large Language Models (LLM) highly rely on the composition and selection on extensive pretraining datasets, treated as commercial secrets by several institutions. To mitigate this issue, we open-source the…

We present MM1.5, a new family of multimodal large language models (MLLMs) designed to enhance capabilities in text-rich image understanding, visual referring and grounding, and multi-image reasoning. Building upon the MM1 architecture,…

We present REARANK, a large language model (LLM)-based listwise reasoning reranking agent. REARANK explicitly reasons before reranking, significantly improving both performance and interpretability. Leveraging reinforcement learning and…

In the absence of large labelled datasets, self-supervised learning techniques can boost performance by learning useful representations from unlabelled data, which is often more readily available. However, there is often a domain shift…

This paper describes a compact and effective model for low-latency passage retrieval in conversational search based on learned dense representations. Prior to our work, the state-of-the-art approach uses a multi-stage pipeline comprising…

Over recent years, an increasing amount of compute and data has been poured into training large language models (LLMs), usually by doing one-pass learning on as many tokens as possible randomly selected from large-scale web corpora. While…

As agents operate over long horizons, their memory stores grow continuously, making retrieval critical to accessing relevant information. Many agent queries require reasoning-intensive retrieval, where the connection between query and…

Deep neural nets typically perform end-to-end backpropagation to learn the weights, a procedure that creates synchronization constraints in the weight update step across layers and is not biologically plausible. Recent advances in…

Transformer-based document cross-encoder rerankers are a central component of modern information retrieval systems. Despite their success, these models suffer from high computational costs due to processing long query-document sequences at…

We present a contrasting learning approach with data augmentation techniques to learn document representations in an unsupervised manner. Inspired by recent contrastive self-supervised learning algorithms used for image and NLP pretraining,…

Deep Imitation Learning requires a large number of expert demonstrations, which are not always easy to obtain, especially for complex tasks. A way to overcome this shortage of labels is through data augmentation. However, this cannot be…

We introduce a novel approach to options trading strategies using a highly scalable and data-driven machine learning algorithm. In contrast to traditional approaches that often require specifications of underlying market dynamics or…